Predictive modelling of threshold exceedance and airborne concentrations of Alternaria and Epicoccum spores across bioclimatic regions in Central Europe

Predictive modelling of threshold exceedance and airborne concentrations of Alternaria and Epicoccum spores across bioclimatic regions in Central Europe | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Predictive modelling of threshold exceedance and airborne concentrations of Alternaria and Epicoccum spores across bioclimatic regions in Central Europe Jana Ščevková, Jozef Dušička, Janka Lafférsová, Ondřej Rybníček, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7210967/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 07 Jan, 2026 Read the published version in International Journal of Biometeorology → Version 1 posted 4 You are reading this latest preprint version Abstract Several airborne fungal spores, such as Alternaria and Epicoccum , are known for their allergenic potential, yet accurately predicting their atmospheric concentrations remains a challenge. This study presents predictive models for estimating daily concentrations and clinically relevant threshold exceedance events of Alternaria and Epicoccum spores, using long-term aerobiological and meteorological data from five cities in Central Europe. Key meteorological predictors, including time-lagged variables, were identified for each location, and interpretable lasso linear and lasso logistic regression models were developed to forecast spore levels up to seven days in advance. The lasso logistic models achieved high accuracy in threshold exceedance predictions, with F1 scores reaching up to 88.6% for Epicoccum . While lasso linear models effectively captured seasonal patterns and timing, they tended to underestimate peak concentrations, particularly for Alternaria , likely due to the sporadic nature of spore release events. Notably, this is the first predictive model developed for Epicoccum , underscoring the need for clinical validation of allergological thresholds. Regional variability in model performance highlights the importance of local calibration and sustained aerobiological monitoring. These models offer a promising foundation for operational spore forecasting systems, supporting both public health advisories and agricultural decision-making. Aerobiology Airborne fungal spores Lasso logistic regression Lasso linear regression Weather-based forecasting Figures Figure 1 Figure 2 1 Introduction Airborne fungi, particularly their spores, as well as hyphal and mycelial fragments, constitute a significant fraction of bioaerosols (Elbert et al., 2007 ). Several taxa are considered allergenic and raise concerns for public health, e.g., the genera Alternaria (Pleosporaceae) and Epicoccum (Didymellaceae) are well known for their allergenic potential. Spores of these fungi have been associated with the onset and exacerbation of respiratory diseases, including allergic rhinitis and asthma (Bisht et al., 2002 ; Brito et al., 2012 ; Gabriel et al., 2016 ; Abel-Fernández et al., 2023 ). According to Bousquet et al. ( 2007 ), Alternaria sensitisation was identified in 4.4% of the 11,355 individuals tested as part of the European Community Respiratory Health Survey. In two later studies conducted under the Global Asthma and Allergy European Network (GA²LEN), sensitisation to Alternaria was found in approximately 9% of the 3,034 participants tested for inhalant allergies across 14 European countries (Burbach et al., 2009 ; Heinzerling et al., 2009 ). Although sensitisation to Epicoccum is less frequently reported, co-sensitisation or cross-reactivity with Alternaria is often observed (Portnoy et al., 1987 ; Bisht et al., 2004 ), potentially leading to a stronger immune response and an increased risk of developing or worsening asthma and allergic rhinitis. Both genera are also well recognised for their phytopathogenic potential, causing diseases in a wide range of economically important crops. Alternaria spp. are among the most prevalent fungal pathogens worldwide, responsible for leaf spots, blights, rots, and seedling damping-off in crops such as cereals, vegetables, and fruits (Thomma, 2003 ; Woudenberg et al., 2015 ; Schmey et al., 2024 ). Similarly, species of Epicoccum , although mostly saprophytic and occurring on senescent and dead plant material (Lee et al., 2020 ), have been reported as causal agents of leaf spots and other foliar diseases in crops, including cereals, grapes, and various horticultural plants (Taguiam et al., 2021 ; Balendres et al., 2025 ). The concentration of fungal spores in the atmosphere is shaped by a complex interplay of multiple biotic and abiotic factors, such as vegetation type, land use, meteorological conditions, and seasonal dynamics (Crandall and Gilbert, 2017 ; Anees-Hill et al., 2022 ), resulting in significant spatial variability that can be observed not only between countries but also within regions and individual areas (Ianovici et al., 2013 ; Patel et al., 2018 ; Anees-Hill et al., 2022 ; Renard et al., 2024 ). Although the health and phytopathogenic relevance of Alternaria and Epicoccum is well established, studies focused on predicting their fungal spore concentrations in the air remain limited, with a few papers dealing with Alternaria spores (Aira et al., 2008 ; Tomassetti et al., 2009 ; Vélez-Pereira et al., 2019 ; Grinn-Gofroń et al., 2019 ), but none about Epicoccum . One of the main reasons of their rare use is the methodological challenge of developing reliable predictive models, as aerobiological data often exhibit non-linear relationships and non-normal distributions (e.g., Vélez-Pereira et al., 2021 ). Traditional statistical methods typically assume linearity and normality, which are frequently violated in this context. As a result, threshold-based models and non-linear classification techniques, such as logistic regression and regression trees, have gained traction (Vélez-Pereira et al., 2019 ; Reich et al., 2024 ). These methods are well-suited for binary outcomes, such as whether or not a defined concentration threshold is exceeded, and offer a more interpretable and computationally efficient alternative to more complex machine learning approaches. Accurate forecasting of allergenic and phytopathogenic fungal spores is vital for public health and agriculture. Timely predictions enhance early warning systems, support allergy prevention, and enable rapid responses to crop diseases, helping to minimise yield losses. Although advanced modelling techniques are increasingly available, their performance must be assessed across diverse environments. Evaluating models on large datasets from new geographic regions is key to testing their transferability and reliability under varying meteorological and ecological conditions, especially across different phytogeographical zones, where spore dynamics may vary. The aim of this study was therefore to develop and evaluate predictive models for Alternaria and Epicoccum spore concentrations across different bioclimatic regions in Central Europe. By combining aeromycological and meteorological data, we seek to identify key drivers of spore dynamics and establish forecasting tools tailored to specific bioclimatic regions. The results will contribute to a better understanding of the spatiotemporal patterns of allergenic spores and improve the preparedness and management of fungal allergy risks in a changing climate. 2 Materials and methods 2.1 Study area The aeromycological study was conducted in five cities representing diverse geomorphological and climatic conditions across Central Europe: Bratislava (BA) and Banská Bystrica (BB) in Slovakia, and Brno (BR), Prague (PR), and Plzeň (PL) in the Czech Republic (Fig. 1 ; Table 1 ). All sampling sites are characterised by a continental climate but differ in orographic features that influence local temperature and precipitation patterns. BA, situated in the Podunajská nížina Lowland, has the warmest conditions, while BB, surrounded by mountains, experiences lower temperatures and higher precipitation totals. The Czech cities, positioned in various basins and lowlands, exhibit intermediate climatic conditions characterised by moderately warm and relatively dry weather (Table 1 ). Except for BB, all locations are classified as Cfb according to the Köppen-Geiger system (Kottek et al., 2006 ), indicating a warm temperate, fully humid climate with warm summers. In contrast, BB is categorised as Dfb, which corresponds to a fully humid, snowy climate with warm summers. Table 1 Characteristics of the sampling stations in the study areas. Sampling station Years of available spore data Missing years Latitude Longitude Elevation (m a. s. l.) Sampler height (m a. g. l.) Average annual temperature (℃)* Average total annual precipitation (mm)* Bratislava 2002–2024 - N 48.14973 E 17.07375 166 18 11.5 686 Banská Bystrica 2002–2024 2005, 2022 N 48.74204 E 19.16276 367 10 9.4 870 Praha 1993–2024 1994, 2008 N 50.07615 E 14.47313 249 14 11.1 468 Brno 1992–2024 2006–2010 N 49.20369 E 16.61800 227 15 10.6 534 Plzeň 2005–2023 - N 49.72999 E 13.37207 328 20 10.1 532 *meteorological data averaged for 2002–2024 were provided by the Slovak Hydrometeorological Institute and the Czech Meteorological Society Cereal fields and grasslands are the main sources of Alternaria spores. The highest risk of spore exposure occurs during the harvest period, when conditions are optimal for their release and spread through the air (Apangu et al., 2022 ; Rodríguez-Fernández et al., 2023 ). In all monitored sites except BB, the surrounding areas are characterised by intensive agricultural use. BB, situated in a submontane area, is located in a region with limited agricultural activity due to terrain and climatic conditions (Fig. 1 ). 2.2 Aeromycological analysis Fungal spores were captured from the air using a Hirst-type trap (Hirst 1952 ) positioned on building roofs 10–20 meters above the ground (Table 1 ). The monitoring period ranged from 18 years (PL) to 29 years (PR), depending on data availability. All periods fall between 1992 and 2024, with the exact years of observation and any data interruptions detailed in Table 1 . Samples were examined using standardised aerobiological procedures in compliance with the minimum criteria set by the European Aerobiology Society (Galán et al., 2014 ) and the European standard EN 16868:2019. The resulting daily Alternaria and Epicoccum spore concentrations were expressed as the mean daily number of spores per cubic metre of air (spores/m³). To evaluate the seasonal dynamics of the analysed spore taxa, we assessed the Annual Spore Integral (ASIn, the sum of daily spore concentrations throughout the year), peak spore concentration (peak value), peak date, and the number of high days (HD). A high day was defined as a day when the daily spore concentration exceeded 80 spores/m³ for Alternaria and 20 spores/m³ for Epicoccum . For Alternaria , this value is recognised as the threshold for triggering clinical symptoms of fungal spore allergy (Rapiejko et al., 2007 ). However, for Epicoccum , a universally accepted threshold value for eliciting allergic reactions has not been established. The value of 20 spores/m³ used in this study is based on previous aerobiological research practices, where similar levels have been considered indicative of increased exposure risk, although its direct association with clinical symptoms remains to be clarified. 2.3 Meteorological data The following daily meteorological data were included in the predictive modelling: mean, maximum, and minimum temperature (°C), relative humidity (%), precipitation (mm), sunshine duration (h), and wind speed (m/s). The Slovak Hydrometeorological Institute and the Czech Hydrometeorological Institute provided meteorological data used in this study. The distances between the meteorological stations and the aerobiological sampling sites were approximately 0.5 km (BA), 3.7 km (BB), 3.3 km (PR and BR), and 6.5 km (PL). 2.4 Data evaluation and prediction modelling Weekly mean spore concentrations for analysed years were calculated using the pollen_calendar() function from the AeRobiology R package, with the method set to "heatplot". This approach enabled the visualisation of seasonal patterns in spore concentrations across multiple years. To compare ASIn values between monitoring sites for individual years, we applied the Friedman test, including only years with complete data for all localities to ensure valid cross-site comparisons. The test was performed using the PMCMRplus R package, and the Nemenyi post-hoc test from the same package was used to identify significant pairwise differences between localities. We applied statistical models to predict daily airborne fungal spore concentrations in each city from one to seven days in advance, with a focus on identifying relevant meteorological predictors. The primary modelling task was to determine whether the daily concentration would exceed a predefined threshold of 80 spores/m³ for Alternaria and 20 spores/m³ for Epicoccum . In addition, we implemented an extended two-stage model to estimate concentration values on days predicted to have non-zero counts. In all models, the predictors included meteorological variables from the current day and the preceding 13 days – that is, 14 temporal lags per variable. For each meteorological parameter, a single optimal lag was selected based on performance metrics to enhance model interpretability and accuracy. To account for seasonality, we incorporated cyclical calendar variables derived from sine and cosine transformations of the monthly index, which allow for smooth modelling of seasonal patterns. The dataset was chronologically divided into training (up to 2018), validation (2019–2021), and test sets (2022–2024). To prevent information leakage caused by lagged predictors crossing set boundaries, the final two weeks of December were excluded from both the training and validation sets. The classification model for exceedance prediction was fitted using lasso logistic regression via the glmnet package in R. The regularisation parameter lambda was selected by cross-validation on the training set. For each meteorological variable, the most informative lag was chosen based on the area under the ROC curve (AUC), calculated separately within the training set. The final classification threshold (probability cutoff) was optimised on the validation set to maximise the F1 score – the harmonic mean of precision and recall. Model performance was assessed on the test set using standard classification metrics: accuracy (overall correct classification rate), sensitivity (true positive rate), specificity (true negative rate), precision (positive predictive value), F1 score (harmonic mean of sensitivity and precision), and the confusion matrix (counts of true positives, false positives, true negatives, and false negatives). To capture the full concentration profile, we implemented a two-stage modelling approach. In the first stage, a lasso logistic regression model predicted whether the concentration would be strictly positive (i.e., non-zero), using the same methodology described above. In the second stage, a lasso linear regression model was trained to predict spore concentration only on days with observed non-zero values. Given the strong skewness of the data, the response variable was log-transformed. For each predictor, the lag exhibiting the highest Pearson correlation with the log-transformed concentration was selected. Since this regression model did not require separate threshold optimisation, it was trained on the combined training and validation datasets. The regression component was assessed using the mean absolute error (MAE) computed on non-zero days in the test set. We additionally report the MAE improvement compared to a baseline model that predicts a constant mean concentration. Model coefficients (from both logistic and linear models) were ranked based on the estimated impact of a one-standard-deviation increase in each predictor on the model output, providing a clearer interpretation of the relative meteorological influence. 3 Results 3.1 Seasonal patterns and spatial variation of Alternaria and Epicoccum spore concentrations The dynamics of Alternaria and Epicoccum fungal spore concentrations throughout the year for each study area are presented in Fig. 2 . Both types of spores were detected continuously throughout the vegetation period until the end of October. Peak concentrations for both spore types were reached in July in all study areas, except Epicoccum in BA and PL, where the highest spore concentrations were recorded in September and August, respectively. Table 2 summarises the main characteristics of the spore seasons of Alternaria and Epicoccum across the monitored sites. On average, Alternaria exhibited approximately 1.5 times higher seasonal intensity than Epicoccum , as indicated by both the ASIn and peak values. The highest ASIn for Alternaria (17,768 spore*day/m³) was recorded in BR and lowest in PL (7,140 spore*day/m³). For Epicoccum , the highest ASIn was recorded in PL (7,174 spore*day/m³) and lowest in PR (3,473 spore*day/m³). The highest mean peak values for both genera were detected in BR (1,214 spores/m³ for Alternaria , 369 spores/m³ for Epicoccum ), and the lowest in PL and PR (336 spores/m³ for Alternaria , 162 spores/m³ for Epicoccum , respectively). Alternaria had the highest number of HD in BA (63) lowest in PL (30), while the highest number of HD for Epicoccum was recorded in PL (108) and lowest in PR (52). On average, the peak date of Alternaria occurred 29 days earlier than that of Epicoccum . Table 2 Descriptive statistics of the airborne Alternaria and Epicoccum spore data: Annual Spore Integral (ASIn, the sum of daily spore concentrations throughout the year), peak value, peak date and number of high days (HD, days when the daily spore concentration exceeded 80 spores/m³ for Alternaria and 20 spores/m³ for Epicoccum ) in five study areas over the analysed years shown in Table 1 . Abbreviations of the study areas are provided in Section 2.1 . Sampling station Taxon ASIn (spore*day/m 3 ) Peak value (spores/m 3 ) Peak date (DOY) HD (days) Mean Max Min SD Mean Max Min SD Mean Max Min SD Mean Max Min SD BA Alternaria 16,794 33,196 4,432 7,009.6 621 1,472 87 336.7 221 278 166 37.1 63 104 1 26.6 Epicoccum 6,093 13,414 1,578 2,950.8 278 725 37 175.9 273 300 242 14.3 86 133 9 35.6 BB Alternaria 13,791 28,064 2,999 6,899.4 661 1,588 161 318.5 223 274 173 26.2 50 90 1 27.3 Epicoccum 4,710 12,759 786 3,201.4 213 432 54 100.6 233 287 112 39.2 63 122 11 34.0 PR Alternaria 11,625 27,177 2,678 6,497.1 701 1,708 228 444.8 211 238 190 12.4 39 74 10 15.8 Epicoccum 3,473 7,738 992 1,730.6 162 361 53 78.2 238 303 190 29.0 52 97 13 22.2 BR Alternaria 17,768 39,146 5,712 7,614.6 1,214 4,334 382 878.3 215 281 179 27.2 57 92 24 15.8 Epicoccum 5,578 9,898 1,091 2,390.4 369 1,203 62 274.0 262 302 197 30.6 68 99 16 21.9 PL Alternaria 7,140 14,559 3,064 3,378.6 336 778 119 150.0 219 237 197 11.3 30 74 3 22.3 Epicoccum 7,174 13,161 3,890 2,631.7 163 260 86 46.1 227 281 187 21.2 108 158 55 26.3 DOY – day of the year from 1 January According to the Friedman test, there was a statistically significant difference in Alternaria ASIn values between the 5 study sites (χ² = 24.36, p < 0.001). Pairwise comparisons revealed significant differences between PL and all other cities ( p < 0.01–0.001) except PR, while no significant differences were found among the remaining localities. For Epicoccum , the inter-site differences were also significant (χ² = 22.65, p < 0.001). Significant pairwise differences were observed between PR and BA ( p < 0.001) and between PR and PL ( p < 0.001). No other pairwise comparisons showed statistically significant differences. 3.2 Forecasting methods for airborne spore concentrations To forecast airborne fungal spore concentrations, two modelling approaches were implemented: lasso logistic regression to predict exceedance events of predefined concentration thresholds (80 spores/m³ for Alternaria and 20 spores/m³ for Epicoccum ), and lasso linear regression to estimate daily spore concentrations for the mentioned fungal taxa. Both model types were developed for five monitoring stations and validated over 1- to 7-day forecast horizons. Since model performance was consistent across horizons (Table 3 ), detailed results for only the 7-day-ahead forecasts are reported in Tables 4 – 7 , while full outputs for all horizons are provided in the Supplementary material (Tables S1–S20). Table 3 Descriptive statistics of model performance for lasso logistic regression (exceedance prediction) and lasso linear regression (concentration prediction) of Alternaria ( Alt ) and Epicoccum ( Epi ) spore levels across five monitoring sites, based on forecasts from 1- to 7-day prediction horizons. Sampling station Regression model Metric (%) Mean Max Min SD Bratislava Lasso logistic Alt _F1 score (> 80 spores/m 3 ) 70.6 71.3 70.1 0.5 Epi _F1 score (> 20 spores/m 3 ) 80.6 81 79.9 0.4 Alt _F1 score (> 0 spores/m 3 ) 99.3 99.4 99.2 0.1 Epi _F1 score (> 0 spores/m 3 ) 95.5 96 94.9 0.4 Lasso linear Alt _MAE_improv. 19.5 19.6 19.4 0.1 Epi _MAE_improv. 18.4 18.6 18.2 0.2 Banská Bystrica Lasso logistic Alt _F1 score (> 80 spores/m 3 ) 78.5 81.1 76.9 1.3 Epi _F1 score (> 20 spores/m 3 ) 57.9 58.7 57.5 0.4 Alt _F1 score (> 0 spores/m 3 ) 92.0 92.4 91.7 0.3 Epi _F1 score (> 0 spores/m 3 ) 77.1 78 76.2 0.7 Lasso linear Alt _MAE_improv. 21.4 23.8 20.8 1.1 Epi _MAE_improv. 15.8 16 15.3 0.2 Praha Lasso logistic Alt _F1 score (> 80 spores/m 3 ) 60.4 61.3 59.1 0.7 Epi _F1 score (> 20 spores/m 3 ) 52.1 52.5 51.5 0.4 Alt _F1 score (> 0 spores/m 3 ) 89.2 89.7 88.9 0.3 Epi _F1 score (> 0 spores/m 3 ) 82.3 83.2 81.4 0.8 Lasso linear Alt _MAE_improv. 15.7 16.1 15.3 0.3 Epi _MAE_improv. 10.1 11.4 6.4 1.8 Brno Lasso logistic Alt _F1 score (> 80 spores/m 3 ) 63.7 64.7 62.8 0.7 Epi _F1 score (> 20 spores/m 3 ) 66.6 67.8 64.9 0.9 Alt _F1 score (> 0 spores/m 3 ) 84.4 84.6 84.2 0.1 Epi _F1 score (> 0 spores/m 3 ) 79.5 80.2 77.3 1.0 Lasso linear Alt _MAE_improv. 26.0 28.1 25.1 1.0 Epi _MAE_improv. 26.0 29.2 22.1 2.2 Plzeň Lasso logistic Alt _F1 score (> 80 spores/m 3 ) 75.1 76.1 73.3 0.9 Epi _F1 score (> 20 spores/m 3 ) 88.6 91.9 85 2.7 Alt _F1 score (> 0 spores/m 3 ) 89.1 89.9 88.3 0.5 Epi _F1 score (> 0 spores/m 3 ) 89.2 89.7 88.9 0.3 Lasso linear Alt _MAE_improv. 22.7 23.2 22.5 0.2 Epi _MAE_improv. 34.2 34.8 33.6 0.5 Table 4 Lasso logistic regression results predicting the exceedance of 80 Alternaria spores/m³ in daily airborne concentrations seven days in advance in five study areas. Bratislava Banská Bystrica Praha Brno Plzeň Metrics % Metrics % Metrics % Metrics % Metrics % Accuracy 85.4 Accuracy 89.7 Accuracy 89.6 Accuracy 86.0 Accuracy 91.0 Sensitivity 77.8 Sensitivity 83.2 Sensitivity 76.4 Sensitivity 84.6 Sensitivity 83.6 Specificity 87.7 Specificity 91.5 Specificity 91.1 Specificity 86.3 Specificity 92.4 Precision 65.6 Precision 73.3 Precision 50.0 Precision 50.8 Precision 67.8 F1 score 71.1 F1 score 77.9 F1 score 60.4 F1 score 63.5 F1 score 74.9 Predictor Coeff. Predictor Coeff. Predictor Coeff. Predictor Coeff. Predictor Coeff. month_sin -3.017 month_sin -2.009 month_sin -5.26 month_sin -3.474 month_sin -4.402 month_cos -2.04 month_cos -1.484 month_cos -4.325 month_cos -2.168 month_cos -3.043 T min (lag 8) 0.044 T mean (lag 3) 0.071 T min 0.087 T max 0.047 T min (lag 4) 0.064 T max (lag 13) 0.029 T max (lag 9) 0.051 WS -0.055 T min (lag 9) 0.038 T mean (lag 5) 0.055 RH (lag 13) -0.009 T min (lag 2) 0.015 S (lag 13) 0.015 S (lag 10) -0.009 WS (lag 11) 0.323 P (lag 1) 0.007 P (lag 11) 0.008 P 0.01 RH (lag 13) 0.001 T max (lag 6) 0.019 WS (lag 7) -0.012 RH (lag 9) 0 T mean 0 P (lag 13) 0.002 S (lag 9) 0.025 T mean (lag 13) 0 S (lag 9) 0 T max 0 T mean (lag 10) 0 RH (lag 12) 0 S (lag 12) 0 WS (lag 11) 0 RH (lag 13) 0 WS (lag 3) 0 P 0 T mean − mean air temperature; T min − minimum air temperature; T max − maximum air temperature; P – precipitation; RH – relative humidity; S – sunshine; WS – wind speed Table 7 Lasso linear regression results predicting daily airborne Epicoccum spore concentrations seven days in advance in five study areas. Bratislava Banská Bystrica Praha Brno Plzeň Classification Metric % Metric % Metric % Metric % Metric % Accuracy 93.8 Accuracy 73.6 Accuracy 86.8 Accuracy 79.0 Accuracy 85.3 Sensitivity 94.2 Sensitivity 82.8 Sensitivity 78.0 Sensitivity 77.2 Sensitivity 86.6 Specificity 93.1 Specificity 63.3 Specificity 92.1 Specificity 81.0 Specificity 82.8 Precision 96.5 Precision 71.4 Precision 85.6 Precision 82.1 Precision 91.4 F1 score 95.3 F1 score 76.7 F1 score 81.6 F1 score 79.6 F1 score 88.9 Predictor Coeff. Predictor Coeff. Predictor Coeff. Predictor Coeff. Predictor Coeff. month_cos -2.459 month_cos -1.442 month_sin -2.437 month_cos -1.808 month_cos -3.513 T mean -0.115 month_sin -0.977 month_cos -1.717 month_sin -1.637 T max 0.14 T max 0.096 T max (lag 2) 0.062 T mean (lag 13) 0.026 T max (lag 13) 0.043 T mean -0.164 month_sin -1.298 S (lag 11) 0.039 S (lag 13) 0.02 T min (lag 9) 0.019 month_sin -1.59 T min (lag 1) 0.046 T min (lag 3) 0.02 T min (lag 12) 0.012 P (lag 13) 0.03 RH (lag 13) 0.051 WS 0.032 RH (lag 12) 0.009 T max (lag 13) 0.007 S (lag 13) 0.008 T min 0.055 P (lag 13) 0.008 WS (lag 11) 0.103 WS (lag 8) -0.005 WS (lag 9) -0.011 S (lag 9) 0.037 RH (lag 13) 0.003 P (lag 2) 0.007 P (lag 3) -0.001 T mean (lag 13) 0 WS (lag 12) -0.04 S (lag 7) 0.006 T mean (lag 3) 0 RH (lag 13) 0 RH (lag 13) 0 P (lag 13) 0 Regression Metric Value Metric Value Metric Value Metric Value Metric Value MAE_model 31.16 MAE_model 16.05 MAE_model 11.21 MAE_model 15.72 MAE_model 23.54 MAE_baseline 38.23 MAE_baseline 19.04 MAE_baseline 11.98 MAE_baseline 21.41 MAE_baseline 35.72 MAE_imrov. 18.5% MAE_imrov. 15.7% MAE_imrov. 6.4% MAE_imrov. 26.6% MAE_imrov. 34.1% Predictor Coeff. Predictor Coeff. Predictor Coeff. Predictor Coeff. Predictor Coeff. month_sin -1.35 month_sin -0.954 month_sin -1.321 month_sin -1.678 month_sin -1.019 T min (lag 13) 0.026 month_cos -0.271 T mean (lag 9) 0.054 RH (lag 1) 0.012 month_cos -0.681 month_cos -0.152 T max (lag 11) 0.012 T max (lag 9) -0.025 month_cos -0.271 T max (lag 13) 0.013 P (lag 1) 0.006 T mean (lag 13) 0.011 month_cos -0.261 T max (lag 13) -0.005 T mean (lag 11) 0.014 WS (lag 1) -0.014 RH 0.004 RH 0.007 P (lag 2) 0.007 T min (lag 10) 0.012 RH (lag 1) 0.001 P 0.006 T min (lag 10) 0.016 T min (lag 13) 0.004 RH (lag 13) 0.005 T mean (lag 13) 0.001 S (lag 9) 0.007 WS (lag 11) -0.044 WS (lag 1) 0.015 WS (lag 1) -0.059 T max (lag 13) 0 WS 0.002 P 0.005 T mean (lag 13) 0 S (lag 13) -0.007 S (lag 13) 0 T min (lag 13) 0 S (lag 9) -0.003 S (lag 13) 0 P (lag 8) 0.001 T mean − mean air temperature; T min − minimum air temperature; T max − maximum air temperature; P – precipitation; RH – relative humidity; S – sunshine; WS – wind speed 3.2.1 Lasso logistic regression models – prediction of the threshold exceedance Lasso logistic regression models achieved overall good classification accuracy for both taxa. For Alternaria (Tables 4 and S1–S5), the mean sensitivity and specificity across all forecast horizons were 80.3% and 90.3%, respectively. The highest sensitivity was observed in BR (84.6%) and lowest in BA (74.4%). Specificity reached the highest value in PL (93%) and lowest in BR (86.4%). For Epicoccum (Tables 5 and S6–S10), the mean sensitivity and specificity were 81.6% and 88.2%, respectively, with the best sensitivity recorded in BB (89.2%) and the highest specificity in PL (97.2%). Table 5 Lasso logistic regression results predicting the exceedance of 20 Epicoccum spores/m³ in daily airborne concentrations seven days in advance in five study areas. Bratislava Banská Bystrica Praha Brno Plzeň Metrics % Metrics % Metrics % Metrics % Metrics % Accuracy 87.3 Accuracy 82.0 Accuracy 83.7 Accuracy 86.5 Accuracy 93.9 Sensitivity 86.4 Sensitivity 86.3 Sensitivity 81.6 Sensitivity 69.2 Sensitivity 89.6 Specificity 87.7 Specificity 81.3 Specificity 83.9 Specificity 90.7 Specificity 96.6 Precision 74.3 Precision 43.6 Precision 38.1 Precision 64.0 Precision 94.3 F1 score 79.9 F1 score 57.9 F1 score 52.0 F1 score 66.5 F1 score 91.9 Predictor Coeff. Predictor Coeff. Predictor Coeff. Predictor Coeff. Predictor Coeff. month_sin -3.661 month_sin -1.638 month_sin -3.705 month_sin -4.781 month_sin -2.575 month_cos -1.416 T min (lag 2) 0.053 month_cos -1.218 month_cos -1.922 month_cos -1.858 T min (lag 13) 0.077 month_cos -0.555 T min (lag 8) 0.073 T min (lag 13) -0.059 T mean (lag 13) 0.067 RH (lag 13) -0.019 T mean (lag 7) 0.043 WS -0.08 T mean (lag 13) 0.048 T max (lag 8) 0.035 S (lag 13) -0.05 T max (lag 4) 0.034 T mean (lag 11) 0.013 RH (lag 13) 0.023 T min (lag 6) 0.049 P (lag 2) 0.008 RH (lag 13) 0 P 0.017 T max (lag 12) -0.022 RH (lag 13) 0.022 WS (lag 1) 0.027 S (lag 9) 0 T max (lag 13) 0 S (lag 12) 0.029 WS (lag 12) 0.066 T max (lag 13) 0 P 0 RH (lag 13) 0 P (lag 3) 0.017 S (lag 11) 0.01 T mean (lag 13) 0 WS (lag 11) 0 S (lag 13) 0 WS (lag 1) -0.042 P (lag 13) 0.005 T mean − mean air temperature; T min − minimum air temperature; T max − maximum air temperature; P – precipitation; RH – relative humidity; S – sunshine; WS – wind speed F1 scores, which balance sensitivity and precision, reached up to 88.6% for Epicoccum in PL and 78.5% for Alternaria in BB (Table 3 ), suggesting that the models were particularly effective in identifying high-risk days in those locations. Conversely, the lowest F1 scores were observed in PR (60.4% for Alternaria , 52.1% for Epicoccum ). The influence of meteorological predictors, often with time lags, on exceedance probability varied by taxa and site. With a few exceptions, temperature and precipitation generally had a positive effect on both analysed taxa. Sunshine and wind speed proved as a significant parameter, but with a mixed impact on both studied spore types in different cities. Relative humidity had a mixed effect on Alternaria and a mostly positive effect on Epicoccum . 3.2.2 Lasso linear regression models – prediction of spore concentration The lasso linear regression models (Tables 6 , 7 and S11–S20) were used to predict daily airborne concentrations of Alternaria and Epicoccum spores in days with non-zero spore concentration determined by the lasso logistic models. Logistic models have a very good prediction ability, expressed by the F1 score, reaching up to 99.3% for Alternaria and 95.5% for Epicoccum (both in BA). The lowest value was 84.4% for Alternaria in BR and 77.1% for Epicoccum in BB (Table 3 ). The lasso linear regression models were evaluated by comparing the model performance with a persistence-based baseline using mean absolute error (MAE). Improvements in MAE ranged from 15.7% (PR) to 26% (BR) for Alternaria , and from 10.1% (PR) to 34.2% (PL) for Epicoccum (Table 3 ). The best model performance for Alternaria was observed in PR, followed by BA; for Epicoccum , it was highest in PR, followed by BB. Table 6 Lasso linear regression results predicting daily airborne Alternaria spore concentrations seven days in advance in five study areas. Bratislava Banská Bystrica Praha Brno Plzeň Classification Metric % Metric % Metric % Metric % Metric % Accuracy 99.1 Accuracy 88.7 Accuracy 90.5 Accuracy 81.7 Accuracy 87.1 Sensitivity 100 Sensitivity 92.5 Sensitivity 91.9 Sensitivity 84.9 Sensitivity 92.7 Specificity 97.3 Specificity 81.0 Specificity 89.4 Specificity 77.3 Specificity 79.8 Precision 98.6 Precision 91.0 Precision 87.0 Precision 83.7 Precision 85.8 F1 score 99.3 F1 score 91.7 F1 score 89.4 F1 score 84.3 F1 score 89.1 Predictor Coeff. Predictor Coeff. Predictor Coeff. Predictor Coeff. Predictor Coeff. month_cos -4.697 month_cos -2.32 month_cos -2.076 month_cos -2.878 month_cos -3.13 month_sin -1.717 T max 0.086 month_sin -1.862 month_sin -1.801 month_sin -1.684 T max 0.108 month_sin -0.774 T max (lag 8) 0.036 T max (lag 1) 0.042 T max 0.105 T mean -0.085 WS (lag 11) 0.12 T min 0.026 S (lag 8) 0.019 T mean -0.109 S (lag 1) 0.031 T mean 0 RH (lag 13) -0.008 P 0.019 T min 0.064 P (lag 12) 0.012 T min 0 WS -0.04 T mean 0.005 RH (lag 13) 0.031 RH (lag 13) -0.001 RH (lag 11) 0 P (lag 10) 0.017 WS (lag 6) 0.027 S (lag 8) 0.026 WS 0.005 S 0 S (lag 13) 0.008 RH (lag 13) -0.002 WS (lag 12) 0.093 T min 0 P (lag 13) 0 T mean (lag 8) 0 T min 0 P (lag 5) 0.001 Regression Metric Value Metric Value Metric Value Metric Value Metric Value MAE_model 76.42 MAE_model 55.44 MAE_model 56.57 MAE_model 39.95 MAE_model 35.44 MAE_baseline 94.9 MAE_baseline 70.33 MAE_baseline 66.87 MAE_baseline 54.09 MAE_baseline 45.73 MAE_imrov. 19.5% MAE_imrov. 21.2% MAE_imrov. 15.4% MAE_imrov. 26.2% MAE_imrov. 22.5% Predictor Coeff. Predictor Coeff. Predictor Coeff. Predictor Coeff. Predictor Coeff. month_sin -1.545 month_sin -0.927 month_sin -1.62 month_sin -1.78 month_sin -0.772 month_cos -1.009 month_cos -0.626 month_cos -1.31 month_cos -1.039 month_cos -0.758 T mean (lag 13) 0.02 T min (lag 2) 0.05 T min (lag 10) 0.049 T mean (lag 13) 0.045 T mean (lag 9) 0.042 T min (lag 13) 0.011 T max (lag 11) 0.022 RH (lag 9) -0.004 T max (lag 13) -0.027 T min (lag 6) 0.041 P (lag 1) 0.006 T mean (lag 12) 0.019 T mean (lag 10) 0.006 T min (lag 11) 0.025 WS (lag 13) 0.021 WS (lag 12) -0.028 WS -0.055 T max (lag 12) 0.005 WS (lag 4) -0.037 P (lag 6) 0 RH (lag 1) -0.001 RH (lag 13) -0.001 S (lag 12) -0.007 P (lag 13) 0.006 T max (lag 9) 0 T max (lag 13) 0 P (lag 2) 0.001 P (lag 12) 0.006 RH (lag 13) -0.002 RH (lag 13) 0 S (lag 13) 0 S (lag 13) 0 WS (lag 11) -0.002 S (lag 13) 0 S (lag 11) 0 T mean − mean air temperature; T min − minimum air temperature; T max − maximum air temperature; P – precipitation; RH – relative humidity; S – sunshine; WS – wind speed The influence of meteorological predictors was similar to the lasso logistic models, with the exception of wind speed having a negative effect on both spore types and relative humidity having a mostly negative effect on Alternaria and a positive effect on Epicoccum . In general, the models captured seasonal trends well and provided reasonable forecasts for low and moderate concentrations. However, graphical outputs (Figs. S1–S5) clearly show that the models systematically underestimated higher daily concentrations, particularly during peak events. This limitation was more pronounced for Alternaria , which exhibits more abrupt and intense peak episodes compared to Epicoccum . Table 8 presents examples of 1- and 7-day ahead predictions of threshold exceedance and spore concentrations for two analysed taxa at five sites. The model accurately predicted threshold exceedance for Alternaria at all sites except PL, but generally underestimated spore concentrations. For Epicoccum , the model correctly predicted threshold exceedance at all locations. Predicted spore concentrations aligned well with observed values, demonstrating good overall agreement between predictions and measurements. Table 8 Example predictions of threshold exceedance and spore concentrations (1- and 7-day ahead) for Alternaria and Epicoccum at five monitoring sites. Taxon Sampling station Date Predicted threshold exceedance (1-day ahead)* Predicted threshold exceedance (7-day ahead)* Predicted spore concentration (1-day ahead) Predicted spore concentration (7-day ahead) Observed spore concentration (spores/m 3 ) Alternaria Bratislava 21.9.2024 1 1 127 129 380 Banská Bystrica 20.7.2023 1 1 80 58 260 Praha 19.7.2023 1 1 80 65 112 Brno 15.8.2023 1 1 128 77 147 Plzeň 29.8.2023 1 1 50 46 34 Epicoccum Bratislava 21.9.2024 1 1 66 60 119 Banská Bystrica 20.7.2023 0 0 18 19 8 Praha 19.7.2023 0 0 14 14 10 Brno 15.8.2023 1 1 42 36 35 Plzeň 29.8.2023 1 1 60 46 53 *Binary values indicate predicted threshold exceedance: 80 spores/m³ for Alternaria and 20 spores/m³ for Epicoccum (1 = exceedance predicted. 0 = no exceedance predicted) 4 Discussion In recent years, predictive modelling has become a valuable tool for assessing the risk of airborne allergens and phytopathogenic fungi. Unlike the pollen grains of different plant species that have a clear seasonal pattern, the release of fungal spores of the studied genera is spread over a longer period. These spores are produced asexually (conidia), and as such, do not depend on the seasonality of reproduction but only on the availability of growth substrate, in this case plant matter. Their seasonal patterns therefore reflect the growth of plants, with a peak during the summer, when the biomass is most abundant, consistent with the analysis of Kasprzyk ( 2008 ) stating that maximum concentration of most spores occurs in summer or early autumn. Alternaria is mostly a phytopathogenic genus with specific plant hosts (Marin-Felix et al., 2019 ), while Epicoccum is a saprophytic genus with a broad host spectrum (Lee et al., 2020 ). This explains the earlier beginning and peak of Alternaria spore season, corresponding with the time of harvest, which promotes mechanical release of spores from fungi growing on cereals. The spore season of Epicoccum has a later start with more variation in peak date, since it depends on the local distribution of dead plant matter. The actual daily spore concentrations during the spore season depend on many variables. Accurate predicting requires complex statistical procedures with many input variables, limiting their practical use in operational forecasting. On the other hand, simplification can make this process easier regarding data availability, e.g., De Linares et al. ( 2010 ) used simplified categorical (dummy) precipitation variables. This, however, decreases the accuracy of the model. It is a challenge to find the balance between these two approaches, and our models made this compromise by utilising continuous meteorological data. By including time-lagged variables and selecting optimal lags based on cross-validation and correlation metrics, we were able to balance model complexity with predictive performance. Importantly, the use of lasso regression allowed automatic variable selection, which improved generalisability and prevented overfitting – a challenge frequently encountered in environmental prediction models (Tibshirani, 1996 ). Consistent with previous studies (e.g., Grinn-Gofroń and Strzelczak, 2013 ; Aira et al., 2013 ; Vélez-Pereira et al., 2016 ; Grinn-Gofroń et al., 2019 ), air temperature and precipitation were identified as some of the most influential predictors of fungal spore concentrations, showing predominantly positive associations. The most noticeable difference between the two genera was in the response to relative humidity, which had a mostly negative effect on Alternaria and a positive effect on Epicoccum . This can again be explained by their substrate preference. The factors influencing plant growth have a positive influence on both genera, but relative humidity promotes the decay of dead plant matter and so increases the sporulation of Epicoccum . Using lagged data provides important context for environmental parameters. This is most visible in the influence of precipitation, which has been reported to have a negative influence on fungal spore concentrations in other studies only using daily data (Oliveira et al., 2009 ; Ščevková and Kováč, 2019 ; Žilka et al., 2024 ). This is due to the rain-out and wash-out effect (Sakiyan and Inceoğlu, 2003 ), but the positive effect of precipitation on plant growth also increases the growth and sporulation of fungi using these plants as substrate, which is visible in our data and consistent with the studies of van der Waals et al. ( 2003 ) and Knutsen et al. ( 2012 ). Interestingly, the impact of sunshine duration and wind speed was more variable, sometimes even showing opposite effects across sites or taxa. These findings are consistent with literature reporting location-specific responses to microclimatic factors (Vélez-Pereira et al., 2019 ). The clear inter-site differences in model coefficients underscore the importance of regional calibration in aerobiological forecasting. Such distinctions in meteorological responsiveness are important for refining predictive models and improving risk assessments related to airborne fungal spores. Using the F1 scores allows to balance both precision and sensitivity of the model, unlike using only one of these parameters (e.g., Vélez-Pereira et al., 2019 ). Our models showed high classification accuracy when predicting threshold exceedance, particularly for Epicoccum , where F1 scores reached up to 88.6%, which falls within the “excellent” discrimination category (80–90%) defined by Hosmer and Lemeshow ( 2000 ), indicating that the lasso logistic regression models are well suited for practical applications. The lowest F1 scores for both genera were recorded in PR, the biggest of the studied cities, reflecting possible challenges in predicting exceedance events in some highly urbanised environments with a high percentage of built-up areas and connected microclimatic conditions, like the urban heat island effect (Franceschi et al., 2023 ). Similar to observations by Vélez-Pereira et al. ( 2019 ), we noted that model performance varied with the threshold spore abundance. Lower threshold values tend to yield more accurate results, which explains the higher accuracy of the model for Epicoccum with a lower set threshold value. For Alternaria , the 80 spores/m³ threshold is well established in clinical literature (Rapiejko et al., 2007 ), but for Epicoccum , no universally accepted threshold exists. The 20 spores/m³ threshold used here was selected based on prior aerobiological conventions (Rodinkova et al., 2015 ), but future research should aim to validate this value in the context of clinical symptom onset, leaving room for future adjustments to the models as more accurate allergological data becomes available. Other factors, including microclimatic conditions, local environmental specifics, and data quality and availability, also influence model performance (Anees-Hill et al., 2022 ). While the lasso logistic models predicting threshold exceedance demonstrated overall strong performance, the lasso linear regression models estimating daily spore concentrations systematically underestimated higher concentration values, particularly for Alternaria . This limitation has also been reported by other authors (Skjøth et al., 2012 ; Apangu et al., 2022 ) and may be attributed to the episodic nature of spore releases associated with harvest activities or storm events – factors that are difficult to capture using meteorological variables alone. The inclusion of land use data, crop phenology, and remote sensing indicators (e.g., Normalised Difference Vegetation Index – NDVI) may improve performance, especially during high-variability periods (Pettorelli et al., 2011 ; Pervez et al., 2021 ). Our findings reaffirm the importance of long-term aerobiological monitoring in multiple bioclimatic zones. Site-specific differences in both spore dynamics and model performance highlight that predictive systems should be locally validated and tailored to regional environmental conditions. The models presented in this study provide a valuable foundation for operational forecasting of fungal spore concentrations. Given that they rely on widely available meteorological data, they could be readily adjusted to different local conditions and implemented in regional alert systems to inform allergy sufferers or farmers about periods of elevated spore risk. The ability to forecast up to seven days in advance offers substantial lead time for preventive actions. 5 Conclusions Our study aimed to develop interpretable, meteorologically driven models to predict daily concentrations and threshold exceedances of Alternaria and Epicoccum spores across multiple bioclimatic regions in Central Europe. For the genus Epicoccum , this study is the first of its kind. By employing lasso logistic and lasso linear regression approaches, we were able to identify key meteorological predictors, including lagged data, and generate forecasts up to seven days in advance with promising accuracy. We have identified temperature and precipitation as the main factors positively influencing spore concentrations of both species in the following days, while the influence of relative humidity was mostly negative on the phytopathogenic genus Alternaria and positive on the saprophytic genus Epicoccum . The lasso linear regression models successfully captured seasonal and meteorological patterns in spore concentrations and provided meaningful improvements over the baseline predictions. However, their limitations in predicting peak events, especially for Alternaria , underscore the importance of combining concentration-based and threshold-based approaches for comprehensive aerobiological forecasting. Our findings support the integration of these models into operational forecasting systems, leveraging readily available meteorological data to inform public health alerts and agricultural management. Further improvements, particularly for Epicoccum , may be achieved by validating clinical thresholds and incorporating land use or remote sensing data. Declarations Competing Interests and Funding: The authors declare that they have no conflict of interest.This study was supported by the Grant Agency VEGA (Bratislava), Grant No. 1/0180/22. Acknowledgements The authors acknowledge the Slovak Hydrometeorological Institute and the Czech Hydrometeorological Institute for providing meteorological data used in this paper. This study was supported by the Grant Agency VEGA (Bratislava), Grant No. 1/0180/22. Authors' contributions Jana Ščevková: Conceptualisation, Methodology, Supervision, Data curation, Validation, Writing ‒ original draft. Jozef Dušička: Data curation, Writing ‒ review & editing. Janka Laffersová: Data curation, Writing ‒ review & editing. Ondřej Rybníček: Data curation, Writing ‒ review & editing. Natália Štefániková: Data curation, Writing ‒ review & editing. Matúš Žilka: Data curation, Writing ‒ review & editing. Eva Zahradníková: Visualisation, Writing ‒ review & editing. Michal Hrabovský: Formal analysis, Visualisation, Writing ‒ review & editing. Jozef Kováč: Formal analysis, Validation, Writing ‒ review & editing. References Abel-Fernández, E., Martínez, M. J., Galán, T., Pineda, F. (2023) Going over fungal allergy: Alternaria alternata and its allergens. J Fungi, 9, 582. https://doi.org/10.3390/jof9050582 Aira, M. J., Rodriguez-Rajo, F. J., Fernandez-Gonzalez, M., Seijo, C., Elvira-Rendueles, B., Abreu, I., Gutierrez-Bustillo, M., Perez Sanchez, E., Oliveira, M., Recio, M., Tormo, R., Morales, J. (2013) Spatial and temporal distribution of Alternaria spores in the Iberian Peninsula atmosphere, and meteorological relationships: 1993-2009. Int J Biometeorol, 57, 265–274. https://doi.org/10.1007/s00484-012-0550-x Aira, M. J., Rodriguez-Rajo, F., Jato, V. (2008) 47 annual records of allergenic fungi spore: predictive models from the NW Iberian Peninsula. Ann Agric Environ Med, 15, 91–8. Anees-Hill, S., Douglas, P., Pashley, C. H., Hansell, A., Marczylo, E. L. (2022) A systematic review of outdoor airborne fungal spore seasonality across Europe and the implications for health. Sci Total Environ, 818, 151716. https://doi.org/10.1016/j.scitotenv.2021.151716 Apangu, G. P., Adams-Groom, B., Satchwell, J., Pashley, C. H., Werner, M., Kryza, M., Szymanowski, M., Malkiewicz, M., Bruffaerts, N., Hoebeke, L., Grinn-Gofroń, A., Grewling, Ł., Roldan, N. G., Oliver, G., Sindt, Ch., Kloster, M., Skjøth, C. A. (2022) Sentinel-2 satellite and HYSPLIT model suggest that local cereal harvesting substantially contribute to peak Alternaria spore concentrations. Agric Forest Meteorol, 326, 109156. https://doi.org/10.1016/j.agrformet.2022.109156 Balendres, M. A., Angeles, Y., Calabon, M., Cruz, M. A., Flores, A., Fronda, M., Guerrero, J. J., Jamago, J., Millado, J. B., Montecalvo, M., Seco, M. N., Yusingco, A. I. (2025) Epicoccum . In: Amaresan, N., Kumar, K. (Eds.) Compendium of phytopathogenic microbes in agro-ecology . Springer Nature Switzerland AG, 289–309. https://doi.org/10.1007/978-3-031-81770-0_13 Bisht, V., Arora, N., Singh, B. P., Pasha, S., Gaur, S. N., Sridhara, S. (2004) Epi p 1, an allergenic glycoprotein of Epicoccum purpurascens is a serine protease. FEMS Immunol Med Microbiol, 42, 205–211. https://doi.org/10.1016/j.femsim.2004.05.003 Bisht, V., Singh, B. P., Arora, N., Gaur, S. N., Sridhara, S. (2002) Antigenic and allergenic cross-reactivity of Epicoccum nigrum with other fungi. Ann Allergy Asthma Immunol, 89, 285–291. https://doi.org/10.1016/S1081-1206(10)61956-4 Bousquet, P. J., Hooper, R., Kogevinas, M., Jarvis, D., Burney, P. (2007) Number of allergens to be tested to assess allergenic sensitization in epidemiologic studies: results of the European Community Respiratory Health Survey I. Clin Exp Allergy, 37, 780–7. https://doi.org/10.1111/j.1365-2222.2007.02714.x Brito, F. F., Alonso, A. M., Carnés, J., Martín-Martín, R., Fernández-Caldas, E., Galindo, P. A., Alfaya, T., Amo-Salas, M. (2012) Correlation between Alt a 1 levels and clinical symptoms in Alternaria alternata -monosensitized patients. J Investig Allergol Clin Immunol, 22, 154–159. Burbach, G. J., Heinzerling, L. M., Edenharter, G., Bachert, C., Bindslev-Jensen, C., Bonini, S., et al. (2009) GA(2)LEN skin test study II: clinical relevance of inhalant allergen sensitizations in Europe. Allergy, 64, 1507–1515. https://doi.org/10.1111/j.13989995.2009.02089.x Crandall, S. G., Gilbert, G. S. (2017) Meteorological factors associated with abundance of airborne fungal spores over natural vegetation. Atmos Environ, 162, 87–99. https://doi.org/10.1016/j.atmosenv.2017.05.018 De Linares, C., Belmonte, J., Canela, M., Díaz de la Guardia, C., Alba-Sanchez, F., Sabariego, S., Alonso-Pérez, S. (2010) Dispersal patterns of Alternaria conidia in Spain. Agric Forest Meteorol, 150, 1491–1500. https://doi.org/10.1016/j.agrformet.2010.07.004 Elbert, W., Taylor, P. E., Andreae, M. O., Pöschl, U. (2007) Contribution of fungi to primary biogenic aerosols in the atmosphere: Wet and dry discharged spores, carbohydrates, and inorganic ions. Atmos Chem Phys, 7, 4569–4588. https://doi.org/10.5194/acp-7-4569-2007 EN 16868:2019 Ambient air – sampling and analysis of airborne pollen grains and fungal spores for allergy networks – volumetric Hirst method. CEN-CENELEC Management Centre: Rue de la Science 23, B-1040 Brussels, European Committee for Standardization, 2019. Franceschi, E., Moser-Reischl, A., Honold, M., Rahman, M. A., Pretzsch, H., Pauleit, S., Rötzer, T. (2023) Urban environment, drought events and climate change strongly affect the growth of common urban tree species in a temperate city. Urban For Urban Green, 88, 128083. https://doi.org/10.1016/j.ufug.2023.128083 Gabriel, M. F., Postigo, I., Tomaz, C. T., Martínez, J. (2016) Alternaria alternata allergens: Markers of exposure, phylogeny and risk of fungi-induced respiratory allergy. Environ Int, 89–90, 71–80. https://doi.org/10.1016/j.envint.2016.01.003 Galán, C., Smith, M., Thibaudon, M., Frenguelli, G., Oteros, J., Gehrig, R., Berger, U., Clot, B., Brandao, R., Working Group EAS QC (2014) Pollen monitoring: minimum requirements and reproducibility of analysis. Aerobiologia, 30, 385–395. https://doi.org/10.1007/s10453-014-9335-5 Grinn-Gofroń, A., Nowosad, J., Bosiacka, B., Camacho, I., Pashley, C., Belmonte, J., De Linares, C., Ianovici, N., Maya Manzano, J. M., Sadyś, M., Skjøth, C., Rodinkova, V., Tormo-Molina, R., Vokou, D., Fernández-Rodríguez, S., Damialis, A. (2019) Airborne Alternaria and Cladosporium fungal spores in Europe: Forecasting possibilities and relationships with meteorological parameters. Sci Total Environ, 653, 938–946. https://doi.org/10.1016/j.scitotenv.2018.10.419 Grinn-Gofroń, A., Strzelczak, A. (2013) Changes in concentration of Alternaria and Cladosporium spores during summer storms. Int J Biometeorol, 57, 759–68. https://doi.org/10.1007/s00484-012-0604-0 Heinzerling, L. M., Burbach, G. J., Edenharter, G., Bachert, C., Bindslev-Jensen, C., Bonini, S., et al. (2009) GA(2)LEN skin test study I: GA(2)LEN harmonization of skin prick testing: novel sensitization patterns for inhalant allergens in Europe. Allergy, 64, 1498–1506. https://doi.org/10.1111/j.1398-9995.2009.02093.x Hirst, J. M. (1952) An automatic volumetric spore trap. Ann Appl Biol, 39, 257–265. https://doi.org/10.1111/j.1744-7348.1952.tb00904.x Hosmer, D. W., Lemeshow, S. (2000) Applied logistic regression . 2nd edition. John Wiley & Sons. https://doi.org/10.1002/0471722146 Ianovici, N., Maria, C., Rădutoiu, M. N., Haniş, A., Tudorică, D. (2013) Variation in airborne fungal spore concentrations in four different microclimate regions in Romania. Notulae Botanicae Horti Agrobotanici Cluj-Napoca, 41, 450–457. Kasprzyk, I. (2008) Aeromycology–main research fields of interest during the last 25 years. Ann Agric Environ Med, 15, 1–7. Knutsen, A. P., Bush, R. K., Demain, J. G., Denning, D. W., Dixit, A., Fairs, A., Greenberger, P. A., Kariuki, B., Kita, H., Kurup, V. P., Moss, R. B., Niven, R. M., Pashley, C. H., Slavin, R. G., Vijay, H. M., Wardlaw, A. J. (2012) Fungi and allergic lower respiratory tract diseases. J Allergy Clin Immunol, 129, 280–291. https://doi.org/10.1016/j.jaci.2011.12.970 Kottek, M., Grieser, J., Beck, C., Rudolf, B., Rubel, F. (2006) World map of the Köppen–Geiger climate classification updated. Meteorologische Zeitschrift, 15, 259–263. https://doi.org/10.1127/0941-2948/2006/0130 Lee, A. J., Cadelis, M. M., Kim, S. H., Swift, S., Copp, B. R., Villas-Boas, S. G. (2020) Epipyrone A, a broad-spectrum antifungal compound produced by Epicoccum nigrum ICMP 19927. Molecules, 25, 5997. https://doi.org/10.3390/molecules25245997 Marin-Felix, Y., Hernández-Restrepo, M., Iturrieta-González, I., García, D., Gené, J., Groenewald, J. Z., Cai, L., Chen, Q., Quaedvlieg, W., Schumacher, R. K., Taylor, P. W. J., Ambers, C., Bonthond, G., Edwards, J., Krueger-Hadfield, S. A., Luangsa-Ard, J. J., Morton, L., Moslemi, A., Sandoval-Denis, M., Tan, Y. P., Thangavel, R., Vaghefi, N., Cheewangkoon, R., Crous, P. W. (2019) Genera of phytopathogenic fungi: GOPHY 3. Stud Mycol, 94, 1–124. https://doi.org/10.1016/j.simyco.2019.05.001 Oliveira, M., Ribeiro, H., Delgado, J. L., Abreu, I. (2009) The effects of meteorological factors on airborne fungal spore concentration in two areas differing in urbanisation level. Int J Biometeorol, 53, 61–73. https://doi.org/10.1007/s00484-008-0191-2 Patel, T. Y., Buttner, M., Rivas, D., Cross, C., Bazylinski, D. A., Seggev, J. (2018) Variation in airborne fungal spore concentrations among five monitoring locations in a desert urban environment. Environ Monit Assess, 190, 634. https://doi.org/10.1007/s10661-018-7008-5 Pervez, S., McNally, A., Arsenault, K., Budde, M., Rowland, J. (2021) Vegetation monitoring optimization with normalized difference vegetation index and evapotranspiration using remote sensing measurements and land surface models over East Africa. Front Clim, 3, 589981. https://doi.org/10.3389/fclim.2021.589981 Pettorelli, N., Ryan, S., Mueller, T., Bunnefeld, N., Jedrzejewska, B., Lima, M., Kausrud, K. (2011) The normalized difference vegetation index (NDVI): unforeseen successes in animal ecology. Clim Res, 46, 15–27. https://doi.org/10.3354/cr00936 Portnoy, J., Chapman, J., Burge, H., Muilenberg, M., Solomon, W. (1987) Epicoccum allergy: skin reaction patterns and spore/mycelium disparities recognized by IgG and IgE ELISA inhibition. Ann Allergy, 59, 39–43. Rapiejko, P., Stankiewicz, W., Szczygielski, K., Jurkiewicz, D. (2007) Progowe stężenie pyłku roślin niezbędnedo wywołania objawów alergicznych./Threshold pollen count necessary to evoke allergic symptoms. Otolaryngol Pol LXI, 4, 591–594 (in Polish). Reich, J., McLaren, D., Kim, Y. M., Wally, O., Yevtushenko, D., Hamelin, R., Chatterton, S. (2024) Predicting airborne ascospores of Sclerotinia sclerotiorum through machine learning and statistical methods. Plant Pathol, 73, 1586–1601. https://doi.org/10.1111/ppa.13902 Renard, J.-B., El Azari, H., Lauthier, J., Surcin, J. (2024) Spatial variation of airborne pollen concentrations locally around Brussels city, Belgium, during a field campaign in 2022–2023, using the automatic sensor Beenose. Sensors, 24, 3731. https://doi.org/10.3390/s24123731 Rodinkova, V., Bilous, E. S., Motruk, I, Musatova, K. V., Slobodyanyuk, L. V., DuBuske, L. M. (2015) Seasonal and daily distribution of allergic Epicoccum spores in ambient air in Vinnitsa, Ukraine. J Allergy Clin Immunol, 135, AB20. https://doi.org/10.1016/j.jaci.2014.12.996 Rodríguez-Fernández, A., Blanco-Alegre, C., Vega-Maray, A. M., Valencia-Barrera, R. M., Molnár, T., Fernández-González, D. (2023) Effect of prevailing winds and land use on Alternaria airborne spore load. J Environ Manage, 332, 117414. https://doi.org/10.1016/j.jenvman.2023.117414 Sakiyan, N., Inceoğlu, O. (2003) Atmospheric concentrations of Cladosporium Link and Alternaria Nees spores in Ankara and the effects of meteorological factors. Turk J Bot, 27, 77–81. Schmey, T., Tominello-Ramirez, C. S., Brune, C., Stam, R. (2024) Alternaria diseases on potato and tomato. Mol Plant Pathol, 25, 13435. https://doi.org/10.1111/mpp.13435 Skjøth, C. A., Sommer, J., Frederiksen, L., Gosewinkel Karlson, U. (2012) Crop harvest in Denmark and Central Europe contributes to the local load of airborne Alternaria spore concentrations in Copenhagen. Atmos Chem Phys, 12, 11107–11123. https://doi.org/10.5194/acp-12-11107-2012, 2012 Ščevková, J., Kováč, J. (2019) First fungal spore calendar for the atmosphere of Bratislava, Slovakia. Aerobiologia, 35, 343–356. https://doi.org/10.1007/s10453-019-09564-4 Taguiam, J. D., Evallo, E., Balendres, M. A. (2021) Epicoccum species: ubiquitous plant pathogens and effective biological control agents. Eur J Plant Pathol, 159, 713–725. https://doi.org/10.1007/s10658-021-02207-w Thomma, B. P. (2003) Alternaria spp.: from general saprophyte to specific parasite. Mol Plant Pathol, 4, 225–36. https://doi.org/10.1046/j.1364-3703.2003.00173.x Tibshirani, R. (1996) Regression shrinkage and selection via the lasso. J R Stat Soc Ser B (Methodological), 58, 267–288. https://doi.org/10.1111/j.2517-6161.1996.tb02080.x Tomassetti, B., Angelosante Bruno, A., Pace, L., Verdecchia, M., Visconti, G. (2009) Prediction of Alternaria and Pleospora concentrations from the meteorological forecast and artificial neural network in L’Aquila, Abruzzo (Central Italy). Aerobiologia, 25, 127–136. https://doi.org/10.1007/s10453-009-9117-7 van der Waals, J. E., Korsten, L., Aveling, T. A. S., Denner, F. D. N. (2003) Influence of environmental factors on field concentrations of Alternaria solani conidia above a South African potato crop. Phytoparasitica, 31, 353–364. https://doi.org/10.1007/BF02979806 Vélez-Pereira, A. M., De Linares, C., Belmonte, J. (2021) Aerobiological modeling I: A review of predictive models. Sci Total Environ, 795, 148783. https://doi.org/10.1016/j.scitotenv.2021.148783 Vélez-Pereira, A. M., De Linares, C., Canela, M. A., Belmonte, J. (2019) Logistic regression models for predicting daily airborne Alternaria and Cladosporium concentration levels in Catalonia (NE Spain). Int J Biometeorol, 63, 1541–1553. https://doi.org/10.1007/s00484-019-01767-1 Vélez-Pereira, A. M., De Linares, C., Delgado, R., Belmonte, J. (2016) Temporal trends of the airborne fungal spores in Catalonia (NE Spain), 1995–2013. Aerobiologia, 31, 23–37. https://doi.org/10.1007/s10453-015-9410-6 Woudenberg, J. H. C., Seidl, M. F., Groenewald, J. Z., de Vries, M., Stielow, J. B., Thomma, B. P. H. J., Crous, P. W. (2015) Alternaria section Alternaria : species, formae speciales or pathotypes? Stud Mycol, 82, 1–21. https://doi.org/10.1016/j.simyco.2015.07.001 Žilka, M., Hrabovský, M., Dušička, J., Zahradníková, E., Gahurová, D., Ščevková, J. (2024) Comparative analysis of airborne fungal spore distribution in urban and rural environments of Slovakia. Environ Sci Pollut Res, 31, 63145–63160. https://doi.org/10.1007/s11356-024-35470-5 Supplementary Files Suplementarymaterials.docx Cite Share Download PDF Status: Published Journal Publication published 07 Jan, 2026 Read the published version in International Journal of Biometeorology → Version 1 posted Reviewers agreed at journal 11 Aug, 2025 Reviewers invited by journal 11 Aug, 2025 Editor assigned by journal 27 Jul, 2025 First submitted to journal 24 Jul, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7210967","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":498886557,"identity":"900708b3-7527-4419-9f6b-a51cca0cb004","order_by":0,"name":"Jana Ščevková","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+0lEQVRIiWNgGAWjYBACxgYYiwdEVDAwsEmAGAeI1nKGCC0IANLC2AYkCGlhbj978APDHzs5gzOHj0n8nHc4j0+6+QHjjzN4HNaTlyzB2JZsbHC2LU2yd9vhYjaZYwbMPDfw+SXHQIKx4UDizH4eYwPebYcT2yQSDJgZPuDR0v/G+AfDnwP1IC2Gf+eAtKR/YPyBT8uMHDMJBrYDCfy8PYaPeRtAWnIMGPA6bMYbM4vEtmTDfp5jiY9ljqUntsmcKTjMg8f7hv05xjc+/LGTZ+NJPnDwTY114vzZ7Rsf/jiGR0sDkEhAFz2AWwMDgzw+yVEwCkbBKBgFYAAAc+9T6Rj7JagAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0002-3432-4105","institution":"Comenius University in Bratislava Faculty of Natural Sciences: Univerzita Komenskeho v Bratislave Prirodovedecka fakulta","correspondingAuthor":true,"prefix":"","firstName":"Jana","middleName":"","lastName":"Ščevková","suffix":""},{"id":498886558,"identity":"b0c29cce-4dac-4962-85c9-0b1c88f55704","order_by":1,"name":"Jozef Dušička","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Jozef","middleName":"","lastName":"Dušička","suffix":""},{"id":498886559,"identity":"d702453d-9cd1-49ff-beda-6346a2a31d4e","order_by":2,"name":"Janka Lafférsová","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Janka","middleName":"","lastName":"Lafférsová","suffix":""},{"id":498886560,"identity":"03429098-1fd7-4125-8604-a8cc41735fb2","order_by":3,"name":"Ondřej Rybníček","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Ondřej","middleName":"","lastName":"Rybníček","suffix":""},{"id":498886561,"identity":"fa1be060-e697-4d64-abd5-0b2470c89696","order_by":4,"name":"Natália Štefániková","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Natália","middleName":"","lastName":"Štefániková","suffix":""},{"id":498886562,"identity":"0a8f9216-d17b-464d-a331-92655b4274b3","order_by":5,"name":"Matúš Žilka","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Matúš","middleName":"","lastName":"Žilka","suffix":""},{"id":498886563,"identity":"ce39d749-0b8e-4daa-aeeb-8dbd7b386973","order_by":6,"name":"Eva Zahradníková","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Eva","middleName":"","lastName":"Zahradníková","suffix":""},{"id":498886564,"identity":"dad95217-b55e-480b-8a5d-35f713fae9b8","order_by":7,"name":"Michal Hrabovský","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Michal","middleName":"","lastName":"Hrabovský","suffix":""},{"id":498886565,"identity":"b971ee77-1ed9-40f1-b358-63c2ee77a42c","order_by":8,"name":"Jozef Kováč","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Jozef","middleName":"","lastName":"Kováč","suffix":""}],"badges":[],"createdAt":"2025-07-25 06:27:40","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7210967/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7210967/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00484-025-03084-2","type":"published","date":"2026-01-07T15:57:59+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":89360375,"identity":"f7335307-1144-4041-979f-62a68fc0d383","added_by":"auto","created_at":"2025-08-19 08:19:18","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":594495,"visible":true,"origin":"","legend":"\u003cp\u003eLocation and bioclimatic conditions of the aerobiological monitoring sites in the Czech Republic (CZ) and Slovakia (SK). Abbreviations of the border countries: DE – Germany, AT – Austria, HU – Hungary, PL – Poland, UA – Ukraine.\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-7210967/v1/7ec2906de6d3026dbca004fe.png"},{"id":89360374,"identity":"ac95f601-4a3c-45aa-a112-36a1dda2fc2a","added_by":"auto","created_at":"2025-08-19 08:19:18","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":106829,"visible":true,"origin":"","legend":"\u003cp\u003eDynamics of \u003cem\u003eAlternaria\u003c/em\u003e(a) and \u003cem\u003eEpicoccum\u003c/em\u003e (b) spore concentrations over the analysed years, as presented in Table 1, across the five study areas.\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-7210967/v1/722d37ae424bc95f215fe7ca.png"},{"id":100069252,"identity":"183880f1-3ddf-4ae6-b1e7-67cffbd599e7","added_by":"auto","created_at":"2026-01-12 16:12:00","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2824025,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7210967/v1/c1fdc43b-4739-42de-8916-4ca05b9120e0.pdf"},{"id":89361202,"identity":"59b1e8ac-9101-4ab5-b539-56b66e84c24d","added_by":"auto","created_at":"2025-08-19 08:27:18","extension":"docx","order_by":6,"title":"","display":"","copyAsset":false,"role":"supplement","size":223044,"visible":true,"origin":"","legend":"","description":"","filename":"Suplementarymaterials.docx","url":"https://assets-eu.researchsquare.com/files/rs-7210967/v1/94f58724b2aa54c1f734f38d.docx"}],"financialInterests":"","formattedTitle":"Predictive modelling of threshold exceedance and airborne concentrations of Alternaria and Epicoccum spores across bioclimatic regions in Central Europe","fulltext":[{"header":"1 Introduction","content":"\u003cp\u003eAirborne fungi, particularly their spores, as well as hyphal and mycelial fragments, constitute a significant fraction of bioaerosols (Elbert et al., \u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e2007\u003c/span\u003e). Several taxa are considered allergenic and raise concerns for public health, e.g., the genera \u003cem\u003eAlternaria\u003c/em\u003e (Pleosporaceae) and \u003cem\u003eEpicoccum\u003c/em\u003e (Didymellaceae) are well known for their allergenic potential. Spores of these fungi have been associated with the onset and exacerbation of respiratory diseases, including allergic rhinitis and asthma (Bisht et al., \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e2002\u003c/span\u003e; Brito et al., \u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e2012\u003c/span\u003e; Gabriel et al., \u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e2016\u003c/span\u003e; Abel-Fern\u0026aacute;ndez et al., \u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e2023\u003c/span\u003e). According to Bousquet et al. (\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e2007\u003c/span\u003e), \u003cem\u003eAlternaria\u003c/em\u003e sensitisation was identified in 4.4% of the 11,355 individuals tested as part of the European Community Respiratory Health Survey. In two later studies conducted under the Global Asthma and Allergy European Network (GA\u0026sup2;LEN), sensitisation to \u003cem\u003eAlternaria\u003c/em\u003e was found in approximately 9% of the 3,034 participants tested for inhalant allergies across 14 European countries (Burbach et al., \u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e2009\u003c/span\u003e; Heinzerling et al., \u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e2009\u003c/span\u003e). Although sensitisation to \u003cem\u003eEpicoccum\u003c/em\u003e is less frequently reported, co-sensitisation or cross-reactivity with \u003cem\u003eAlternaria\u003c/em\u003e is often observed (Portnoy et al., \u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e1987\u003c/span\u003e; Bisht et al., \u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e2004\u003c/span\u003e), potentially leading to a stronger immune response and an increased risk of developing or worsening asthma and allergic rhinitis.\u003c/p\u003e\u003cp\u003eBoth genera are also well recognised for their phytopathogenic potential, causing diseases in a wide range of economically important crops. \u003cem\u003eAlternaria\u003c/em\u003e spp. are among the most prevalent fungal pathogens worldwide, responsible for leaf spots, blights, rots, and seedling damping-off in crops such as cereals, vegetables, and fruits (Thomma, \u003cspan citationid=\"CR45\" class=\"CitationRef\"\u003e2003\u003c/span\u003e; Woudenberg et al., \u003cspan citationid=\"CR52\" class=\"CitationRef\"\u003e2015\u003c/span\u003e; Schmey et al., \u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). Similarly, species of \u003cem\u003eEpicoccum\u003c/em\u003e, although mostly saprophytic and occurring on senescent and dead plant material (Lee et al., \u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e2020\u003c/span\u003e), have been reported as causal agents of leaf spots and other foliar diseases in crops, including cereals, grapes, and various horticultural plants (Taguiam et al., \u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e2021\u003c/span\u003e; Balendres et al., \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e2025\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eThe concentration of fungal spores in the atmosphere is shaped by a complex interplay of multiple biotic and abiotic factors, such as vegetation type, land use, meteorological conditions, and seasonal dynamics (Crandall and Gilbert, \u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e2017\u003c/span\u003e; Anees-Hill et al., \u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e2022\u003c/span\u003e), resulting in significant spatial variability that can be observed not only between countries but also within regions and individual areas (Ianovici et al., \u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e2013\u003c/span\u003e; Patel et al., \u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e2018\u003c/span\u003e; Anees-Hill et al., \u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e2022\u003c/span\u003e; Renard et al., \u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e2024\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eAlthough the health and phytopathogenic relevance of \u003cem\u003eAlternaria\u003c/em\u003e and \u003cem\u003eEpicoccum\u003c/em\u003e is well established, studies focused on predicting their fungal spore concentrations in the air remain limited, with a few papers dealing with \u003cem\u003eAlternaria\u003c/em\u003e spores (Aira et al., \u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e2008\u003c/span\u003e; Tomassetti et al., \u003cspan citationid=\"CR47\" class=\"CitationRef\"\u003e2009\u003c/span\u003e; V\u0026eacute;lez-Pereira et al., \u003cspan citationid=\"CR50\" class=\"CitationRef\"\u003e2019\u003c/span\u003e; Grinn-Gofroń et al., \u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e2019\u003c/span\u003e), but none about \u003cem\u003eEpicoccum\u003c/em\u003e. One of the main reasons of their rare use is the methodological challenge of developing reliable predictive models, as aerobiological data often exhibit non-linear relationships and non-normal distributions (e.g., V\u0026eacute;lez-Pereira et al., \u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e2021\u003c/span\u003e). Traditional statistical methods typically assume linearity and normality, which are frequently violated in this context. As a result, threshold-based models and non-linear classification techniques, such as logistic regression and regression trees, have gained traction (V\u0026eacute;lez-Pereira et al., \u003cspan citationid=\"CR50\" class=\"CitationRef\"\u003e2019\u003c/span\u003e; Reich et al., \u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). These methods are well-suited for binary outcomes, such as whether or not a defined concentration threshold is exceeded, and offer a more interpretable and computationally efficient alternative to more complex machine learning approaches.\u003c/p\u003e\u003cp\u003eAccurate forecasting of allergenic and phytopathogenic fungal spores is vital for public health and agriculture. Timely predictions enhance early warning systems, support allergy prevention, and enable rapid responses to crop diseases, helping to minimise yield losses. Although advanced modelling techniques are increasingly available, their performance must be assessed across diverse environments. Evaluating models on large datasets from new geographic regions is key to testing their transferability and reliability under varying meteorological and ecological conditions, especially across different phytogeographical zones, where spore dynamics may vary.\u003c/p\u003e\u003cp\u003eThe aim of this study was therefore to develop and evaluate predictive models for \u003cem\u003eAlternaria\u003c/em\u003e and \u003cem\u003eEpicoccum\u003c/em\u003e spore concentrations across different bioclimatic regions in Central Europe. By combining aeromycological and meteorological data, we seek to identify key drivers of spore dynamics and establish forecasting tools tailored to specific bioclimatic regions. The results will contribute to a better understanding of the spatiotemporal patterns of allergenic spores and improve the preparedness and management of fungal allergy risks in a changing climate.\u003c/p\u003e"},{"header":"2 Materials and methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003e2.1 Study area\u003c/h2\u003e\u003cp\u003eThe aeromycological study was conducted in five cities representing diverse geomorphological and climatic conditions across Central Europe: Bratislava (BA) and Bansk\u0026aacute; Bystrica (BB) in Slovakia, and Brno (BR), Prague (PR), and Plzeň (PL) in the Czech Republic (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e; Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e). All sampling sites are characterised by a continental climate but differ in orographic features that influence local temperature and precipitation patterns. BA, situated in the Podunajsk\u0026aacute; n\u0026iacute;žina Lowland, has the warmest conditions, while BB, surrounded by mountains, experiences lower temperatures and higher precipitation totals. The Czech cities, positioned in various basins and lowlands, exhibit intermediate climatic conditions characterised by moderately warm and relatively dry weather (Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e). Except for BB, all locations are classified as Cfb according to the K\u0026ouml;ppen-Geiger system (Kottek et al., \u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e2006\u003c/span\u003e), indicating a warm temperate, fully humid climate with warm summers. In contrast, BB is categorised as Dfb, which corresponds to a fully humid, snowy climate with warm summers.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eCharacteristics of the sampling stations in the study areas.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"9\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSampling\u003c/p\u003e\u003cp\u003estation\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eYears of available spore data\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eMissing years\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eLatitude\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eLongitude\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eElevation\u003c/p\u003e\u003cp\u003e(m a. s. l.)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003eSampler height\u003c/p\u003e\u003cp\u003e(m a. g. l.)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c8\"\u003e\u003cp\u003eAverage annual temperature (℃)*\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c9\"\u003e\u003cp\u003eAverage total annual precipitation (mm)*\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBratislava\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2002\u0026ndash;2024\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eN 48.14973\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eE 17.07375\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e166\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e18\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e11.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e686\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBansk\u0026aacute; Bystrica\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2002\u0026ndash;2024\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e2005, 2022\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eN 48.74204\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eE 19.16276\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e367\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e10\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e9.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e870\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePraha\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1993\u0026ndash;2024\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e1994, 2008\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eN 50.07615\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eE 14.47313\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e249\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e14\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e11.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e468\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBrno\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1992\u0026ndash;2024\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e2006\u0026ndash;2010\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eN 49.20369\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eE 16.61800\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e227\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e15\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e10.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e534\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePlzeň\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2005\u0026ndash;2023\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eN 49.72999\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eE 13.37207\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e328\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e20\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e10.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e532\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"9\"\u003e*meteorological data averaged for 2002\u0026ndash;2024 were provided by the Slovak Hydrometeorological Institute and the Czech Meteorological Society\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003eCereal fields and grasslands are the main sources of \u003cem\u003eAlternaria\u003c/em\u003e spores. The highest risk of spore exposure occurs during the harvest period, when conditions are optimal for their release and spread through the air (Apangu et al., \u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e2022\u003c/span\u003e; Rodr\u0026iacute;guez-Fern\u0026aacute;ndez et al., \u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e2023\u003c/span\u003e). In all monitored sites except BB, the surrounding areas are characterised by intensive agricultural use. BB, situated in a submontane area, is located in a region with limited agricultural activity due to terrain and climatic conditions (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e).\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec4\" class=\"Section2\"\u003e\u003ch2\u003e2.2 Aeromycological analysis\u003c/h2\u003e\u003cp\u003eFungal spores were captured from the air using a Hirst-type trap (Hirst \u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e1952\u003c/span\u003e) positioned on building roofs 10\u0026ndash;20 meters above the ground (Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e). The monitoring period ranged from 18 years (PL) to 29 years (PR), depending on data availability. All periods fall between 1992 and 2024, with the exact years of observation and any data interruptions detailed in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. Samples were examined using standardised aerobiological procedures in compliance with the minimum criteria set by the European Aerobiology Society (Gal\u0026aacute;n et al., \u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e2014\u003c/span\u003e) and the European standard EN 16868:2019. The resulting daily \u003cem\u003eAlternaria\u003c/em\u003e and \u003cem\u003eEpicoccum\u003c/em\u003e spore concentrations were expressed as the mean daily number of spores per cubic metre of air (spores/m\u0026sup3;).\u003c/p\u003e\u003cp\u003eTo evaluate the seasonal dynamics of the analysed spore taxa, we assessed the Annual Spore Integral (ASIn, the sum of daily spore concentrations throughout the year), peak spore concentration (peak value), peak date, and the number of high days (HD). A high day was defined as a day when the daily spore concentration exceeded 80 spores/m\u0026sup3; for \u003cem\u003eAlternaria\u003c/em\u003e and 20 spores/m\u0026sup3; for \u003cem\u003eEpicoccum\u003c/em\u003e. For \u003cem\u003eAlternaria\u003c/em\u003e, this value is recognised as the threshold for triggering clinical symptoms of fungal spore allergy (Rapiejko et al., \u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e2007\u003c/span\u003e). However, for \u003cem\u003eEpicoccum\u003c/em\u003e, a universally accepted threshold value for eliciting allergic reactions has not been established. The value of 20 spores/m\u0026sup3; used in this study is based on previous aerobiological research practices, where similar levels have been considered indicative of increased exposure risk, although its direct association with clinical symptoms remains to be clarified.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec5\" class=\"Section2\"\u003e\u003ch2\u003e2.3 Meteorological data\u003c/h2\u003e\u003cp\u003eThe following daily meteorological data were included in the predictive modelling: mean, maximum, and minimum temperature (\u0026deg;C), relative humidity (%), precipitation (mm), sunshine duration (h), and wind speed (m/s). The Slovak Hydrometeorological Institute and the Czech Hydrometeorological Institute provided meteorological data used in this study. The distances between the meteorological stations and the aerobiological sampling sites were approximately 0.5 km (BA), 3.7 km (BB), 3.3 km (PR and BR), and 6.5 km (PL).\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec6\" class=\"Section2\"\u003e\u003ch2\u003e2.4 Data evaluation and prediction modelling\u003c/h2\u003e\u003cp\u003eWeekly mean spore concentrations for analysed years were calculated using the pollen_calendar() function from the AeRobiology R package, with the method set to \"heatplot\". This approach enabled the visualisation of seasonal patterns in spore concentrations across multiple years.\u003c/p\u003e\u003cp\u003eTo compare ASIn values between monitoring sites for individual years, we applied the Friedman test, including only years with complete data for all localities to ensure valid cross-site comparisons. The test was performed using the PMCMRplus R package, and the Nemenyi post-hoc test from the same package was used to identify significant pairwise differences between localities.\u003c/p\u003e\u003cp\u003eWe applied statistical models to predict daily airborne fungal spore concentrations in each city from one to seven days in advance, with a focus on identifying relevant meteorological predictors. The primary modelling task was to determine whether the daily concentration would exceed a predefined threshold of 80 spores/m\u0026sup3; for \u003cem\u003eAlternaria\u003c/em\u003e and 20 spores/m\u0026sup3; for \u003cem\u003eEpicoccum\u003c/em\u003e. In addition, we implemented an extended two-stage model to estimate concentration values on days predicted to have non-zero counts. In all models, the predictors included meteorological variables from the current day and the preceding 13 days \u0026ndash; that is, 14 temporal lags per variable. For each meteorological parameter, a single optimal lag was selected based on performance metrics to enhance model interpretability and accuracy. To account for seasonality, we incorporated cyclical calendar variables derived from sine and cosine transformations of the monthly index, which allow for smooth modelling of seasonal patterns. The dataset was chronologically divided into training (up to 2018), validation (2019\u0026ndash;2021), and test sets (2022\u0026ndash;2024). To prevent information leakage caused by lagged predictors crossing set boundaries, the final two weeks of December were excluded from both the training and validation sets.\u003c/p\u003e\u003cp\u003eThe classification model for exceedance prediction was fitted using lasso logistic regression via the glmnet package in R. The regularisation parameter lambda was selected by cross-validation on the training set. For each meteorological variable, the most informative lag was chosen based on the area under the ROC curve (AUC), calculated separately within the training set. The final classification threshold (probability cutoff) was optimised on the validation set to maximise the F1 score \u0026ndash; the harmonic mean of precision and recall. Model performance was assessed on the test set using standard classification metrics: accuracy (overall correct classification rate), sensitivity (true positive rate), specificity (true negative rate), precision (positive predictive value), F1 score (harmonic mean of sensitivity and precision), and the confusion matrix (counts of true positives, false positives, true negatives, and false negatives).\u003c/p\u003e\u003cp\u003eTo capture the full concentration profile, we implemented a two-stage modelling approach. In the first stage, a lasso logistic regression model predicted whether the concentration would be strictly positive (i.e., non-zero), using the same methodology described above. In the second stage, a lasso linear regression model was trained to predict spore concentration only on days with observed non-zero values. Given the strong skewness of the data, the response variable was log-transformed. For each predictor, the lag exhibiting the highest Pearson correlation with the log-transformed concentration was selected. Since this regression model did not require separate threshold optimisation, it was trained on the combined training and validation datasets. The regression component was assessed using the mean absolute error (MAE) computed on non-zero days in the test set. We additionally report the MAE improvement compared to a baseline model that predicts a constant mean concentration.\u003c/p\u003e\u003cp\u003eModel coefficients (from both logistic and linear models) were ranked based on the estimated impact of a one-standard-deviation increase in each predictor on the model output, providing a clearer interpretation of the relative meteorological influence.\u003c/p\u003e\u003c/div\u003e"},{"header":"3 Results","content":"\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e\u003ch2\u003e3.1 Seasonal patterns and spatial variation of \u003cem\u003eAlternaria\u003c/em\u003e and \u003cem\u003eEpicoccum\u003c/em\u003e spore concentrations\u003c/h2\u003e\u003cp\u003eThe dynamics of \u003cem\u003eAlternaria\u003c/em\u003e and \u003cem\u003eEpicoccum\u003c/em\u003e fungal spore concentrations throughout the year for each study area are presented in Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. Both types of spores were detected continuously throughout the vegetation period until the end of October. Peak concentrations for both spore types were reached in July in all study areas, except \u003cem\u003eEpicoccum\u003c/em\u003e in BA and PL, where the highest spore concentrations were recorded in September and August, respectively.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e summarises the main characteristics of the spore seasons of \u003cem\u003eAlternaria\u003c/em\u003e and \u003cem\u003eEpicoccum\u003c/em\u003e across the monitored sites. On average, \u003cem\u003eAlternaria\u003c/em\u003e exhibited approximately 1.5 times higher seasonal intensity than \u003cem\u003eEpicoccum\u003c/em\u003e, as indicated by both the ASIn and peak values. The highest ASIn for \u003cem\u003eAlternaria\u003c/em\u003e (17,768 spore*day/m\u0026sup3;) was recorded in BR and lowest in PL (7,140 spore*day/m\u0026sup3;). For \u003cem\u003eEpicoccum\u003c/em\u003e, the highest ASIn was recorded in PL (7,174 spore*day/m\u0026sup3;) and lowest in PR (3,473 spore*day/m\u0026sup3;). The highest mean peak values for both genera were detected in BR (1,214 spores/m\u0026sup3; for \u003cem\u003eAlternaria\u003c/em\u003e, 369 spores/m\u0026sup3; for \u003cem\u003eEpicoccum\u003c/em\u003e), and the lowest in PL and PR (336 spores/m\u0026sup3; for \u003cem\u003eAlternaria\u003c/em\u003e, 162 spores/m\u0026sup3; for \u003cem\u003eEpicoccum\u003c/em\u003e, respectively). \u003cem\u003eAlternaria\u003c/em\u003e had the highest number of HD in BA (63) lowest in PL (30), while the highest number of HD for \u003cem\u003eEpicoccum\u003c/em\u003e was recorded in PL (108) and lowest in PR (52). On average, the peak date of \u003cem\u003eAlternaria\u003c/em\u003e occurred 29 days earlier than that of \u003cem\u003eEpicoccum\u003c/em\u003e.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eDescriptive statistics of the airborne \u003cem\u003eAlternaria\u003c/em\u003e and \u003cem\u003eEpicoccum\u003c/em\u003e spore data: Annual Spore Integral (ASIn, the sum of daily spore concentrations throughout the year), peak value, peak date and number of high days (HD, days when the daily spore concentration exceeded 80 spores/m\u0026sup3; for \u003cem\u003eAlternaria\u003c/em\u003e and 20 spores/m\u0026sup3; for \u003cem\u003eEpicoccum\u003c/em\u003e) in five study areas over the analysed years shown in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. Abbreviations of the study areas are provided in Section \u003cspan refid=\"Sec3\" class=\"InternalRef\"\u003e2.1\u003c/span\u003e.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"18\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c10\" colnum=\"10\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c11\" colnum=\"11\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c12\" colnum=\"12\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c13\" colnum=\"13\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c14\" colnum=\"14\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c15\" colnum=\"15\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c16\" colnum=\"16\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c17\" colnum=\"17\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c18\" colnum=\"18\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eSampling\u003c/p\u003e\u003cp\u003estation\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eTaxon\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"4\" nameend=\"c6\" namest=\"c3\"\u003e\u003cp\u003eASIn (spore*day/m\u003csup\u003e3\u003c/sup\u003e)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"4\" nameend=\"c10\" namest=\"c7\"\u003e\u003cp\u003ePeak value (spores/m\u003csup\u003e3\u003c/sup\u003e)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"4\" nameend=\"c14\" namest=\"c11\"\u003e\u003cp\u003ePeak date (DOY)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"4\" nameend=\"c18\" namest=\"c15\"\u003e\u003cp\u003eHD (days)\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eMean\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eMax\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eMin\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eSD\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003eMean\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c8\"\u003e\u003cp\u003eMax\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c9\"\u003e\u003cp\u003eMin\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c10\"\u003e\u003cp\u003eSD\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c11\"\u003e\u003cp\u003eMean\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c12\"\u003e\u003cp\u003eMax\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c13\"\u003e\u003cp\u003eMin\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c14\"\u003e\u003cp\u003eSD\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c15\"\u003e\u003cp\u003eMean\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c16\"\u003e\u003cp\u003eMax\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c17\"\u003e\u003cp\u003eMin\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c18\"\u003e\u003cp\u003eSD\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBA\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cem\u003eAlternaria\u003c/em\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e16,794\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e33,196\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e4,432\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e7,009.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e621\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e1,472\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e87\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e\u003cp\u003e336.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e221\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e278\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c13\"\u003e\u003cp\u003e166\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c14\"\u003e\u003cp\u003e37.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c15\"\u003e\u003cp\u003e63\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c16\"\u003e\u003cp\u003e104\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c17\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c18\"\u003e\u003cp\u003e26.6\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cem\u003eEpicoccum\u003c/em\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e6,093\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e13,414\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1,578\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e2,950.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e278\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e725\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e37\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e\u003cp\u003e175.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e273\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e300\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c13\"\u003e\u003cp\u003e242\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c14\"\u003e\u003cp\u003e14.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c15\"\u003e\u003cp\u003e86\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c16\"\u003e\u003cp\u003e133\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c17\"\u003e\u003cp\u003e9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c18\"\u003e\u003cp\u003e35.6\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBB\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cem\u003eAlternaria\u003c/em\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e13,791\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e28,064\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e2,999\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e6,899.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e661\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e1,588\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e161\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e\u003cp\u003e318.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e223\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e274\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c13\"\u003e\u003cp\u003e173\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c14\"\u003e\u003cp\u003e26.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c15\"\u003e\u003cp\u003e50\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c16\"\u003e\u003cp\u003e90\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c17\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c18\"\u003e\u003cp\u003e27.3\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cem\u003eEpicoccum\u003c/em\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e4,710\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e12,759\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e786\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e3,201.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e213\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e432\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e54\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e\u003cp\u003e100.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e233\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e287\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c13\"\u003e\u003cp\u003e112\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c14\"\u003e\u003cp\u003e39.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c15\"\u003e\u003cp\u003e63\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c16\"\u003e\u003cp\u003e122\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c17\"\u003e\u003cp\u003e11\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c18\"\u003e\u003cp\u003e34.0\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePR\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cem\u003eAlternaria\u003c/em\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e11,625\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e27,177\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e2,678\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e6,497.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e701\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e1,708\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e228\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e\u003cp\u003e444.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e211\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e238\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c13\"\u003e\u003cp\u003e190\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c14\"\u003e\u003cp\u003e12.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c15\"\u003e\u003cp\u003e39\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c16\"\u003e\u003cp\u003e74\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c17\"\u003e\u003cp\u003e10\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c18\"\u003e\u003cp\u003e15.8\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cem\u003eEpicoccum\u003c/em\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e3,473\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e7,738\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e992\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e1,730.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e162\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e361\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e53\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e\u003cp\u003e78.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e238\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e303\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c13\"\u003e\u003cp\u003e190\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c14\"\u003e\u003cp\u003e29.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c15\"\u003e\u003cp\u003e52\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c16\"\u003e\u003cp\u003e97\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c17\"\u003e\u003cp\u003e13\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c18\"\u003e\u003cp\u003e22.2\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBR\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cem\u003eAlternaria\u003c/em\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e17,768\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e39,146\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e5,712\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e7,614.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e1,214\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e4,334\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e382\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e\u003cp\u003e878.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e215\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e281\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c13\"\u003e\u003cp\u003e179\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c14\"\u003e\u003cp\u003e27.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c15\"\u003e\u003cp\u003e57\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c16\"\u003e\u003cp\u003e92\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c17\"\u003e\u003cp\u003e24\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c18\"\u003e\u003cp\u003e15.8\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cem\u003eEpicoccum\u003c/em\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e5,578\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e9,898\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1,091\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e2,390.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e369\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e1,203\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e62\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e\u003cp\u003e274.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e262\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e302\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c13\"\u003e\u003cp\u003e197\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c14\"\u003e\u003cp\u003e30.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c15\"\u003e\u003cp\u003e68\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c16\"\u003e\u003cp\u003e99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c17\"\u003e\u003cp\u003e16\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c18\"\u003e\u003cp\u003e21.9\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePL\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cem\u003eAlternaria\u003c/em\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e7,140\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e14,559\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e3,064\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e3,378.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e336\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e778\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e119\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e\u003cp\u003e150.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e219\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e237\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c13\"\u003e\u003cp\u003e197\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c14\"\u003e\u003cp\u003e11.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c15\"\u003e\u003cp\u003e30\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c16\"\u003e\u003cp\u003e74\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c17\"\u003e\u003cp\u003e3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c18\"\u003e\u003cp\u003e22.3\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cem\u003eEpicoccum\u003c/em\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e7,174\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e13,161\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e3,890\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e2,631.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e163\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e260\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e86\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e\u003cp\u003e46.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e227\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c12\"\u003e\u003cp\u003e281\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c13\"\u003e\u003cp\u003e187\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c14\"\u003e\u003cp\u003e21.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c15\"\u003e\u003cp\u003e108\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c16\"\u003e\u003cp\u003e158\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c17\"\u003e\u003cp\u003e55\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c18\"\u003e\u003cp\u003e26.3\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"18\"\u003e\u003cem\u003eDOY\u003c/em\u003e \u0026ndash; day of the year from 1 January\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003eAccording to the Friedman test, there was a statistically significant difference in \u003cem\u003eAlternaria\u003c/em\u003e ASIn values between the 5 study sites (χ\u0026sup2; = 24.36, \u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001). Pairwise comparisons revealed significant differences between PL and all other cities (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.01\u0026ndash;0.001) except PR, while no significant differences were found among the remaining localities. For \u003cem\u003eEpicoccum\u003c/em\u003e, the inter-site differences were also significant (χ\u0026sup2; = 22.65, \u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001). Significant pairwise differences were observed between PR and BA (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001) and between PR and PL (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001). No other pairwise comparisons showed statistically significant differences.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec9\" class=\"Section2\"\u003e\u003ch2\u003e3.2 Forecasting methods for airborne spore concentrations\u003c/h2\u003e\u003cp\u003eTo forecast airborne fungal spore concentrations, two modelling approaches were implemented: lasso logistic regression to predict exceedance events of predefined concentration thresholds (80 spores/m\u0026sup3; for \u003cem\u003eAlternaria\u003c/em\u003e and 20 spores/m\u0026sup3; for \u003cem\u003eEpicoccum\u003c/em\u003e), and lasso linear regression to estimate daily spore concentrations for the mentioned fungal taxa. Both model types were developed for five monitoring stations and validated over 1- to 7-day forecast horizons. Since model performance was consistent across horizons (Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e), detailed results for only the 7-day-ahead forecasts are reported in Tables\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e\u0026ndash;\u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e7\u003c/span\u003e, while full outputs for all horizons are provided in the Supplementary material (Tables S1\u0026ndash;S20).\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eDescriptive statistics of model performance for lasso logistic regression (exceedance prediction) and lasso linear regression (concentration prediction) of \u003cem\u003eAlternaria\u003c/em\u003e (\u003cem\u003eAlt\u003c/em\u003e) and \u003cem\u003eEpicoccum\u003c/em\u003e (\u003cem\u003eEpi\u003c/em\u003e) spore levels across five monitoring sites, based on forecasts from 1- to 7-day prediction horizons.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"7\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSampling station\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eRegression model\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eMetric (%)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eMean\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eMax\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eMin\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003eSD\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBratislava\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLasso logistic\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eAlt\u003c/em\u003e_F1 score (\u0026gt;\u0026thinsp;80 spores/m\u003csup\u003e3\u003c/sup\u003e)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e70.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e71.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e70.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.5\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eEpi\u003c/em\u003e_F1 score (\u0026gt;\u0026thinsp;20 spores/m\u003csup\u003e3\u003c/sup\u003e)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e80.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e81\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e79.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.4\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eAlt\u003c/em\u003e_F1 score (\u0026gt;\u0026thinsp;0 spores/m\u003csup\u003e3\u003c/sup\u003e)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e99.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e99.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e99.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.1\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eEpi\u003c/em\u003e_F1 score (\u0026gt;\u0026thinsp;0 spores/m\u003csup\u003e3\u003c/sup\u003e)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e95.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e96\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e94.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.4\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLasso linear\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eAlt\u003c/em\u003e_MAE_improv.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e19.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e19.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e19.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.1\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eEpi\u003c/em\u003e_MAE_improv.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e18.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e18.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e18.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.2\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBansk\u0026aacute; Bystrica\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLasso logistic\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eAlt\u003c/em\u003e_F1 score (\u0026gt;\u0026thinsp;80 spores/m\u003csup\u003e3\u003c/sup\u003e)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e78.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e81.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e76.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e1.3\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eEpi\u003c/em\u003e_F1 score (\u0026gt;\u0026thinsp;20 spores/m\u003csup\u003e3\u003c/sup\u003e)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e57.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e58.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e57.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.4\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eAlt\u003c/em\u003e_F1 score (\u0026gt;\u0026thinsp;0 spores/m\u003csup\u003e3\u003c/sup\u003e)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e92.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e92.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e91.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.3\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eEpi\u003c/em\u003e_F1 score (\u0026gt;\u0026thinsp;0 spores/m\u003csup\u003e3\u003c/sup\u003e)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e77.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e78\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e76.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.7\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLasso linear\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eAlt\u003c/em\u003e_MAE_improv.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e21.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e23.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e20.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e1.1\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eEpi\u003c/em\u003e_MAE_improv.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e15.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e16\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e15.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.2\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePraha\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLasso logistic\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eAlt\u003c/em\u003e_F1 score (\u0026gt;\u0026thinsp;80 spores/m\u003csup\u003e3\u003c/sup\u003e)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e60.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e61.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e59.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.7\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eEpi\u003c/em\u003e_F1 score (\u0026gt;\u0026thinsp;20 spores/m\u003csup\u003e3\u003c/sup\u003e)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e52.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e52.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e51.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.4\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eAlt\u003c/em\u003e_F1 score (\u0026gt;\u0026thinsp;0 spores/m\u003csup\u003e3\u003c/sup\u003e)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e89.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e89.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e88.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.3\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eEpi\u003c/em\u003e_F1 score (\u0026gt;\u0026thinsp;0 spores/m\u003csup\u003e3\u003c/sup\u003e)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e82.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e83.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e81.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.8\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLasso linear\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eAlt\u003c/em\u003e_MAE_improv.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e15.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e16.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e15.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.3\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eEpi\u003c/em\u003e_MAE_improv.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e10.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e11.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e6.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e1.8\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBrno\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLasso logistic\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eAlt\u003c/em\u003e_F1 score (\u0026gt;\u0026thinsp;80 spores/m\u003csup\u003e3\u003c/sup\u003e)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e63.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e64.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e62.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.7\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eEpi\u003c/em\u003e_F1 score (\u0026gt;\u0026thinsp;20 spores/m\u003csup\u003e3\u003c/sup\u003e)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e66.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e67.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e64.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.9\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eAlt\u003c/em\u003e_F1 score (\u0026gt;\u0026thinsp;0 spores/m\u003csup\u003e3\u003c/sup\u003e)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e84.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e84.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e84.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.1\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eEpi\u003c/em\u003e_F1 score (\u0026gt;\u0026thinsp;0 spores/m\u003csup\u003e3\u003c/sup\u003e)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e79.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e80.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e77.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e1.0\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLasso linear\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eAlt\u003c/em\u003e_MAE_improv.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e26.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e28.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e25.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e1.0\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eEpi\u003c/em\u003e_MAE_improv.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e26.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e29.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e22.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e2.2\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePlzeň\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLasso logistic\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eAlt\u003c/em\u003e_F1 score (\u0026gt;\u0026thinsp;80 spores/m\u003csup\u003e3\u003c/sup\u003e)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e75.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e76.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e73.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.9\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eEpi\u003c/em\u003e_F1 score (\u0026gt;\u0026thinsp;20 spores/m\u003csup\u003e3\u003c/sup\u003e)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e88.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e91.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e85\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e2.7\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eAlt\u003c/em\u003e_F1 score (\u0026gt;\u0026thinsp;0 spores/m\u003csup\u003e3\u003c/sup\u003e)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e89.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e89.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e88.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.5\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eEpi\u003c/em\u003e_F1 score (\u0026gt;\u0026thinsp;0 spores/m\u003csup\u003e3\u003c/sup\u003e)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e89.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e89.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e88.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.3\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLasso linear\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eAlt\u003c/em\u003e_MAE_improv.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e22.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e23.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e22.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.2\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cem\u003eEpi\u003c/em\u003e_MAE_improv.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e34.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e34.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e33.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.5\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab4\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eLasso logistic regression results predicting the exceedance of 80 \u003cem\u003eAlternaria\u003c/em\u003e spores/m\u0026sup3; in daily airborne concentrations seven days in advance in five study areas.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"10\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c10\" colnum=\"10\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e\u003cp\u003eBratislava\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e\u003cp\u003eBansk\u0026aacute; Bystrica\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c6\" namest=\"c5\"\u003e\u003cp\u003ePraha\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c8\" namest=\"c7\"\u003e\u003cp\u003eBrno\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c10\" namest=\"c9\"\u003e\u003cp\u003ePlzeň\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMetrics\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eMetrics\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eMetrics\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eMetrics\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eMetrics\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAccuracy\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e85.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eAccuracy\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e89.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eAccuracy\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e89.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eAccuracy\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e86.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eAccuracy\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e91.0\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSensitivity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e77.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eSensitivity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e83.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eSensitivity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e76.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eSensitivity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e84.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eSensitivity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e83.6\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSpecificity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e87.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eSpecificity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e91.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eSpecificity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e91.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eSpecificity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e86.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eSpecificity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e92.4\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePrecision\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e65.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003ePrecision\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e73.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003ePrecision\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e50.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003ePrecision\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e50.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003ePrecision\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e67.8\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eF1 score\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e71.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eF1 score\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e77.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eF1 score\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e60.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eF1 score\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e63.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eF1 score\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e74.9\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e-3.017\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e-2.009\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e-5.26\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e-3.474\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e-4.402\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e-2.04\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e-1.484\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e-4.325\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e-2.168\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e-3.043\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e (lag 8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.044\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e (lag 3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.071\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.087\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.047\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e (lag 4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.064\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.029\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e (lag 9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.051\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eWS\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e-0.055\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e (lag 9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.038\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e (lag 5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.055\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRH (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e-0.009\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e (lag 2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.015\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eS (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.015\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eS (lag 10)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e-0.009\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eWS (lag 11)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.323\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eP (lag 1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.007\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eP (lag 11)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.008\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eP\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.01\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eRH (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e (lag 6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.019\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eWS (lag 7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e-0.012\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eRH (lag 9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eP (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.002\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eS (lag 9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.025\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eS (lag 9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e (lag 10)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eRH (lag 12)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eS (lag 12)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eWS (lag 11)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eRH (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eWS (lag 3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eP\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"10\"\u003e\u003cem\u003eT\u003c/em\u003e\u003csub\u003e\u003cem\u003emean\u003c/em\u003e\u003c/sub\u003e \u0026minus; mean air temperature; \u003cem\u003eT\u003c/em\u003e\u003csub\u003e\u003cem\u003emin\u003c/em\u003e\u003c/sub\u003e \u0026minus; minimum air temperature; \u003cem\u003eT\u003c/em\u003e\u003csub\u003e\u003cem\u003emax\u003c/em\u003e\u003c/sub\u003e \u0026minus; maximum air temperature; \u003cem\u003eP\u003c/em\u003e \u0026ndash; precipitation; \u003cem\u003eRH\u003c/em\u003e \u0026ndash; relative humidity; \u003cem\u003eS\u003c/em\u003e \u0026ndash; sunshine; \u003cem\u003eWS\u003c/em\u003e \u0026ndash; wind speed\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab5\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 7\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eLasso linear regression results predicting daily airborne \u003cem\u003eEpicoccum\u003c/em\u003e spore concentrations seven days in advance in five study areas.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"11\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c10\" colnum=\"10\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c11\" colnum=\"11\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003eBratislava\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u003cp\u003eBansk\u0026aacute; Bystrica\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\u003cp\u003ePraha\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\u003cp\u003eBrno\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\u003cp\u003ePlzeň\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eClassification\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eMetric\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eMetric\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eMetric\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eMetric\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eMetric\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eAccuracy\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e93.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eAccuracy\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e73.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eAccuracy\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e86.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eAccuracy\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e79.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eAccuracy\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e85.3\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSensitivity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e94.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eSensitivity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e82.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eSensitivity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e78.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eSensitivity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e77.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eSensitivity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e86.6\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSpecificity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e93.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eSpecificity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e63.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eSpecificity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e92.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eSpecificity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e81.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eSpecificity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e82.8\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003ePrecision\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e96.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003ePrecision\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e71.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003ePrecision\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e85.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003ePrecision\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e82.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003ePrecision\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e91.4\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eF1 score\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e95.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eF1 score\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e76.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eF1 score\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e81.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eF1 score\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e79.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eF1 score\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e88.9\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-2.459\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e-1.442\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e-2.437\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e-1.808\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e-3.513\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-0.115\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e-0.977\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e-1.717\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e-1.637\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0.14\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.096\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e (lag 2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.062\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.026\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.043\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e-0.164\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-1.298\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eS (lag 11)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.039\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eS (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e (lag 9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.019\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e-1.59\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e (lag 1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.046\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e (lag 3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e (lag 12)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.012\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eP (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.03\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eRH (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0.051\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eWS\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.032\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eRH (lag 12)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.009\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.007\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eS (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.008\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0.055\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eP (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.008\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eWS (lag 11)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.103\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eWS (lag 8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e-0.005\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eWS (lag 9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e-0.011\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eS (lag 9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0.037\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eRH (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.003\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eP (lag 2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.007\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eP (lag 3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e-0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eWS (lag 12)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e-0.04\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eS (lag 7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.006\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e (lag 3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eRH (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eRH (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eP (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRegression\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eMetric\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eValue\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eMetric\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eValue\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eMetric\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eValue\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eMetric\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eValue\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eMetric\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003eValue\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eMAE_model\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e31.16\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eMAE_model\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e16.05\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eMAE_model\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e11.21\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eMAE_model\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e15.72\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eMAE_model\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e23.54\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eMAE_baseline\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e38.23\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eMAE_baseline\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e19.04\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eMAE_baseline\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e11.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eMAE_baseline\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e21.41\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eMAE_baseline\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e35.72\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eMAE_imrov.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e18.5%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eMAE_imrov.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e15.7%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eMAE_imrov.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e6.4%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eMAE_imrov.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e26.6%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eMAE_imrov.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e34.1%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-1.35\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e-0.954\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e-1.321\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e-1.678\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e-1.019\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.026\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e-0.271\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e (lag 9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.054\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eRH (lag 1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.012\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e-0.681\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-0.152\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e (lag 11)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.012\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e (lag 9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e-0.025\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e-0.271\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0.013\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eP (lag 1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.006\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.011\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e-0.261\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e-0.005\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e (lag 11)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0.014\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eWS (lag 1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-0.014\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eRH\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.004\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eRH\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.007\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eP (lag 2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.007\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e (lag 10)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0.012\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eRH (lag 1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eP\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.006\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e (lag 10)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.016\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.004\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eRH (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0.005\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eS (lag 9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.007\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eWS (lag 11)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e-0.044\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eWS (lag 1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.015\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eWS (lag 1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e-0.059\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eWS\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.002\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eP\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.005\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eS (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e-0.007\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eS (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eS (lag 9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e-0.003\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eS (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eP (lag 8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"11\"\u003e\u003cem\u003eT\u003c/em\u003e\u003csub\u003e\u003cem\u003emean\u003c/em\u003e\u003c/sub\u003e \u0026minus; mean air temperature; \u003cem\u003eT\u003c/em\u003e\u003csub\u003e\u003cem\u003emin\u003c/em\u003e\u003c/sub\u003e \u0026minus; minimum air temperature; \u003cem\u003eT\u003c/em\u003e\u003csub\u003e\u003cem\u003emax\u003c/em\u003e\u003c/sub\u003e \u0026minus; maximum air temperature; \u003cem\u003eP\u003c/em\u003e \u0026ndash; precipitation; \u003cem\u003eRH\u003c/em\u003e \u0026ndash; relative humidity; \u003cem\u003eS\u003c/em\u003e \u0026ndash; sunshine; \u003cem\u003eWS\u003c/em\u003e \u0026ndash; wind speed\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cdiv id=\"Sec10\" class=\"Section3\"\u003e\u003ch2\u003e3.2.1 Lasso logistic regression models \u0026ndash; prediction of the threshold exceedance\u003c/h2\u003e\u003cp\u003eLasso logistic regression models achieved overall good classification accuracy for both taxa. For \u003cem\u003eAlternaria\u003c/em\u003e (Tables\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e and S1\u0026ndash;S5), the mean sensitivity and specificity across all forecast horizons were 80.3% and 90.3%, respectively. The highest sensitivity was observed in BR (84.6%) and lowest in BA (74.4%). Specificity reached the highest value in PL (93%) and lowest in BR (86.4%). For \u003cem\u003eEpicoccum\u003c/em\u003e (Tables\u0026nbsp;\u003cspan refid=\"Tab6\" class=\"InternalRef\"\u003e5\u003c/span\u003e and S6\u0026ndash;S10), the mean sensitivity and specificity were 81.6% and 88.2%, respectively, with the best sensitivity recorded in BB (89.2%) and the highest specificity in PL (97.2%).\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab6\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 5\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eLasso logistic regression results predicting the exceedance of 20 \u003cem\u003eEpicoccum\u003c/em\u003e spores/m\u0026sup3; in daily airborne concentrations seven days in advance in five study areas.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"10\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c10\" colnum=\"10\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e\u003cp\u003eBratislava\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e\u003cp\u003eBansk\u0026aacute; Bystrica\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c6\" namest=\"c5\"\u003e\u003cp\u003ePraha\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c8\" namest=\"c7\"\u003e\u003cp\u003eBrno\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c10\" namest=\"c9\"\u003e\u003cp\u003ePlzeň\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMetrics\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eMetrics\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eMetrics\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eMetrics\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eMetrics\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAccuracy\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e87.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eAccuracy\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e82.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eAccuracy\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e83.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eAccuracy\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e86.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eAccuracy\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e93.9\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSensitivity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e86.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eSensitivity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e86.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eSensitivity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e81.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eSensitivity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e69.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eSensitivity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e89.6\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSpecificity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e87.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eSpecificity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e81.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eSpecificity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e83.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eSpecificity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e90.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eSpecificity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e96.6\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePrecision\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e74.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003ePrecision\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e43.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003ePrecision\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e38.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003ePrecision\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e64.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003ePrecision\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e94.3\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eF1 score\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e79.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eF1 score\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e57.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eF1 score\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e52.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eF1 score\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e66.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eF1 score\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e91.9\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e-3.661\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e-1.638\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e-3.705\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e-4.781\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e-2.575\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e-1.416\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e (lag 2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.053\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e-1.218\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e-1.922\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e-1.858\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.077\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e-0.555\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e (lag 8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.073\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e-0.059\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.067\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRH (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e-0.019\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e (lag 7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.043\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eWS\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e-0.08\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.048\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e (lag 8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.035\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eS (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e-0.05\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e (lag 4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.034\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e (lag 11)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.013\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eRH (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.023\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e (lag 6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.049\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eP (lag 2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.008\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eRH (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eP\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.017\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e (lag 12)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e-0.022\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eRH (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.022\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eWS (lag 1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.027\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eS (lag 9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eS (lag 12)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.029\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eWS (lag 12)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.066\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eP\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eRH (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eP (lag 3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.017\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eS (lag 11)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.01\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eWS (lag 11)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eS (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eWS (lag 1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e-0.042\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eP (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.005\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"10\"\u003e\u003cem\u003eT\u003c/em\u003e\u003csub\u003e\u003cem\u003emean\u003c/em\u003e\u003c/sub\u003e \u0026minus; mean air temperature; \u003cem\u003eT\u003c/em\u003e\u003csub\u003e\u003cem\u003emin\u003c/em\u003e\u003c/sub\u003e \u0026minus; minimum air temperature; \u003cem\u003eT\u003c/em\u003e\u003csub\u003e\u003cem\u003emax\u003c/em\u003e\u003c/sub\u003e \u0026minus; maximum air temperature; \u003cem\u003eP\u003c/em\u003e \u0026ndash; precipitation; \u003cem\u003eRH\u003c/em\u003e \u0026ndash; relative humidity; \u003cem\u003eS\u003c/em\u003e \u0026ndash; sunshine; \u003cem\u003eWS\u003c/em\u003e \u0026ndash; wind speed\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003eF1 scores, which balance sensitivity and precision, reached up to 88.6% for \u003cem\u003eEpicoccum\u003c/em\u003e in PL and 78.5% for \u003cem\u003eAlternaria\u003c/em\u003e in BB (Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e), suggesting that the models were particularly effective in identifying high-risk days in those locations. Conversely, the lowest F1 scores were observed in PR (60.4% for \u003cem\u003eAlternaria\u003c/em\u003e, 52.1% for \u003cem\u003eEpicoccum\u003c/em\u003e).\u003c/p\u003e\u003cp\u003eThe influence of meteorological predictors, often with time lags, on exceedance probability varied by taxa and site. With a few exceptions, temperature and precipitation generally had a positive effect on both analysed taxa. Sunshine and wind speed proved as a significant parameter, but with a mixed impact on both studied spore types in different cities. Relative humidity had a mixed effect on \u003cem\u003eAlternaria\u003c/em\u003e and a mostly positive effect on \u003cem\u003eEpicoccum\u003c/em\u003e.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec11\" class=\"Section3\"\u003e\u003ch2\u003e3.2.2 Lasso linear regression models \u0026ndash; prediction of spore concentration\u003c/h2\u003e\u003cp\u003eThe lasso linear regression models (Tables\u0026nbsp;\u003cspan refid=\"Tab7\" class=\"InternalRef\"\u003e6\u003c/span\u003e, \u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e7\u003c/span\u003e and S11\u0026ndash;S20) were used to predict daily airborne concentrations of \u003cem\u003eAlternaria\u003c/em\u003e and \u003cem\u003eEpicoccum\u003c/em\u003e spores in days with non-zero spore concentration determined by the lasso logistic models. Logistic models have a very good prediction ability, expressed by the F1 score, reaching up to 99.3% for \u003cem\u003eAlternaria\u003c/em\u003e and 95.5% for \u003cem\u003eEpicoccum\u003c/em\u003e (both in BA). The lowest value was 84.4% for \u003cem\u003eAlternaria\u003c/em\u003e in BR and 77.1% for \u003cem\u003eEpicoccum\u003c/em\u003e in BB (Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e). The lasso linear regression models were evaluated by comparing the model performance with a persistence-based baseline using mean absolute error (MAE). Improvements in MAE ranged from 15.7% (PR) to 26% (BR) for \u003cem\u003eAlternaria\u003c/em\u003e, and from 10.1% (PR) to 34.2% (PL) for \u003cem\u003eEpicoccum\u003c/em\u003e (Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e). The best model performance for \u003cem\u003eAlternaria\u003c/em\u003e was observed in PR, followed by BA; for \u003cem\u003eEpicoccum\u003c/em\u003e, it was highest in PR, followed by BB.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab7\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 6\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eLasso linear regression results predicting daily airborne \u003cem\u003eAlternaria\u003c/em\u003e spore concentrations seven days in advance in five study areas.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"11\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c10\" colnum=\"10\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c11\" colnum=\"11\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003eBratislava\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u003cp\u003eBansk\u0026aacute; Bystrica\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\u003cp\u003ePraha\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c9\" namest=\"c8\"\u003e\u003cp\u003eBrno\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c11\" namest=\"c10\"\u003e\u003cp\u003ePlzeň\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eClassification\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eMetric\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eMetric\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eMetric\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eMetric\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eMetric\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eAccuracy\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e99.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eAccuracy\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e88.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eAccuracy\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e90.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eAccuracy\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e81.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eAccuracy\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e87.1\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSensitivity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e100\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eSensitivity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e92.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eSensitivity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e91.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eSensitivity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e84.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eSensitivity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e92.7\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSpecificity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e97.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eSpecificity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e81.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eSpecificity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e89.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eSpecificity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e77.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eSpecificity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e79.8\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003ePrecision\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e98.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003ePrecision\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e91.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003ePrecision\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e87.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003ePrecision\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e83.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003ePrecision\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e85.8\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eF1 score\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e99.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eF1 score\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e91.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eF1 score\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e89.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eF1 score\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e84.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eF1 score\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e89.1\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-4.697\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e-2.32\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e-2.076\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e-2.878\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e-3.13\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-1.717\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.086\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e-1.862\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e-1.801\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e-1.684\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.108\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e-0.774\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e (lag 8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.036\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e (lag 1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.042\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0.105\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-0.085\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eWS (lag 11)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.12\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.026\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eS (lag 8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.019\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e-0.109\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eS (lag 1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.031\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eRH (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e-0.008\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eP\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.019\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0.064\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eP (lag 12)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.012\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eWS\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e-0.04\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.005\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eRH (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0.031\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eRH (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eRH (lag 11)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eP (lag 10)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.017\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eWS (lag 6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.027\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eS (lag 8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0.026\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eWS\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.005\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eS\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eS (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.008\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eRH (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e-0.002\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eWS (lag 12)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0.093\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eP (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e (lag 8)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eP (lag 5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRegression\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eMetric\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eValue\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eMetric\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eValue\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eMetric\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eValue\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eMetric\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eValue\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eMetric\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003eValue\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eMAE_model\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e76.42\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eMAE_model\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e55.44\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eMAE_model\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e56.57\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eMAE_model\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e39.95\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eMAE_model\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e35.44\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eMAE_baseline\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e94.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eMAE_baseline\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e70.33\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eMAE_baseline\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e66.87\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eMAE_baseline\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e54.09\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eMAE_baseline\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e45.73\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eMAE_imrov.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e19.5%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eMAE_imrov.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e21.2%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eMAE_imrov.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e15.4%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eMAE_imrov.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e26.2%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eMAE_imrov.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e22.5%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003ePredictor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003eCoeff.\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-1.545\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e-0.927\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e-1.62\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e-1.78\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003emonth_sin\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e-0.772\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-1.009\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e-0.626\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e-1.31\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e-1.039\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003emonth_cos\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e-0.758\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e (lag 2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.05\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e (lag 10)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.049\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.045\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e (lag 9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0.042\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.011\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e (lag 11)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.022\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eRH (lag 9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e-0.004\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e-0.027\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e (lag 6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0.041\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eP (lag 1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.006\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e (lag 12)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.019\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eT\u003csub\u003emean\u003c/sub\u003e (lag 10)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.006\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eT\u003csub\u003emin\u003c/sub\u003e (lag 11)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.025\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eWS (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0.021\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eWS (lag 12)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-0.028\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eWS\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e-0.055\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e (lag 12)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.005\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eWS (lag 4)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e-0.037\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eP (lag 6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eRH (lag 1)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eRH (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e-0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eS (lag 12)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e-0.007\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eP (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.006\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e (lag 9)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eT\u003csub\u003emax\u003c/sub\u003e (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eP (lag 2)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eP (lag 12)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.006\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eRH (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e-0.002\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eRH (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eS (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eS (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eWS (lag 11)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e-0.002\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eS (lag 13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eS (lag 11)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"11\"\u003e\u003cem\u003eT\u003c/em\u003e\u003csub\u003e\u003cem\u003emean\u003c/em\u003e\u003c/sub\u003e \u0026minus; mean air temperature; \u003cem\u003eT\u003c/em\u003e\u003csub\u003e\u003cem\u003emin\u003c/em\u003e\u003c/sub\u003e \u0026minus; minimum air temperature; \u003cem\u003eT\u003c/em\u003e\u003csub\u003e\u003cem\u003emax\u003c/em\u003e\u003c/sub\u003e \u0026minus; maximum air temperature; \u003cem\u003eP\u003c/em\u003e \u0026ndash; precipitation; \u003cem\u003eRH\u003c/em\u003e \u0026ndash; relative humidity; \u003cem\u003eS\u003c/em\u003e \u0026ndash; sunshine; \u003cem\u003eWS\u003c/em\u003e \u0026ndash; wind speed\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003eThe influence of meteorological predictors was similar to the lasso logistic models, with the exception of wind speed having a negative effect on both spore types and relative humidity having a mostly negative effect on \u003cem\u003eAlternaria\u003c/em\u003e and a positive effect on \u003cem\u003eEpicoccum\u003c/em\u003e.\u003c/p\u003e\u003cp\u003eIn general, the models captured seasonal trends well and provided reasonable forecasts for low and moderate concentrations. However, graphical outputs (Figs. S1\u0026ndash;S5) clearly show that the models systematically underestimated higher daily concentrations, particularly during peak events. This limitation was more pronounced for \u003cem\u003eAlternaria\u003c/em\u003e, which exhibits more abrupt and intense peak episodes compared to \u003cem\u003eEpicoccum\u003c/em\u003e.\u003c/p\u003e\u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab8\" class=\"InternalRef\"\u003e8\u003c/span\u003e presents examples of 1- and 7-day ahead predictions of threshold exceedance and spore concentrations for two analysed taxa at five sites. The model accurately predicted threshold exceedance for \u003cem\u003eAlternaria\u003c/em\u003e at all sites except PL, but generally underestimated spore concentrations. For \u003cem\u003eEpicoccum\u003c/em\u003e, the model correctly predicted threshold exceedance at all locations. Predicted spore concentrations aligned well with observed values, demonstrating good overall agreement between predictions and measurements.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab8\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 8\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eExample predictions of threshold exceedance and spore concentrations (1- and 7-day ahead) for \u003cem\u003eAlternaria\u003c/em\u003e and \u003cem\u003eEpicoccum\u003c/em\u003e at five monitoring sites.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"8\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTaxon\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSampling\u003c/p\u003e\u003cp\u003estation\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eDate\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003ePredicted threshold exceedance\u003c/p\u003e\u003cp\u003e(1-day ahead)*\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003ePredicted threshold exceedance\u003c/p\u003e\u003cp\u003e(7-day ahead)*\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003ePredicted spore concentration\u003c/p\u003e\u003cp\u003e(1-day ahead)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003ePredicted spore concentration (7-day ahead)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c8\"\u003e\u003cp\u003eObserved spore concentration\u003c/p\u003e\u003cp\u003e(spores/m\u003csup\u003e3\u003c/sup\u003e)\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cem\u003eAlternaria\u003c/em\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eBratislava\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e21.9.2024\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e127\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e129\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e380\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eBansk\u0026aacute; Bystrica\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e20.7.2023\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e80\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e58\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e260\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003ePraha\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e19.7.2023\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e80\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e65\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e112\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eBrno\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e15.8.2023\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e128\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e77\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e147\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003ePlzeň\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e29.8.2023\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e50\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e46\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e34\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cem\u003eEpicoccum\u003c/em\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eBratislava\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e21.9.2024\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e66\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e60\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e119\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eBansk\u0026aacute; Bystrica\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e20.7.2023\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e18\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e19\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e8\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003ePraha\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e19.7.2023\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e14\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e14\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e10\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eBrno\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e15.8.2023\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e42\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e36\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e35\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003ePlzeň\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e29.8.2023\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e60\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e46\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e53\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"8\"\u003e*Binary values indicate predicted threshold exceedance: 80 spores/m\u0026sup3; for \u003cem\u003eAlternaria\u003c/em\u003e and 20 spores/m\u0026sup3; for \u003cem\u003eEpicoccum\u003c/em\u003e (1\u0026thinsp;=\u0026thinsp;exceedance predicted. 0\u0026thinsp;=\u0026thinsp;no exceedance predicted)\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e"},{"header":"4 Discussion","content":"\u003cp\u003eIn recent years, predictive modelling has become a valuable tool for assessing the risk of airborne allergens and phytopathogenic fungi. Unlike the pollen grains of different plant species that have a clear seasonal pattern, the release of fungal spores of the studied genera is spread over a longer period. These spores are produced asexually (conidia), and as such, do not depend on the seasonality of reproduction but only on the availability of growth substrate, in this case plant matter. Their seasonal patterns therefore reflect the growth of plants, with a peak during the summer, when the biomass is most abundant, consistent with the analysis of Kasprzyk (\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e2008\u003c/span\u003e) stating that maximum concentration of most spores occurs in summer or early autumn. \u003cem\u003eAlternaria\u003c/em\u003e is mostly a phytopathogenic genus with specific plant hosts (Marin-Felix et al., \u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e2019\u003c/span\u003e), while \u003cem\u003eEpicoccum\u003c/em\u003e is a saprophytic genus with a broad host spectrum (Lee et al., \u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e2020\u003c/span\u003e). This explains the earlier beginning and peak of \u003cem\u003eAlternaria\u003c/em\u003e spore season, corresponding with the time of harvest, which promotes mechanical release of spores from fungi growing on cereals. The spore season of \u003cem\u003eEpicoccum\u003c/em\u003e has a later start with more variation in peak date, since it depends on the local distribution of dead plant matter.\u003c/p\u003e\u003cp\u003eThe actual daily spore concentrations during the spore season depend on many variables. Accurate predicting requires complex statistical procedures with many input variables, limiting their practical use in operational forecasting. On the other hand, simplification can make this process easier regarding data availability, e.g., De Linares et al. (\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e2010\u003c/span\u003e) used simplified categorical (dummy) precipitation variables. This, however, decreases the accuracy of the model. It is a challenge to find the balance between these two approaches, and our models made this compromise by utilising continuous meteorological data. By including time-lagged variables and selecting optimal lags based on cross-validation and correlation metrics, we were able to balance model complexity with predictive performance. Importantly, the use of lasso regression allowed automatic variable selection, which improved generalisability and prevented overfitting \u0026ndash; a challenge frequently encountered in environmental prediction models (Tibshirani, \u003cspan citationid=\"CR46\" class=\"CitationRef\"\u003e1996\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eConsistent with previous studies (e.g., Grinn-Gofroń and Strzelczak, \u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e2013\u003c/span\u003e; Aira et al., \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2013\u003c/span\u003e; V\u0026eacute;lez-Pereira et al., \u003cspan citationid=\"CR51\" class=\"CitationRef\"\u003e2016\u003c/span\u003e; Grinn-Gofroń et al., \u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e2019\u003c/span\u003e), air temperature and precipitation were identified as some of the most influential predictors of fungal spore concentrations, showing predominantly positive associations. The most noticeable difference between the two genera was in the response to relative humidity, which had a mostly negative effect on \u003cem\u003eAlternaria\u003c/em\u003e and a positive effect on \u003cem\u003eEpicoccum\u003c/em\u003e. This can again be explained by their substrate preference. The factors influencing plant growth have a positive influence on both genera, but relative humidity promotes the decay of dead plant matter and so increases the sporulation of \u003cem\u003eEpicoccum\u003c/em\u003e. Using lagged data provides important context for environmental parameters. This is most visible in the influence of precipitation, which has been reported to have a negative influence on fungal spore concentrations in other studies only using daily data (Oliveira et al., \u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e2009\u003c/span\u003e; Ščevkov\u0026aacute; and Kov\u0026aacute;č, \u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e2019\u003c/span\u003e; Žilka et al., \u003cspan citationid=\"CR53\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). This is due to the rain-out and wash-out effect (Sakiyan and Inceoğlu, \u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e2003\u003c/span\u003e), but the positive effect of precipitation on plant growth also increases the growth and sporulation of fungi using these plants as substrate, which is visible in our data and consistent with the studies of van der Waals et al. (\u003cspan citationid=\"CR48\" class=\"CitationRef\"\u003e2003\u003c/span\u003e) and Knutsen et al. (\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e2012\u003c/span\u003e). Interestingly, the impact of sunshine duration and wind speed was more variable, sometimes even showing opposite effects across sites or taxa. These findings are consistent with literature reporting location-specific responses to microclimatic factors (V\u0026eacute;lez-Pereira et al., \u003cspan citationid=\"CR50\" class=\"CitationRef\"\u003e2019\u003c/span\u003e). The clear inter-site differences in model coefficients underscore the importance of regional calibration in aerobiological forecasting. Such distinctions in meteorological responsiveness are important for refining predictive models and improving risk assessments related to airborne fungal spores.\u003c/p\u003e\u003cp\u003eUsing the F1 scores allows to balance both precision and sensitivity of the model, unlike using only one of these parameters (e.g., V\u0026eacute;lez-Pereira et al., \u003cspan citationid=\"CR50\" class=\"CitationRef\"\u003e2019\u003c/span\u003e). Our models showed high classification accuracy when predicting threshold exceedance, particularly for \u003cem\u003eEpicoccum\u003c/em\u003e, where F1 scores reached up to 88.6%, which falls within the \u0026ldquo;excellent\u0026rdquo; discrimination category (80\u0026ndash;90%) defined by Hosmer and Lemeshow (\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e2000\u003c/span\u003e), indicating that the lasso logistic regression models are well suited for practical applications. The lowest F1 scores for both genera were recorded in PR, the biggest of the studied cities, reflecting possible challenges in predicting exceedance events in some highly urbanised environments with a high percentage of built-up areas and connected microclimatic conditions, like the urban heat island effect (Franceschi et al., \u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e2023\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eSimilar to observations by V\u0026eacute;lez-Pereira et al. (\u003cspan citationid=\"CR50\" class=\"CitationRef\"\u003e2019\u003c/span\u003e), we noted that model performance varied with the threshold spore abundance. Lower threshold values tend to yield more accurate results, which explains the higher accuracy of the model for \u003cem\u003eEpicoccum\u003c/em\u003e with a lower set threshold value. For \u003cem\u003eAlternaria\u003c/em\u003e, the 80 spores/m\u0026sup3; threshold is well established in clinical literature (Rapiejko et al., \u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e2007\u003c/span\u003e), but for \u003cem\u003eEpicoccum\u003c/em\u003e, no universally accepted threshold exists. The 20 spores/m\u0026sup3; threshold used here was selected based on prior aerobiological conventions (Rodinkova et al., \u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e2015\u003c/span\u003e), but future research should aim to validate this value in the context of clinical symptom onset, leaving room for future adjustments to the models as more accurate allergological data becomes available. Other factors, including microclimatic conditions, local environmental specifics, and data quality and availability, also influence model performance (Anees-Hill et al., \u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e2022\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eWhile the lasso logistic models predicting threshold exceedance demonstrated overall strong performance, the lasso linear regression models estimating daily spore concentrations systematically underestimated higher concentration values, particularly for \u003cem\u003eAlternaria\u003c/em\u003e. This limitation has also been reported by other authors (Skj\u0026oslash;th et al., \u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e2012\u003c/span\u003e; Apangu et al., \u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e2022\u003c/span\u003e) and may be attributed to the episodic nature of spore releases associated with harvest activities or storm events \u0026ndash; factors that are difficult to capture using meteorological variables alone. The inclusion of land use data, crop phenology, and remote sensing indicators (e.g., Normalised Difference Vegetation Index \u0026ndash; NDVI) may improve performance, especially during high-variability periods (Pettorelli et al., \u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e2011\u003c/span\u003e; Pervez et al., \u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e2021\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eOur findings reaffirm the importance of long-term aerobiological monitoring in multiple bioclimatic zones. Site-specific differences in both spore dynamics and model performance highlight that predictive systems should be locally validated and tailored to regional environmental conditions. The models presented in this study provide a valuable foundation for operational forecasting of fungal spore concentrations. Given that they rely on widely available meteorological data, they could be readily adjusted to different local conditions and implemented in regional alert systems to inform allergy sufferers or farmers about periods of elevated spore risk. The ability to forecast up to seven days in advance offers substantial lead time for preventive actions.\u003c/p\u003e"},{"header":"5 Conclusions","content":"\u003cp\u003eOur study aimed to develop interpretable, meteorologically driven models to predict daily concentrations and threshold exceedances of \u003cem\u003eAlternaria\u003c/em\u003e and \u003cem\u003eEpicoccum\u003c/em\u003e spores across multiple bioclimatic regions in Central Europe. For the genus \u003cem\u003eEpicoccum\u003c/em\u003e, this study is the first of its kind. By employing lasso logistic and lasso linear regression approaches, we were able to identify key meteorological predictors, including lagged data, and generate forecasts up to seven days in advance with promising accuracy. We have identified temperature and precipitation as the main factors positively influencing spore concentrations of both species in the following days, while the influence of relative humidity was mostly negative on the phytopathogenic genus \u003cem\u003eAlternaria\u003c/em\u003e and positive on the saprophytic genus \u003cem\u003eEpicoccum\u003c/em\u003e. The lasso linear regression models successfully captured seasonal and meteorological patterns in spore concentrations and provided meaningful improvements over the baseline predictions. However, their limitations in predicting peak events, especially for \u003cem\u003eAlternaria\u003c/em\u003e, underscore the importance of combining concentration-based and threshold-based approaches for comprehensive aerobiological forecasting. Our findings support the integration of these models into operational forecasting systems, leveraging readily available meteorological data to inform public health alerts and agricultural management. Further improvements, particularly for \u003cem\u003eEpicoccum\u003c/em\u003e, may be achieved by validating clinical thresholds and incorporating land use or remote sensing data.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eCompeting Interests and Funding:\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare that they have no conflict of interest.This study was supported by the Grant Agency VEGA (Bratislava), Grant No. 1/0180/22.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAcknowledgements\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors acknowledge the Slovak Hydrometeorological Institute and the Czech Hydrometeorological Institute for providing meteorological data used in this paper. This study was supported by the Grant Agency VEGA (Bratislava), Grant No. 1/0180/22.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthors' contributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eJana Ščevková:\u003c/strong\u003e Conceptualisation, Methodology, Supervision, Data curation, Validation, Writing ‒ original draft. \u003cstrong\u003eJozef Dušička:\u003c/strong\u003e Data curation, Writing ‒ review \u0026amp; editing. \u003cstrong\u003eJanka Laffersová:\u003c/strong\u003e Data curation, Writing ‒ review \u0026amp; editing. \u003cstrong\u003eOndřej Rybníček:\u003c/strong\u003e Data curation, Writing ‒ review \u0026amp; editing. \u003cstrong\u003eNatália Štefániková:\u003c/strong\u003e Data curation, Writing ‒ review \u0026amp; editing. \u003cstrong\u003eMatúš Žilka:\u003c/strong\u003e Data curation, Writing ‒ review \u0026amp; editing. \u003cstrong\u003eEva Zahradníková:\u003c/strong\u003e Visualisation, Writing ‒ review \u0026amp; editing. \u003cstrong\u003eMichal Hrabovský:\u003c/strong\u003e Formal analysis, Visualisation, Writing ‒ review \u0026amp; editing. \u003cstrong\u003eJozef Kováč:\u003c/strong\u003e Formal analysis, Validation, Writing ‒ review \u0026amp; editing.\u0026nbsp;\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eAbel-Fern\u0026aacute;ndez, E., Mart\u0026iacute;nez, M. J., Gal\u0026aacute;n, T., Pineda, F. (2023) Going over fungal allergy: \u003cem\u003eAlternaria alternata\u003c/em\u003e and its allergens. J Fungi, 9, 582. https://doi.org/10.3390/jof9050582 \u003c/li\u003e\n\u003cli\u003eAira, M. J., Rodriguez-Rajo, F. J., Fernandez-Gonzalez, M., Seijo, C., Elvira-Rendueles, B., Abreu, I., Gutierrez-Bustillo, M., Perez Sanchez, E., Oliveira, M., Recio, M., Tormo, R., Morales, J. (2013) Spatial and temporal distribution of \u003cem\u003eAlternaria\u003c/em\u003e spores in the Iberian Peninsula atmosphere, and meteorological relationships: 1993-2009. Int J Biometeorol, 57, 265\u0026ndash;274. https://doi.org/10.1007/s00484-012-0550-x\u003c/li\u003e\n\u003cli\u003eAira, M. J., Rodriguez-Rajo, F., Jato, V. (2008) 47 annual records of allergenic fungi spore: predictive models from the NW Iberian Peninsula. Ann Agric Environ Med, 15, 91\u0026ndash;8.\u003c/li\u003e\n\u003cli\u003eAnees-Hill, S., Douglas, P., Pashley, C. H., Hansell, A., Marczylo, E. L. (2022) A systematic review of outdoor airborne fungal spore seasonality across Europe and the implications for health. Sci Total Environ, 818, 151716. https://doi.org/10.1016/j.scitotenv.2021.151716\u003c/li\u003e\n\u003cli\u003eApangu, G. P., Adams-Groom, B., Satchwell, J., Pashley, C. H., Werner, M., Kryza, M., Szymanowski, M., Malkiewicz, M., Bruffaerts, N., Hoebeke, L., Grinn-Gofroń, A., Grewling, Ł., Roldan, N. G., Oliver, G., Sindt, Ch., Kloster, M., Skj\u0026oslash;th, C. A. (2022) Sentinel-2 satellite and HYSPLIT model suggest that local cereal harvesting substantially contribute to peak \u003cem\u003eAlternaria\u003c/em\u003e spore concentrations. Agric Forest Meteorol, 326, 109156. https://doi.org/10.1016/j.agrformet.2022.109156\u003c/li\u003e\n\u003cli\u003eBalendres, M. A., Angeles, Y., Calabon, M., Cruz, M. A., Flores, A., Fronda, M., Guerrero, J. J., Jamago, J., Millado, J. B., Montecalvo, M., Seco, M. N., Yusingco, A. I. (2025) \u003cem\u003eEpicoccum\u003c/em\u003e. In: Amaresan, N., Kumar, K. (Eds.) \u003cem\u003eCompendium of phytopathogenic microbes in agro-ecology\u003c/em\u003e. Springer Nature Switzerland AG, 289\u0026ndash;309. https://doi.org/10.1007/978-3-031-81770-0_13\u003c/li\u003e\n\u003cli\u003eBisht, V., Arora, N., Singh, B. P., Pasha, S., Gaur, S. N., Sridhara, S. (2004) Epi p 1, an allergenic glycoprotein of \u003cem\u003eEpicoccum purpurascens\u003c/em\u003e is a serine protease. FEMS Immunol Med Microbiol, 42, 205\u0026ndash;211. https://doi.org/10.1016/j.femsim.2004.05.003\u003c/li\u003e\n\u003cli\u003eBisht, V., Singh, B. P., Arora, N., Gaur, S. N., Sridhara, S. (2002) Antigenic and allergenic cross-reactivity of \u003cem\u003eEpicoccum nigrum\u003c/em\u003e with other fungi. Ann Allergy Asthma Immunol, 89, 285\u0026ndash;291. https://doi.org/10.1016/S1081-1206(10)61956-4\u003c/li\u003e\n\u003cli\u003eBousquet, P. J., Hooper, R., Kogevinas, M., Jarvis, D., Burney, P. (2007) Number of allergens to be tested to assess allergenic sensitization in epidemiologic studies: results of the European Community Respiratory Health Survey I. Clin Exp Allergy, 37, 780\u0026ndash;7. https://doi.org/10.1111/j.1365-2222.2007.02714.x\u003c/li\u003e\n\u003cli\u003eBrito, F. F., Alonso, A. M., Carn\u0026eacute;s, J., Mart\u0026iacute;n-Mart\u0026iacute;n, R., Fern\u0026aacute;ndez-Caldas, E., Galindo, P. A., Alfaya, T., Amo-Salas, M. (2012) Correlation between Alt a 1 levels and clinical symptoms in \u003cem\u003eAlternaria alternata\u003c/em\u003e-monosensitized patients. J Investig Allergol Clin Immunol, 22, 154\u0026ndash;159.\u003c/li\u003e\n\u003cli\u003eBurbach, G. J., Heinzerling, L. M., Edenharter, G., Bachert, C., Bindslev-Jensen, C., Bonini, S., et al. (2009) GA(2)LEN skin test study II: clinical relevance of inhalant allergen sensitizations in Europe. Allergy, 64, 1507\u0026ndash;1515. https://doi.org/10.1111/j.13989995.2009.02089.x\u003c/li\u003e\n\u003cli\u003eCrandall, S. G., Gilbert, G. S. (2017) Meteorological factors associated with abundance of airborne fungal spores over natural vegetation. Atmos Environ, 162, 87\u0026ndash;99. https://doi.org/10.1016/j.atmosenv.2017.05.018\u003c/li\u003e\n\u003cli\u003eDe Linares, C., Belmonte, J., Canela, M., D\u0026iacute;az de la Guardia, C., Alba-Sanchez, F., Sabariego, S., Alonso-P\u0026eacute;rez, S. (2010) Dispersal patterns of \u003cem\u003eAlternaria\u003c/em\u003e conidia in Spain. Agric Forest Meteorol, 150, 1491\u0026ndash;1500. https://doi.org/10.1016/j.agrformet.2010.07.004\u003c/li\u003e\n\u003cli\u003eElbert, W., Taylor, P. E., Andreae, M. O., P\u0026ouml;schl, U. (2007) Contribution of fungi to primary biogenic aerosols in the atmosphere: Wet and dry discharged spores, carbohydrates, and inorganic ions. Atmos Chem Phys, 7, 4569\u0026ndash;4588. https://doi.org/10.5194/acp-7-4569-2007\u003c/li\u003e\n\u003cli\u003eEN 16868:2019 Ambient air \u0026ndash; sampling and analysis of airborne pollen grains and fungal spores for allergy networks \u0026ndash; volumetric Hirst method. CEN-CENELEC Management Centre: Rue de la Science 23, B-1040 Brussels, European Committee for Standardization, 2019.\u003c/li\u003e\n\u003cli\u003eFranceschi, E., Moser-Reischl, A., Honold, M., Rahman, M. A., Pretzsch, H., Pauleit, S., R\u0026ouml;tzer, T. (2023) Urban environment, drought events and climate change strongly affect the growth of common urban tree species in a temperate city. Urban For Urban Green, 88, 128083. https://doi.org/10.1016/j.ufug.2023.128083\u003c/li\u003e\n\u003cli\u003eGabriel, M. F., Postigo, I., Tomaz, C. T., Mart\u0026iacute;nez, J. (2016) \u003cem\u003eAlternaria alternata\u003c/em\u003e allergens: Markers of exposure, phylogeny and risk of fungi-induced respiratory allergy. Environ Int, 89\u0026ndash;90, 71\u0026ndash;80. https://doi.org/10.1016/j.envint.2016.01.003\u003c/li\u003e\n\u003cli\u003eGal\u0026aacute;n, C., Smith, M., Thibaudon, M., Frenguelli, G., Oteros, J., Gehrig, R., Berger, U., Clot, B., Brandao, R., Working Group EAS QC (2014) Pollen monitoring: minimum requirements and reproducibility of analysis. Aerobiologia, 30, 385\u0026ndash;395. https://doi.org/10.1007/s10453-014-9335-5\u003c/li\u003e\n\u003cli\u003eGrinn-Gofroń, A., Nowosad, J., Bosiacka, B., Camacho, I., Pashley, C., Belmonte, J., De Linares, C., Ianovici, N., Maya Manzano, J. M., Sadyś, M., Skj\u0026oslash;th, C., Rodinkova, V., Tormo-Molina, R., Vokou, D., Fern\u0026aacute;ndez-Rodr\u0026iacute;guez, S., Damialis, A. (2019) Airborne \u003cem\u003eAlternaria\u003c/em\u003e and \u003cem\u003eCladosporium\u003c/em\u003e fungal spores in Europe: Forecasting possibilities and relationships with meteorological parameters. Sci Total Environ, 653, 938\u0026ndash;946. https://doi.org/10.1016/j.scitotenv.2018.10.419\u003c/li\u003e\n\u003cli\u003eGrinn-Gofroń, A., Strzelczak, A. (2013) Changes in concentration of \u003cem\u003eAlternaria\u003c/em\u003e and \u003cem\u003eCladosporium\u003c/em\u003e spores during summer storms. Int J Biometeorol, 57, 759\u0026ndash;68. https://doi.org/10.1007/s00484-012-0604-0\u003c/li\u003e\n\u003cli\u003eHeinzerling, L. M., Burbach, G. J., Edenharter, G., Bachert, C., Bindslev-Jensen, C., Bonini, S., et al. (2009) GA(2)LEN skin test study I: GA(2)LEN harmonization of skin prick testing: novel sensitization patterns for inhalant allergens in Europe. Allergy, 64, 1498\u0026ndash;1506. https://doi.org/10.1111/j.1398-9995.2009.02093.x\u003c/li\u003e\n\u003cli\u003eHirst, J. M. (1952) An automatic volumetric spore trap. Ann Appl Biol, 39, 257\u0026ndash;265. https://doi.org/10.1111/j.1744-7348.1952.tb00904.x\u003c/li\u003e\n\u003cli\u003eHosmer, D. W., Lemeshow, S. (2000) \u003cem\u003eApplied logistic regression\u003c/em\u003e. 2nd edition. John Wiley \u0026amp; Sons. https://doi.org/10.1002/0471722146\u003c/li\u003e\n\u003cli\u003eIanovici, N., Maria, C., Rădutoiu, M. N., Haniş, A., Tudorică, D. (2013) Variation in airborne fungal spore concentrations in four different microclimate regions in Romania. Notulae Botanicae Horti Agrobotanici Cluj-Napoca, 41, 450\u0026ndash;457.\u003c/li\u003e\n\u003cli\u003eKasprzyk, I. (2008) Aeromycology\u0026ndash;main research fields of interest during the last 25 years. Ann Agric Environ Med, 15, 1\u0026ndash;7.\u003c/li\u003e\n\u003cli\u003eKnutsen, A. P., Bush, R. K., Demain, J. G., Denning, D. W., Dixit, A., Fairs, A., Greenberger, P. A., Kariuki, B., Kita, H., Kurup, V. P., Moss, R. B., Niven, R. M., Pashley, C. H., Slavin, R. G., Vijay, H. M., Wardlaw, A. J. (2012) Fungi and allergic lower respiratory tract diseases. J Allergy Clin Immunol, 129, 280\u0026ndash;291. https://doi.org/10.1016/j.jaci.2011.12.970\u003c/li\u003e\n\u003cli\u003eKottek, M., Grieser, J., Beck, C., Rudolf, B., Rubel, F. (2006) World map of the K\u0026ouml;ppen\u0026ndash;Geiger climate classification updated. Meteorologische Zeitschrift, 15, 259\u0026ndash;263. https://doi.org/10.1127/0941-2948/2006/0130\u003c/li\u003e\n\u003cli\u003eLee, A. J., Cadelis, M. M., Kim, S. H., Swift, S., Copp, B. R., Villas-Boas, S. G. (2020) Epipyrone A, a broad-spectrum antifungal compound produced by \u003cem\u003eEpicoccum nigrum\u003c/em\u003e ICMP 19927. Molecules, 25, 5997. https://doi.org/10.3390/molecules25245997\u003c/li\u003e\n\u003cli\u003eMarin-Felix, Y., Hern\u0026aacute;ndez-Restrepo, M., Iturrieta-Gonz\u0026aacute;lez, I., Garc\u0026iacute;a, D., Gen\u0026eacute;, J., Groenewald, J. Z., Cai, L., Chen, Q., Quaedvlieg, W., Schumacher, R. K., Taylor, P. W. J., Ambers, C., Bonthond, G., Edwards, J., Krueger-Hadfield, S. A., Luangsa-Ard, J. J., Morton, L., Moslemi, A., Sandoval-Denis, M., Tan, Y. P., Thangavel, R., Vaghefi, N., Cheewangkoon, R., Crous, P. W. (2019) Genera of phytopathogenic fungi: GOPHY 3. Stud Mycol, 94, 1\u0026ndash;124. https://doi.org/10.1016/j.simyco.2019.05.001\u003c/li\u003e\n\u003cli\u003eOliveira, M., Ribeiro, H., Delgado, J. L., Abreu, I. (2009) The effects of meteorological factors on airborne fungal spore concentration in two areas differing in urbanisation level. Int J Biometeorol, 53, 61\u0026ndash;73. https://doi.org/10.1007/s00484-008-0191-2\u003c/li\u003e\n\u003cli\u003ePatel, T. Y., Buttner, M., Rivas, D., Cross, C., Bazylinski, D. A., Seggev, J. (2018) Variation in airborne fungal spore concentrations among five monitoring locations in a desert urban environment. Environ Monit Assess, 190, 634. https://doi.org/10.1007/s10661-018-7008-5\u003c/li\u003e\n\u003cli\u003ePervez, S., McNally, A., Arsenault, K., Budde, M., Rowland, J. (2021) Vegetation monitoring optimization with normalized difference vegetation index and evapotranspiration using remote sensing measurements and land surface models over East Africa. Front Clim, 3, 589981. https://doi.org/10.3389/fclim.2021.589981\u003c/li\u003e\n\u003cli\u003ePettorelli, N., Ryan, S., Mueller, T., Bunnefeld, N., Jedrzejewska, B., Lima, M., Kausrud, K. (2011) The normalized difference vegetation index (NDVI): unforeseen successes in animal ecology. Clim Res, 46, 15\u0026ndash;27. https://doi.org/10.3354/cr00936\u003c/li\u003e\n\u003cli\u003ePortnoy, J., Chapman, J., Burge, H., Muilenberg, M., Solomon, W. (1987) \u003cem\u003eEpicoccum\u003c/em\u003e allergy: skin reaction patterns and spore/mycelium disparities recognized by IgG and IgE ELISA inhibition. Ann Allergy, 59, 39\u0026ndash;43.\u003c/li\u003e\n\u003cli\u003eRapiejko, P., Stankiewicz, W., Szczygielski, K., Jurkiewicz, D. (2007) Progowe stężenie pyłku roślin niezbędnedo wywołania objaw\u0026oacute;w alergicznych./Threshold pollen count necessary to evoke allergic symptoms. Otolaryngol Pol LXI, 4, 591\u0026ndash;594 (in Polish).\u003c/li\u003e\n\u003cli\u003eReich, J., McLaren, D., Kim, Y. M., Wally, O., Yevtushenko, D., Hamelin, R., Chatterton, S. (2024) Predicting airborne ascospores of \u003cem\u003eSclerotinia sclerotiorum\u003c/em\u003e through machine learning and statistical methods. Plant Pathol, 73, 1586\u0026ndash;1601. https://doi.org/10.1111/ppa.13902\u003c/li\u003e\n\u003cli\u003eRenard, J.-B., El Azari, H., Lauthier, J., Surcin, J. (2024) Spatial variation of airborne pollen concentrations locally around Brussels city, Belgium, during a field campaign in 2022\u0026ndash;2023, using the automatic sensor Beenose. Sensors, 24, 3731. https://doi.org/10.3390/s24123731\u003c/li\u003e\n\u003cli\u003eRodinkova, V., Bilous, E. S., Motruk, I, Musatova, K. V., Slobodyanyuk, L. V., DuBuske, L. M. (2015) Seasonal and daily distribution of allergic \u003cem\u003eEpicoccum\u003c/em\u003e spores in ambient air in Vinnitsa, Ukraine. J Allergy Clin Immunol, 135, AB20. https://doi.org/10.1016/j.jaci.2014.12.996\u003c/li\u003e\n\u003cli\u003eRodr\u0026iacute;guez-Fern\u0026aacute;ndez, A., Blanco-Alegre, C., Vega-Maray, A. M., Valencia-Barrera, R. M., Moln\u0026aacute;r, T., Fern\u0026aacute;ndez-Gonz\u0026aacute;lez, D. (2023) Effect of prevailing winds and land use on \u003cem\u003eAlternaria\u003c/em\u003e airborne spore load. J Environ Manage, 332, 117414. https://doi.org/10.1016/j.jenvman.2023.117414\u003c/li\u003e\n\u003cli\u003eSakiyan, N., Inceoğlu, O. (2003) Atmospheric concentrations of \u003cem\u003eCladosporium\u003c/em\u003e Link and \u003cem\u003eAlternaria\u003c/em\u003e Nees spores in Ankara and the effects of meteorological factors. Turk J Bot, 27, 77\u0026ndash;81.\u003c/li\u003e\n\u003cli\u003eSchmey, T., Tominello-Ramirez, C. S., Brune, C., Stam, R. (2024) \u003cem\u003eAlternaria\u003c/em\u003e diseases on potato and tomato. Mol Plant Pathol, 25, 13435. https://doi.org/10.1111/mpp.13435\u003c/li\u003e\n\u003cli\u003eSkj\u0026oslash;th, C. A., Sommer, J., Frederiksen, L., Gosewinkel Karlson, U. (2012) Crop harvest in Denmark and Central Europe contributes to the local load of airborne \u003cem\u003eAlternaria\u003c/em\u003e spore concentrations in Copenhagen. Atmos Chem Phys, 12, 11107\u0026ndash;11123. https://doi.org/10.5194/acp-12-11107-2012, 2012\u003c/li\u003e\n\u003cli\u003e\u0026Scaron;čevkov\u0026aacute;, J., Kov\u0026aacute;č, J. (2019) First fungal spore calendar for the atmosphere of Bratislava, Slovakia. Aerobiologia, 35, 343\u0026ndash;356. https://doi.org/10.1007/s10453-019-09564-4\u003c/li\u003e\n\u003cli\u003eTaguiam, J. D., Evallo, E., Balendres, M. A. (2021) \u003cem\u003eEpicoccum\u003c/em\u003e species: ubiquitous plant pathogens and effective biological control agents. Eur J Plant Pathol, 159, 713\u0026ndash;725. https://doi.org/10.1007/s10658-021-02207-w\u003c/li\u003e\n\u003cli\u003eThomma, B. P. (2003) \u003cem\u003eAlternaria\u003c/em\u003e spp.: from general saprophyte to specific parasite. Mol Plant Pathol, 4, 225\u0026ndash;36. https://doi.org/10.1046/j.1364-3703.2003.00173.x\u003c/li\u003e\n\u003cli\u003eTibshirani, R. (1996) Regression shrinkage and selection via the lasso. J R Stat Soc Ser B (Methodological), 58, 267\u0026ndash;288. https://doi.org/10.1111/j.2517-6161.1996.tb02080.x\u003c/li\u003e\n\u003cli\u003eTomassetti, B., Angelosante Bruno, A., Pace, L., Verdecchia, M., Visconti, G. (2009) Prediction of \u003cem\u003eAlternaria\u003c/em\u003e and \u003cem\u003ePleospora\u003c/em\u003e concentrations from the meteorological forecast and artificial neural network in L\u0026rsquo;Aquila, Abruzzo (Central Italy). Aerobiologia, 25, 127\u0026ndash;136. https://doi.org/10.1007/s10453-009-9117-7\u003c/li\u003e\n\u003cli\u003evan der Waals, J. E., Korsten, L., Aveling, T. A. S., Denner, F. D. N. (2003) Influence of environmental factors on field concentrations of \u003cem\u003eAlternaria solani\u003c/em\u003e conidia above a South African potato crop. Phytoparasitica, 31, 353\u0026ndash;364. https://doi.org/10.1007/BF02979806\u003c/li\u003e\n\u003cli\u003eV\u0026eacute;lez-Pereira, A. M., De Linares, C., Belmonte, J. (2021) Aerobiological modeling I: A review of predictive models. Sci Total Environ, 795, 148783. https://doi.org/10.1016/j.scitotenv.2021.148783\u003c/li\u003e\n\u003cli\u003eV\u0026eacute;lez-Pereira, A. M., De Linares, C., Canela, M. A., Belmonte, J. (2019) Logistic regression models for predicting daily airborne \u003cem\u003eAlternaria\u003c/em\u003e and \u003cem\u003eCladosporium\u003c/em\u003e concentration levels in Catalonia (NE Spain). Int J Biometeorol, 63, 1541\u0026ndash;1553. https://doi.org/10.1007/s00484-019-01767-1\u003c/li\u003e\n\u003cli\u003eV\u0026eacute;lez-Pereira, A. M., De Linares, C., Delgado, R., Belmonte, J. (2016) Temporal trends of the airborne fungal spores in Catalonia (NE Spain), 1995\u0026ndash;2013. Aerobiologia, 31, 23\u0026ndash;37. https://doi.org/10.1007/s10453-015-9410-6\u003c/li\u003e\n\u003cli\u003eWoudenberg, J. H. C., Seidl, M. F., Groenewald, J. Z., de Vries, M., Stielow, J. B., Thomma, B. P. H. J., Crous, P. W. (2015) \u003cem\u003eAlternaria\u003c/em\u003e section \u003cem\u003eAlternaria\u003c/em\u003e: species, formae speciales or pathotypes? Stud Mycol, 82, 1\u0026ndash;21. https://doi.org/10.1016/j.simyco.2015.07.001\u003c/li\u003e\n\u003cli\u003eŽilka, M., Hrabovsk\u0026yacute;, M., Du\u0026scaron;ička, J., Zahradn\u0026iacute;kov\u0026aacute;, E., Gahurov\u0026aacute;, D., \u0026Scaron;čevkov\u0026aacute;, J. (2024) Comparative analysis of airborne fungal spore distribution in urban and rural environments of Slovakia. Environ Sci Pollut Res, 31, 63145\u0026ndash;63160. https://doi.org/10.1007/s11356-024-35470-5\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"international-journal-of-biometeorology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ijbm","sideBox":"Learn more about [International Journal of Biometeorology](http://link.springer.com/journal/484)","snPcode":"484","submissionUrl":"https://www.editorialmanager.com/ijbm/default2.aspx","title":"International Journal of Biometeorology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Aerobiology, Airborne fungal spores, Lasso logistic regression, Lasso linear regression, Weather-based forecasting","lastPublishedDoi":"10.21203/rs.3.rs-7210967/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7210967/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eSeveral airborne fungal spores, such as \u003cem\u003eAlternaria\u003c/em\u003e and \u003cem\u003eEpicoccum\u003c/em\u003e, are known for their allergenic potential, yet accurately predicting their atmospheric concentrations remains a challenge. This study presents predictive models for estimating daily concentrations and clinically relevant threshold exceedance events of \u003cem\u003eAlternaria\u003c/em\u003e and \u003cem\u003eEpicoccum\u003c/em\u003e spores, using long-term aerobiological and meteorological data from five cities in Central Europe. Key meteorological predictors, including time-lagged variables, were identified for each location, and interpretable lasso linear and lasso logistic regression models were developed to forecast spore levels up to seven days in advance. The lasso logistic models achieved high accuracy in threshold exceedance predictions, with F1 scores reaching up to 88.6% for \u003cem\u003eEpicoccum\u003c/em\u003e. While lasso linear models effectively captured seasonal patterns and timing, they tended to underestimate peak concentrations, particularly for \u003cem\u003eAlternaria\u003c/em\u003e, likely due to the sporadic nature of spore release events. Notably, this is the first predictive model developed for \u003cem\u003eEpicoccum\u003c/em\u003e, underscoring the need for clinical validation of allergological thresholds. Regional variability in model performance highlights the importance of local calibration and sustained aerobiological monitoring. These models offer a promising foundation for operational spore forecasting systems, supporting both public health advisories and agricultural decision-making.\u003c/p\u003e","manuscriptTitle":"Predictive modelling of threshold exceedance and airborne concentrations of Alternaria and Epicoccum spores across bioclimatic regions in Central Europe","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-19 08:19:13","doi":"10.21203/rs.3.rs-7210967/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"","date":"2025-08-11T15:17:47+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-08-11T14:59:21+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-07-28T00:43:43+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal of Biometeorology","date":"2025-07-25T02:27:06+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"international-journal-of-biometeorology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ijbm","sideBox":"Learn more about [International Journal of Biometeorology](http://link.springer.com/journal/484)","snPcode":"484","submissionUrl":"https://www.editorialmanager.com/ijbm/default2.aspx","title":"International Journal of Biometeorology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"21c563eb-8a05-4eb9-8bf3-40921f725ccf","owner":[],"postedDate":"August 19th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-01-12T16:02:45+00:00","versionOfRecord":{"articleIdentity":"rs-7210967","link":"https://doi.org/10.1007/s00484-025-03084-2","journal":{"identity":"international-journal-of-biometeorology","isVorOnly":false,"title":"International Journal of Biometeorology"},"publishedOn":"2026-01-07 15:57:59","publishedOnDateReadable":"January 7th, 2026"},"versionCreatedAt":"2025-08-19 08:19:13","video":"","vorDoi":"10.1007/s00484-025-03084-2","vorDoiUrl":"https://doi.org/10.1007/s00484-025-03084-2","workflowStages":[]},"version":"v1","identity":"rs-7210967","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7210967","identity":"rs-7210967","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}