Comparative Analysis Between Sentinel-2 And Proximal Sensors to Study the Spatial Distribution of Chlorophyll Content and Potato Crop Yield Using Artificial Intelligence: A Case Study of Salheia, Egypt

Comparative Analysis Between Sentinel-2 And Proximal Sensors to Study the Spatial Distribution of Chlorophyll Content and Potato Crop Yield Using Artificial Intelligence: A Case Study of Salheia, Egypt | 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 Article Comparative Analysis Between Sentinel-2 And Proximal Sensors to Study the Spatial Distribution of Chlorophyll Content and Potato Crop Yield Using Artificial Intelligence: A Case Study of Salheia, Egypt Abdelraouf M Ali, Abdallah Bardisi, Dalia Ahmed SamiNawaR, Noureldin Laban, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6790082/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 14 You are reading this latest preprint version Abstract Leaf Chlorophyll Concentration (LCC) is a vital biochemical parameter for assessing plant status due to its essential role in physiological activities, photosynthesis, and overall plant health. In order to illustrate the development of potato crops and offer advice for precision agriculture management, research was conducted on non-invasive testing methods for chlorophyll levels and methods for mapping crop yield in potatoes. The objective of this study is to examine the spatial distribution of chlorophyll content and yield of potato crops using Sentinel 2 data, SPAD chlorophyll measurements, and laboratory analyses. Artificial intelligence (AI) using the Random forest (RF) classification method was used to study the spatial distribution of crop type and discriminate the potato crop. The overall accuracy and kappa statistics for the spatial distribution derived from Sentinel 2 satellite imagery for potato crops in the study area were 0.79 and 82.5%, respectively. Stepwise Multilinear regression model (SWMLR) between Spectral vegetation indices (Normalized Difference Vegetation Indexed NDVI, Modified Chlorophyll Absorption Ratio Index (MCARI), Leaf Chlorophyll Index (LCI), derived from spectral vegetation indices (SVI), (SPAD chlorophyll and chemical analysis through potato crop growth stages (S1, S2 and S3) were correlated to estimate chlorophyll content and crop yield map. The model accuracy between vegetation indices and Total chlorophyll showed that models based on VIS and selected spectral bands derived from ASD to predict total chlorophyll(chlt) and SPAD chlorophyll values achieved a high coefficient of determination (R 2 ) at the different growth stages, which were 0.983 and 0.986. The produced map for the potato crop, total chlorophyll derived from Sentinel 2, showed high accuracy at 0.966 and 0.974 based on SPAD, VIS, and selected spectral bands, respectively. The study showed that the estimation and mapping of Chlt and SPAD values of a potato crop under an irrigation system pivot can be done with the help of RS and AI techniques. Biological sciences/Ecology/Agri ecology Biological sciences/Plant sciences/Plant ecology Chlorophyll VIs Sentinel-2 AI RS Potato crop yield Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Figure 8 Figure 9 Figure 10 Figure 11 Figure 12 Figure 13 Figure 14 Figure 15 Figure 16 Figure 17 Figure 18 Figure 19 1. Introduction Potato crop (Solanum tuberosum L.) is one of the most important and widely consumed non-grain foods. Many countries have seen this crop rise to prominence. Due to their significance in the food industry's supply chain.(Ortiz and Mares 2017). Over the past decade, potato production in Egypt has steadily increased due to the expansion of both the farmed area and the yield. Out of Egypt's 27 governorates, 25 are engaged in potato cultivation. In 2019, a total of 171,000 hectares were cultivated, resulting in a yield of 5.2 million tons of potatoes, with an average output of about 30.3 tons per hectare(Food 2020 ).Mapping potato crops using Sentinel-2 imagery has become crucial for improving agricultural monitoring, particularly on large-scale farms(Ashourloo et al. 2020 ). With its multispectral imaging capabilities, Sentinel-2 facilitates accurate and timely crop growth and health observation, making it an essential tool . Their frequent revisit time (every 5 days) allows for consistent and detailed monitoring of crop fields, which is vital for precise crop mapping. According to (Cornelissen et al. 2003 ), Sentinel-2 imagery is commonly used to compute vegetation indices (VIs), including the Normalized Difference Vegetation Index (NDVI) and the Enhanced Vegetation Index (EVI), both of which are closely linked to crop health. These indices are crucial in identifying early growth stages, recognizing stress conditions, crop area estimation, and forecasting yields(Islam et al. 2024 ; Kamenova and Dimitrov 2021; Mukiibi et al. 2024 ). Recent research has shown that Sentinel-2 can effectively map potato cultivation by analyzing these indices to assess chlorophyll content, a key factor affecting photosynthesis and crops' overall health(Islam et al. 2024 ; Mukiibi et al. 2024 ; Zheng et al. 2018). Another significant application of Sentinel-2 imagery is estimating the area covered by potato crops and predicting their yields. Several studies have used machine learning algorithms and Sentinel-2 imagery to predict crop yields(Kaplan et al. 2023 ; Morshed et al. 2025 ; Zheng et al. 2018). These models used data from different spectral bands of Sentinel-2 and spectroradiometry to forecast yields depending on crop features like biomass and chlorophyll contents. A notable study by (Kaplan et al. 2023 ; Morshed et al. 2025 ; Mukiibi et al. 2024 )(Nady, Ali, and Mahmoud 2022 ) demonstrated that combining spectral data from Sentinel-2 with machine learning techniques can estimate yields for potato crops, providing a non-invasive approach for large-scale yield assessments. The biochemical characteristics of plants are crucial in regulating their overall photosynthetic and physiological functions. Among these characteristics, chlorophyll pigments play a significant role in photosynthetic activities, making them the most important biochemical features in leaves(Clevers and Kooistra 2012; Cracknell et al. 2009 ; Gitelson, Keydan, and Merzlyak 2006; Inoue et al. 2016 ). For crops to absorb and store the energy necessary for developing their tissues, leaf chlorophyll content (LCC) is essential for plant growth. LCC is a crucial indicator of plant health, helping to evaluate the rate of photosynthetic energy production and overall plant productivity, and nutrient content.(Clevers and Kooistra 2012)and (Vesali et al. 2017 ). Crops' chlorophyll content is positively correlated with their nitrogen levels, photosynthetic capacity, and developmental stages, This technology is a valuable tool for evaluating crop growth. Traditional methods for estimating chlorophyll, such as spectrophotometry, atomic absorption, and HPLC, are time-consuming and destructive. In contrast, analyzing the spectral properties of crops allows for quick, non-destructive, and large-scale estimation of chlorophyll content. This method has been applied to various crops, including corn, soybeans, bananas, potatoes, and sugarcane, to monitor development stages and yield estimates.(Sinha et al. 2020 ) Conducted a study to identify the most effective vegetation indices for assessing the density of chlorophyll content (CCD). in rice and wheat during various growth stages. Linear regression models used to calculate CCD demonstrated determination coefficients greater than 0.85, providing valuable insights for agricultural production management and monitoring crop dynamics across different growing environments.(Feng, Yamin, and Jianlong 2010). (El-Hendawy et al. 2021 ) Multivariate regression to evaluate spectral reflectivity and determine chlorophyll concentrations in winter wheat. Numerous studies indicate that ratio and normalized difference indices, especially those utilizing red-edge bands, can effectively estimate chlorophyll content, can derive the REP using the red-edge bands from MERIS and the recommended bands from Sentinel-2 and Sentinel-3 using a straightforward linear model to analyze the red-infrared slope(Boschetti et al. 2007 ). To create a model for estimating chlorophyll content using spectral data,(Yang et al. 2022; Yin et al. 2021)(Liu et al. 2022 ) developed vegetation indices and studied the correlations between these indices and chlorophyll levels in plant canopies. This work resulted in the creation of a general model for estimating chlorophyll content. they can estimate the amount of chlorophyll present by analyzing variations in the crop's distinctive features, such as spectral position and area. Studies (Curran, Windham, and Gholz 1995 ; Gilabert, Gandía, and Meliá 1996; Xu et al. 2018 )investigated the relationship between chlorophyll levels in plants and the location of the spectral red edge. The researchers found that as leaf maturity progresses, the amplitude of the red edge increases, the position of the red edge shifts forward consistently, and the area of the red edge expands and then declines while the blue edge area continues to grow. To build a model for estimating chlorophyll content, (Song et al. 2024 )examined the relationship between apple leaf chlorophyll content and hyperspectral reflectance. The Minolta company created a handheld dual wavelength chlorophyll meter, known as the SPAD models 501 and 502. The SPAD-502 measures the transmittance of red (650 nm) and infrared (940 nm) radiation through leaves to determine a relative value indicating chlorophyll content. This portable, non-destructive tool, called the Soil Plant Analysis Development (SPAD) chlorophyll meter, provides a quick and precise method for measuring leaf chlorophyll concentration in various crops(Uddling et al. 2007 ). Plant health status and nitrogen concentrations have been successfully inferred from this device's readings in potato remote sensing (Giletto et al. 2010 ; Ramírez et al. 2014 ). For many years, researchers have studied remote sensing imaging techniques to detect changes in the chlorophyll content of crops. Several vegetation indices (VIs) have been proposed to estimate the chlorophyll levels in the canopy. Significant advancements have been made in the biophysical characterization of vegetation using remote sensing technology. Research shows a strong correlation between satellite sensor data and key biophysical variables, including leaf area index, leaf chlorophyll content, plant cover, and pest presence.(Lago et al. 2011 ; Lizarazo et al. 2023 ; Madugundu et al. 2023 ; Safi et al. 2022 ; Sishodia, Ray, and Singh 2020). The primary objectives of this study are to analyze the spatial distributions of chlorophyll content and potato crop yield utilizing spectral vegetation indices obtained from both a spectroradiometer and Sentinel-2 satellite data. 2. Materials and Methods 2.1. Study site, Climate and Soil Condition The study is in the east-south region of El-Kassaseen City, southwest of Ismailia City. As shown in Fig. 1 , its geographical boundaries are defined by latitudes of 30O 22' 02" and 30O 31' 16" and longitudes of 31O 52' 36" and 32O 06' 26". The project began operations in 1982 and was established in 1981, covering 12,500 hectares. The project employs two irrigation systems: drip irrigation and central pivot irrigation. Drip irrigation is used for orchard trees, while central pivot irrigation is used for field crops. The region generally experiences a desert climate, where precipitation satisfies less than 50% of potential evapotranspiration, according to the Köppen Climate Classification System. The average yearly temperature in the area exceeds 18°C, and it receives an average annual rainfall of only 20 millimeters. January serves as the month with the most rainfall, averaging 6.9 millimeters of precipitation, which can benefit the surrounding ecosystems. The highest month of temperatures is June, with average maximums 41. 8°C.while the lowest month was January ranging between 8.0°C and 17.0°C, resulting in a diverse climate throughout the year. By August, temperatures pleasantly drop to around 21.5°C, contributing to a milder environment. The soil types in the study area are clay loams. Sandy loam is especially beneficial for drainage and is mainly made up of sand particles along with moderate amounts of clay and silt, enhancing its moisture retention capabilities. The soil's pH level in the study area varies from 7.5 to 8.5, indicating it is neutral to slightly alkaline; this pH range can support the growth of specific plants. a higher pH can sometimes lead to challenges with nutrient availability, especially regarding micronutrients,(Amira et al. 2020 ). 2.2. Data This study used three types of data remote sensing data (Sentinel 2 and ASD spectroradiometer), proximal sensors (SPAD chlorophyll), and in situ measurements for winter potato crop. also, crop areas were determined to validate the crop yield map. As shown In Fig. 2 , Sentinel-2 data was used to estimate crop area using a random forest algorism to estimate the spatial distribution of potato crops. A spectroradiometer was used to derive vegetation indices to predict LCC and crop yield models using the stepwise multi-linear regression model SWML. derived vegetation indices from Sentinel 2 were used to validate potato LCC and crop yield. 2.2.1. Remote sensing data 2.2.1.1. Satellite Imagery The Sentinel-2 polar-orbiting satellite is scheduled to launch in 2014 by ESA. the spatial resolution of sentinel are Four bands at 10 m, six bands at 20 m, and three bands at 60 m., spatial resolution are equipped with the Multi-Spectral Instrument (MSI) (Drusch et al. 2012 )., swath width is 290 km is achieved using a 20° The total field of view, with two spectral bands with a spatial resolution of 20 m and a bandwidth of 15 nm, specifically targeting 705 and 740 nm in the red-edge area. Table 1 . Three free-of-cloud Sentinel-2 images were processed and projected in WGS84 UTM zone 36N. Sentinel-2 images covering the period from November 2022 to February 2023 were downloaded concurrently with the same dates of field measurements using the ASD field spectroradiometer and SPAD measurements. Samples were collected for the entire phonological cycle on cloud-free days (Table 1 ). Data from the Sentinel-2 Level 2A satellite were used in this study to produce vegetation indices(VIS), specifically the Normalized Difference Vegetation Index (NDVI), Modified Chlorophyll Absorption Ratio index (MCARI), and Leaf Chlorophyll Index (LCI). These data were geomrtric and atmospheric corrected via the Sen2Cor processor, which correct atmospheric disturbances and converts atmospheric surface reflectivity to reflectance of the surface of the target. All images were selected to correspond to the potato crop growth stages in the study area and at the specified dates, and these data were uniformly processed to maintain data quality throughout the analysis and modeling phases. Table 1 Sentinel-2 satellite date acquisition during study season. Fieldwork Date Season Sentinel-2 Image Code November 2022–2023 S2B_MSIL1C_20221119T083139_N0400_R021_T36RUU_20221119T091634 December S2A_MSIL1C_20221214T083341_N0509_R021_T36RUU_20221214T092251 January S2B_MSIL1C_20230108T083229_N0509_R021_T36RUU_20230108T090814 2.2.2. Field Radiometry Measurements Figure 3 shows the grid samples designed to collect the spectral data for chlorophyll measurements using SPAD and leaf samples for laboratory measurements and crop yield data. spectral measurements and plant samples were collected through three potato crop stages (S1) (vegetation and tuber formation, (Stage 2)tuber expansion stage after flowers fell, and (Stage 3) tuber maturation stage during leaves turning yellow, as described in Table 2 . Table 2 Field measurements and spectral data acquisition during potato crop growth stages. Potato Growth stage Characteristics of the crop acquisition date Stage 1 Vegetation and tuber formation stage November 19 Stage 2 Tuber expansion stage after the flowers fall December14 Stage 3 Tuber maturation stage during leaves turning yellow January 8 The ASD 4 FieldSpec spectroradiometer, manufactured by ASD Analytical Spectral Devices, was used to assess the leaf reflectance from chosen potato crops. Data collection was conducted on sunny days from 10:00 a.m. to 2:00 p.m. to reduce the impact of atmospheric fluctuations and changes in solar angle. The spectroradiometer captured reflectance data across the entire optical spectrum, including the visible (VIS), near-infrared (NIR), and short-wave infrared (SWIR) regions, covering wavelengths from 350 nm to 2500 nm, with an output resolution of 1 nm increments. The device spectral resolution with a sampling interval of 1.4 nm for the 350–1050 nm range and 2 nm for the 1000–2500 nm range. It includes automatic interpolation to provide a consistent 1 nm spectral resolution throughout the full spectrum. Spectral data were collected by measuring the spectrometer’s irradiance on a calibration panel. A contact probe, linked through a fiber optic cable, was employed to ensure consistent ambient conditions during the reflectance measurements. Using the View Spec 3 software, the spectral reflectance curves were examined, and the average spectrum of each stage was used to study the dynamic variations between the various stages. The reflectance of each level is displayed in Fig. 4 . Both the visible region (400–680 nm) and the near-infrared region (700–1150 nm) showed comparable patterns. Due to the pigment's significant absorption, the minimum reflectance in the visible spectrum appeared between 400 and 680 nm. Since the reflectance surface is located in the mesophyll's spongy structure, the reflectance increased from 700 to 960 nm in the near-infrared range. While there was a considerable reflection between 960 and 1300 nm, the absorption of leaf water content caused a weak reflectance valley to form between 1400 and 2500 nm. A SPAD-502 meter was used to measure the identical potato leaves for every sample at the same times and dates of the ASD measurements. SPAD-502 meters The Soil Plant Analysis Development chlorophyll meter (SPAD), a portable non-imaging tool, offers a quick, precise, and non-destructive method of measuring the LCC for various crops. This device's readings have been effectively applied to potato remote sensing as an indication of nitrogen concentrations and plant health status (Giletto et al. 2010 ). 2.2.2.1. Vegetation indices Based on the acquisition date shown in Table 2 , three vegetation indices (VIs) were derived for every Sentinel-2 image by spectral analysis. The indices were created using software called SNAP 9.0. The VIs studied in this letter and their definitions are provided in Table 3 . The NDVI, MCARI, and LCI were mainly used as LCC estimators for estimating LCC. The same vegetation indices were calculated from ASD spectra data, as shown in Table 3 . Bands centered at 490 nm, 560 nm, 665 nm, 705 nm, 740 nm, and 783 nm were used for this study. The investigated vegetation indices were calculated using 842 nm, 865 nm, 1610 nm, and 2190 nm wavelength. Table 3 Derived vegetation indices from ASD spectroradiometer Abbreviation Name Formula from ASD Formula from Sentenil-2 Images Reference NDVI Normalized Difference Vegetation Index (R800 - R670) / (R800 + R670) \(\:\frac{\text{B}8-\text{B}4}{\text{B}8+\text{B}4}\) (Devaux et al. 2021 ) MCARI Modified Chlorophyll Absorption Ratio Index (R701 - R670) − 0.2 * (R701 - R550)) * (R701/R670) \(\:\left[(\text{B}5\:-\:\text{B}4)\:-\:0.2\:\text{*}\:(\text{B}5\:-\:\text{B}3)\right]\text{*}\:(\text{B}5\:/\:\text{B}4)\) (Herrmann et al. 2010 ) LCI Leaf Chlorophyll Index (R850 – R710) / (R850 + R680) \(\:\frac{\text{B}8-\text{B}5}{\text{B}8+\text{B}4}\) (Pu, Gong, and Yu 2008) 2.2.3. Potato Leaves Samples leave samples of the potato crop were taken from pivot11-s. The ENVI software version 5.3's was used to plan the pre-planning of the sample field survey that was gathered. The Fig. 3 shows that the spatial distribution based on a prescription map created using soil categorization variability, A number of samples were taken from this axis: 23 samples with two replications for each point, for a total of 69 samples, which were divided into 50 samples for applying the model and 19 samples for validation. The same samples were taken at each of the three growth stages. GPS receivers made the precise location inside the field. To determine total chlorophyll, these leaf samples were gathered from various locations. Every sample plant canopy had three randomly selected leaves, which were then placed in a freshness protection bag, numbered, and kept in a transportable thermal insulation box. Next, using conventional chemical techniques in the lab, the chlorophyll concentration was ascertained (Sumanta et al. 2014 )The amounts of carotenoid and chlorophyll were measured using spectrophotometry in accordance with (Lichtenthaler 1987 )Following filtration, the absorbance of 0.2 g of fresh plant leaf tissue was measured using a Jenway 6800 UV/Vis Spectrophotometer at 663.2, 646.8, and 470 nm in comparison to a blank sample of acetone 80%. The concentration of chlorophyll (Chl) was calculated using the following formulas: Chla = 12.25A 663.2–2.79 A 646.8 (1) Chlb = 21.50 A 646.8–5.1A 663.2 (2 ) The absorbances at 646.8 nanometers and 663.2 nanometers are marked as A646.8 and A663.2. Chla refers to the concentration of chlorophyll-a, and Chlb refers to the concentration of chlorophyll-b. Chlt is the total chlorophyll concentration, reported in micrograms per gram. Fw is used in the study. 2.2.4. in-situ potato yield collection sampling strategy In this study, a centrally irrigated pivot field (11-S) was used as a field sample. Potato (tuber) yield data were collected at Site using stratified random sampling based on the year 2023 for the study season, with three replicates per point location (50 points were used for the generated model and 19 points for validation). A GPS receiver (Trimble GeoXH) was used to locate sample locations in the field and distributed throughout each experimental field using the randomization feature of the ENVI software (version 5.3) according to a recipe map generated based on vegetation variability. A simple random sample was then selected from each subset. At each sampling site, potatoes were harvested over an area of ​​1 m² to obtain the actual crop yield at the site. Weighting and upscaling to the common yield unit (tons ha-1) were performed on the harvested potatoes. Actual yield and remote sensing-generated variation indices (NDVI, SAVI, CNDVI, CSAVI, and LCI) were plotted against each other during the growing period to demonstrate the correlation between the two and produce an empirical equation for predicting potato yield. Pearson's correlation coefficient (linear) was used. To estimate crop yield, 50 samples were used to build the model between the dissimilarity indices (CNDVI and CSAVI) and the single-date dissimilarity indices (NDVI, SAVI, and LCI). The most suitable dissimilarity indices for prediction were determined by analyzing the growth-gradient correlation coefficients to obtain the best-fit empirical equations. The optimal growth stage, at which the dissimilarity indices were most closely related to yield, was evaluated to determine the appropriate timing for predicting potato yield before harvest. 2.2.4. Image classification using AI The use of remote sensing techniques, GIS, and artificial intelligence to obtain information on crop distribution and cultivated areas is important for making optimal agricultural planning and management decisions. Satellite data is used as a data source, based on machine learning methodology, as a tool for static and dynamic crop classification. In this study, the Google Earth Engine (GEE) platform was used for AI image classification based on remote sensing images and vegetation indices. GEE provided by Google, which is a geospatial analysis platform that works based on electronic cloud and can perform geospatial analysis on a global scale. Summer crop classification were done by the Random Forest (RF) method (Indices et al. 2021 ; Orynbaikyzy, Gessner, and Conrad 2022), which is a machine learning (ML) method. 2.2.4.1.Validation of image classification and accuracy assessment Field observations were carried out in the studied area to collect ground control points that were used to discriminate summer crops. 160 Sampleas were collected To determine the accuracy of image classification at a pixel level, it was necessary to distribute ground truth data at various locations and different crops throughout the study region. This was carried out through field trip observations that were carried out during the crop-growing season for summer crops 2023. The efficacy of RF is often evaluated by Overall Accuracy (OA) and the Kappa Coefficient according to (Belgiu and Drăgu 2016) $$\:\varvec{K}=\frac{\varvec{N}\sum\:_{\varvec{i}-1}^{\varvec{r}}{\varvec{x}}_{\varvec{i}\varvec{i}}-\sum\:_{\varvec{i}-1}^{\varvec{r}}\left({\varvec{x}}_{\varvec{i}+.}{\varvec{x}}_{+\varvec{i}}\right)}{{\varvec{N}}^{2}-\sum\:_{\varvec{i}-1}^{\varvec{r}}\left({\varvec{x}}_{\varvec{i}+}.{\varvec{x}}_{+\varvec{i}}\right)}$$ 3 K represents the Kappa coefficient, r denotes the total number of rows in a matrix, xii indicates the count of observations in row i and column i, while xi + and x + i signify the marginal totals for row i and column i, respectively, and N refers to the overall number of observations. The percentage of all reference pixels that are accurately classified (i.e., where the class assignment for the classification and the reference classification agree) is known as overall accuracy. The calculation involves dividing the entire number of reference pixels by the total number of correctly categorized pixels, which is the sum of the elements along the main diagonal (5). 2.2.5. Regression analysis models One method for analyzing the relationship between variables is through regression analysis. This research utilized spectral reflectance data from several bands (490 nm, 560 nm, 665 nm, 705 nm, 740 nm, 783 nm, 842 nm, 865 nm, 1610 nm, and 2190 nm) collected from ASD, along with calculated vegetation indices shown in Table 4 , as independent variables. The chlorophyll concentration at the corresponding locations was used as the dependent variable, and multiple regression models were applied to assess the data. The coefficient of determination (R2) between the mean spectral bands, vegetation indices, and Chlt concentration parameters was then calculated based on the estimated associations. In addition, the RMSE was used to assess the developed regression model. The optimal model was selected for the Chlt concentration estimation because it had the highest R2 and the lowest RMSE value (which is calculated as the difference between the field values observed and the projected values). The optimal model between actual chlorophyll concentration (µg/g. fw) and selected bands separately, as well as between chlorophyll concentration (µg/g. fw) and vegetation indices separately, was created using the stepwise multiple linear regression approach. as well as SPAD chlorophyll values was estimated, the stepwise method was calculated using the following formulas: Where Y is the actual chlorophyll concentration (µg/g. fw) and predicted yield, and are vegetation indices or selected bands, a is the intercept and and are the regression coefficients. 3. Results 3.1. Statistical analysis of Chemical Chlorophyll Concentration The concentrations of chlorophyll were measured from stages S1 to S3. To assess potato growth dynamics, the average chlorophyll values at each stage were calculated. The results are presented in Fig. 5 . The maximum chlorophyll concentration was recorded at S1, with a value of 627.2 (µg/g fw). This decreased to 523.2 (µg/g fw) at S2 and further declined to the lowest value of 495.8 (µg/g fw) at S3, indicating a gradual reduction in chlorophyll concentration. 3.2. Statistics of SPAD Chlorophyll Values of Modeling Data The SPAD chlorophyll values from stages S1 to S3 were measured, showing a consistent pattern in the chemical composition of chlorophyll across the three growth phases. To assess potato growth dynamics, the average chlorophyll values at each stage were calculated. These results are illustrated in Fig. 6 . Chlorophyll readings declined progressively, starting from a maximum value of 55 at S1, decreasing to 48 at S2, and finally reaching 43 at S3. 3.3. Multitemporal Analysis of the vegetation Indices for winter season for potato crop Generally, the average spectral vegetative display values rise with crop development and never fall below the value of 0.8, indicating that the vegetation is not saturated. Figures 7 , 8, and 9 illustrate the geographical spread that occurs in vegetative indices. The uncultivated portion, which is shown diagonally in the field's middle, is recognized by all markers. In contrast to the MCARI index, which displays values between 0.03 and 0.19 and understates the presence of vegetation, the NDVI and LCI indices display values that are consistent with the predominate vegetation. Visualizing the variability in crop yields is also made possible by the NDVI's spatial distribution. The data series obtained following the sprouting, growth, and maturity periods exhibited varying degrees of association with vegetative indicators when analyzed temporally. Based on the vegetative development progress, the NDVI value calculated from sentinel-2 images through the potato growing stages revealed that the first and fourth stages had the lowest values, 0.27 and 0.64, respectively, while the second and third stages had the highest values, 0.78 and 0.68, respectively. The other vegetation MCARI and LCI indices followed the NDVI trend. 3.4. Regression models Analysis 3.4.1. Multiple Linear regression models between SVIs and chemical total chlorophyll Multiple regression models were employed to establish the relationship between three spectral vegetation indices (SVIs) derived from spectroradiometer (ASD) reflectance data, which served as independent variables, and the chemical total chlorophyll (Chlt) concentration (µg/gm. fw) at the same point, which served as the dependent variable, as shown in Table 4 . The results indicated that the model using all three VIS-NDVI, LCI, and MCARI at the third growth stage achieved the highest R² value of 0.983. The next best model, which included two VIS (LCI and NDVI) at the second stage, obtained an R² value of 0.978. The model with the lowest R², which was 0.92, was at the first stage and used two VIS (LCI and MCARI). Table 4 Multiple Linear regression models between SVIs and chemical total chlorophyll (Chlt) concentration (µg/gm. fw) for winter potato crop Growth Stage Model R2 RMSE S1 (19-11-2022) Y = 52.9 + 814*LCI + 423*MCARI 0.92 12.7 S2 (14-12-2022) Y = -1818 + 1764*LCI + 1608*NDVI 0.978 9.57 S3 (8-1-2023) Y = -1052.3 + 1542.3*NDVI + 406*LCI + 127.8*MCARI 0.983 6.2 3.4.2. Multiple Linear regression models between SVIs and SPAD chlorophyll values Various multiple regression models were employed to establish the connection between three vegetation indices, VIS obtained from a spectroradiometer device. (ASD) reflectance data as the independent variable and SPAD chlorophyll values for the same point as the dependent variable as showed in Table 5 , to find the best model to predict by Chlt depending on the high coefficient of determination (R2). the result showed that the model which one (LCI) VIS at the 2nd growth stage had a highest R2 = 0.966, the next model had a high R2 = 0.934 was at 3rd stage which used the same VIS (LCI) and the lowest model had R2 = 0.928 was at the 1st stage which used two VIS (LCI and MCARI). Table 5 Multiple Linear regression models between the SVIs and SPAD chlorophyll values for winter potato crop (2022–2023) Growth Stage Model R2 RMSE S1 (19-11-2022) Y = 7.483 + 60.645*LCI + 25.716*MCARI 0.928 0.826 S2 (14-12-2022) Y = − 39.77 + 156.566*LCI 0.966 0.619 S3 (8-1-2023) Y = 11.178 + 68.445*LCI 0.934 0.643 3.4.3. Multiple Linear regression models between selected spectral bands and chemical total chlorophyll Multiple regression models were used to define the relationship between selected spectral bands derived from spectroradimeter device (ASD) reflectance data as the independent variable these bands were selected depending on the same bands which related with vegetation in sentenil-2 bands as shown in Table 1 and the chemical total chlorophyll (Chlt) concentration (µg/gm. fw) For the same point being used as the dependent variable as shown in Table 6 , to find the best model to predict by Chlt depending on the high coefficient of determination (R2).the result showed that the model which used two bands ( B4 and B8 ) at the 2nd growth stage had a highest R2 = 0.986, the next model had a high R2 = 0.984 was at 3rd stage which used two bands (B6 and B8A) and the lowest model had R2 = 0.89 was at the 1st stage which used one band for correlation(B4). Table 6 Multiple Linear regression models between selected spectral bands and chemical total chlorophyll (Chlt) concentration (µg/gm. fw) for winter potato crop (2022–2023) pivot 11-s Growth Stage Model R2 RMSE S1 (19-11-2022) Y = 461.46 + 3454.5*B4 0.89 14.42 S2 (14-12-2022) Y = -1423.8 + 4520.5*B4 + 2759.4*B8 0.986 7.53 S3 (8-1-2023) Y = -1073 + 1659.9*B6 + 1015*B8A 0.984 5.77 3.4.4. Multiple Linear regression models between selected spectral bands and SPAD chlorophyll values Multiple regression models were used to define the relationship between selected spectral bands derived from spectroradimeter device (ASD) reflectance data as the independent variable these bands were selected depending on the same bands which related with vegetation in sentenil-2 bands as shown in Table 1 and the SPAD chlorophyll values for the same point as the dependent variable as shown in Table 7 , to find the best model to predict by Chlt depending on the high coefficient of determination (R2).the result showed that the model which used two bands ( B8 and B11 ) at the 2nd growth stage had a highest R2 = 0.974, the next model had a high R2 = 0.96 was at 3rd stage which used three bands (B3, B5 and B7) and the lowest model had R2 = 0.884 was at the 1st stage which used one band for correlation(B4). Table 7 Multiple Linear regression models between selected spectral bands and SPAD chlorophyll values for winter potato crop (2022–2023) pivot 11-s Growth Stage Model R2 RMSE S1 (19-11-2022) Y = 37.957 + 232.405*B4 0.884 1.05 S2 (14-12-2022) Y = -71.66 + 137.54*B8 + 107.23*B11 0.974 0.542 S3 (8-1-2023) Y = − 41.9 + 317.17*B3–194.8*B5 + 142.4*B7 0.96 0.52 3.5. spatial distribution of potato crop in the study area crop types are identified and distinguished within agricultural fields through crop discrimination byusing random forest classification methods. The underlying assumption of this claim stems from the finding that each crop has a unique spectrum signature. Compared to the summer, it is noted that a large percentage of the lands covered by center pivot irrigation systems are under cultivation throughout the winter. The reason for this discrepancy is that there is more water available in the winter. As shown in Fig. 10 , a classification study during the winter season (2022–2023) revealed that spatial distribustion of several winter crops were grown in addition to horticultural crops: potatoes, wheat, sugar beet, and onions., we were able to extract the potato crop patches depicted in Fig. 11 using Arc GIs software. The evaluation of crop classification accuracy for the winter season of 2022–2023 employed remotely sensed data, particularly Sentinel-2 imagery. The findings displayed in Table 8 feature a confusion matrix that details the ground truth values for various crop types: Fallow Land, Grape, Onion, Palm Trees, Sugar Beet, Summer Potato, Winter Potato, and Wheat. Table 9 showed the user and producer accuracy for each crop. User accuracy indicates how well the classification model identified each category, while producer accuracy demonstrates the effectiveness of the model in capturing the true crop distribution. while Table 10 , the Kappa coefficient is presented, reflecting the level of agreement between the classification results and the ground truth data, with a reported value of 0.79, indicating strong concordance. The overall accuracy rate of the classification stands at 82.5%, which positively reflects the model's performance. These results are vital for precision agriculture, as they empower farmers to make informed decisions based on the dependability of crop classification outcomes. In the end, this fosters enhanced resource management and more precise crop yield forecasts. Table 8 confusion matrix of crop classification for winter season 2022–2023 Class Citrus Fallow Land Grape Onion Palm trees Sugar beet Summer Potato Winter Potato Wheat Total User Citrus 20 0 0 0 2 0 0 0 0 22 Fallow Land 0 23 0 0 0 0 4 0 0 27 Grape 0 0 2 0 0 0 0 0 0 2 Onion 0 0 0 9 0 2 0 0 1 12 Palm trees 0 0 0 0 1 0 0 0 0 1 Sugar beet 0 0 0 2 0 27 0 5 0 34 Summer Potato 0 2 0 0 0 5 0 0 7 Winter Potato 0 0 0 4 0 3 0 33 0 40 Wheat 0 0 0 3 0 0 0 0 12 15 Total Producer 20 25 2 18 3 32 9 38 13 160 Table 9 User accuracy and Producer accuracy ground check point for winter season 2022–2023 Class User Accuracy % Producer Accuracy % Citrus 90.9 100 Fallow Land 85.185 92 Grape 100 100 Onion 75 50 Palm trees 100 33.33 Sugar beet 79.41 84.37 Summer Potato 71.42 55.55 Winter Potato 82.5 86.84 Wheat 80 92.3 Table 10 Kappa Coefficient and Overall Accuracy ground check point for winter season 2022–2023 Kappa Coefficient 0.79 Overall Accuracy (%) 82.5% 3.6. Mapping and visualization 3.6.1. Chemical total chlorophyll (Chlt) concentration (µg/gm. fw) for winter potato crop pivots in 6th of October Company (2022–2023) based on band combinations Various band combinations were evaluated to produce a regression equation along with their corresponding R² values to ascertain the relationship that most accurately estimates the spatial variability of Chlt concentration across the 6th of October Company, as shown in Table 6 . The band combination represented by the equation (Y = -1423.8 + 4520.5*B4 + 2759.4*B8) achieved the highest R² value, which is highlighted in bold in the table. Figure 12 shows the spatial variations of Chlt concentration over the 6th of October Company, which were mapped using the emphasized regression equation. The major reason for selecting this model was its impressive coefficient of determination of 0.986. 3.6.2. Total Chemical chlorophyll (TChl) concentration (µg/gm. fw) for winter potato crop pivots in 6th of October Company (2022–2023) based on VIS Various VIS combinations were evaluated to develop a regression equation along with their respective R2 values to identify the relationship that most accurately represents the spatial variability of Chlt concentration across the 6th of October Company, as shown in Table 4 . The band combination (Y = -1052.3 + 1542.3*NDVI + 406*LCI + 127.8*MCARI) resulted in the highest R2 value, emphasized in bold in the table. Figure 13 showed the spatial variations of Chlt concentration in the 6th of October Company, which were mapped using the regression equation. The primary reason for selecting this model was its superior coefficient of determination, which was 0.983. 3.6.3. SPAD chlorophyll Values for winter potato crop pivots in 6th of October Company (2022–2023) based on band combinations Various band combinations were examined to develop a regression equation along with their corresponding R² values to determine the best relationship for estimating the spatial variability of SPAD chlorophyll values over the 6th of October Company, as shown in Table 7 . The band combination (Y = -71.66 + 137.54*B8 + 107.23*B11) produced the highest R² value, Fig. 14 showed the spatial variation of SPAD chlorophyll values over the 6th of October project, which were mapped using the emphasized regression equation. The primary reason for selecting this model was its exceptional coefficient of determination of 0.974. 3.6.4. SPAD chlorophyll Values for winter potato crop pivots in 6th of October Company (2022–2023) based on VIS Various visual information systems (VIS) were analyzed to create a regression equation along with their corresponding R² values to determine the relationship that best estimates the spatial variability of SPAD chlorophyll values over the 6th of October Company, as shown in Table 5 . The band combination represented by the equation (Y = -39.77 + 166.566*LCI) yielded the highest R² value,. Figure 15 shows the spatial distribution of SPAD chlorophyll values across the 6th of October Company, which was mapped using the emphasized regression equation. The primary reason for selecting this model was its superior coefficient of determination, which stood at 0.966. 3.7. Model Calibration 3.7.1. Calibration for chemical total chlorophyll (Chlt) concentration Datasets utilized for model validation included chemical total chlorophyll (Chlt) concentration measured in field (µg/gm. fw) versus predicted (Chlt). Root mean square error (RMSE) is a statistical index was used to assess the model’s correctness in Fig. 16 . Results show that these models were successfully validated using the correlation coefficient between actual and predicted map of chemical total chlorophyll (Chlt) concentration (µg/gm. fw). R2 was 0.82 and RMSE was 43.62 for the best model derived from VIS indices shown in Table 4 (Y = -1052.3 + 1542.3*NDVI + 406*LCI + 127.8*MCARI).while R2 was 0.645 and RMSE was 58.26 for the best model derived from selected bands shown in Table 6 (Y = -1423.8 + 4520.5*B4 + 2759.4*B8). 3.7.2. Calibration for predicted chl using SPAD chlorophyll values Datasets utilized for model validation included SPAD chlorophyll values measured in field versus predicted (SPAD chlorophyll values). Root mean square error (RMSE) is a statistical index was used to assess the model’s correctness in Fig. 17A and B. The findings indicate that these models were effectively confirmed through the use of a simple regression model, and that this validation produced precise insights regarding the relationships between the SPAD chlorophyll values recorded in the field and the predicted Map (SPAD chlorophyll values).R2 was 0.689 and RMSE was 4.92 for the best model derived from VIS indices shown in Table 5 (Y = − 39.77 + 166.566*LCI). while R2 was 0.723 and RMSE was 2.26 for the best model derived from selected bands shown in Table 7 (Y = -71.66 + 137.54*B8 + 107.23*B11). 3.8. Multiple Linear regression models between selected SVIs and chemical total chlorophyll to estimate potato crop yield Multiple regression models was used to define the relationship between selected SVIs derived from spectroradimeter device (ASD) reflectance data as the independent variable these bands were selected depending on the same bands which related with vegetation in sentenil-2 bands as shown in Table 11 and the chemical total chlorophyll (Chlt) concentration (µg/gm. fw) for the same point as the dependent variable as shown in Table 6 , to find the best model to predict crop yield depending on the high coefficient of determination (R2).the result showed that the model which used CNDVI, CSAVI and total chlorophyl that was predicted model in section at the 2nd growth stage had a highest R2 = 0.847. Table 11 Multiple Linear regression model between thevegetation indices, predicted total chlorophyll and actual productivity for second season (2022–2023) Growth Stage Model R2 RMSE Mature stage Y = -10.12 + 10.54*CNDVI + 6.4*CSAVI − 0.205*Pre TChl 0.879 2.77 3.8.2. Crop yield map According to the crop yield model that was driven to estimate crop yield and the crop map spatial distribution of crop yield map was derived as showed in Fig. 18. This map was used to study the spatial variability of crop yield for each pixel. Figure 18 showed the expected distribution of potato crop yields based on data from Sentinel-2 satellite images. It uses a color scale to indicate different yield levels across the field green and blue represent highst yields, whereas cooler shades such as red and orange indicate lower yields. The forecasted yield varies from 13.4 tons per hectare to 104.8 tons per hectare across a 5 km area as showed in Fig. 18. Such crop yield maps provide essential insights for recognizing yield variability at a detailed, pixel-level scale. a method that utilizes data and remote sensing technology to enhance farming efficiency and sustainability. Precision agriculture focuses on managing the differences within a field to maximize crop yield and reducing resource consumption. The crop yield distribution as showed in the map allows farmers and agronomists to study the variability of crop yield in the whole study area of both high and low productivity. 3.8.3. Validation of crop yield map The datasets used for validating the model included both the actual yield and the predicted map. The root mean square error (RMSE) serves as a statistical metric to evaluate the accuracy of the model as illustrated in Fig. 19. The results indicate that the models were effectively validated through the relationship between actual and predicted values (R2), leading to accurate assessments of the correlations between the field-measured actual crop yield and the predicted map (predicted crop yield). The highest R2 value achieved was 0.821, with an RMSE of 4.64. 4. Discussion The levels of Chlt often vary and fluctuate based on weather and climate conditions. During the winter months, the ample sunlight leads to an elevated Chlt value, as depicted in Fig. 4 . at the first stage of the growing season (19-11-2022), in addition to this stage have a strong and speed in the plant vigor versus the second stage and third stage (14-12-2022),(8-1-2023) There is reduced sunlight, leading to decreased photosynthesis and ultimately less Chlt.and maturing of plants increases catabolic processes in plants which reduces Chlt. SPAD chlorophyll values took the same trend of chemical chlorophyll at the three stages as shown in Fig. 5 for the same reasons. This suggests that Chl-a is directly influenced by growth state and sunshine (Wagle et al. 2019 ). The majority of research investigations (Wang, Chen, and Li 2004 ; Yadava 2022 ; Yamamoto et al. 2002)The relationship between [chl] and SPAD values is measured using linear regression. This work shows that foliar chlorophyll may be successfully recovered from high spatial resolution Sentinel-2 pictures. Retrieving leaf biochemical characteristics from canopy spectral reflectance is difficult because, in general, signal diffusion from the leaf to the canopy is low (Asner 1998 )and (Daughtry et al. 2000 ). Tables 5 , 6 demonstrate that foliar chlorophyll was estimated with reasonable accuracy (R2 = 0.983) using best fit spectra from ASD data and SPAD data (R2 = 0.966). The same trend was shown in Tables 7 and 8 to the relation between selected spectral bands from ASD and values of chlt and SPAD meter, where the highest R2) 0.986 and 0.974. We used the models with highest R2 ) which were extracted from data acquired from pivot 11-s at the winter season (2022–2023) for potato crop as a case study to map and generalize it all over the 6th of October company for all other pivots in the same season which cultivated with the potato crop. According to (Psomiadis et al. 2017 ), Their mathematical model revealed the most robust and linear relationships with the canopy concentration per unit area of carotenoids, chlorophyll a, and chlorophyll b. The significance of the red-edge bands of the MSI sensor on Sentinel-2 for assessing chlorophyll levels in potato crops is clarified. MSI spectral bands recovering the canopy chlorophyll content are promising for thesa, which have a width of 15 nm and are centered at 705 nm and 740 nm. Due to its short revisit period (Theapproximately weekly) and high spatial resolution (20 m) provided by a pair of identical satellites, it can be utilized for more precise agriculture and various other applications (Clevers and Kooistra 2013 ). According to a previous study one of the most effective indices for evaluating canopy chlorophyll or nitrogen content is the CI red edge. The specific location of the spectral bands within the CI red edge is not particularly This was further explained in this study by analyzing which spectral bands should be utilized in the CI red edge to achieve the lowest coefficient of variation (CV) when estimating chlorophyll levels in potato crop canopies across three different growth seasons. The optimal results were obtained using a spectral band in the range of 695 nm to 725 nm in the denominator and a spectral band in the numerator of the CI red edge. Throughout the growth season, VIS achieved an impressive accuracy with R² = 0.983; these findings are comparable to those of (Aklilu Tesfaye and Gessesse Awoke 2021). Our study's chlt and SPAD chlorophyll value prediction models performed well when validated using root mean square error (RMSE). The simple regression between actual and predicted chlt was used to validate the developed models. The accuracy of the predicted SPAD chlorophyll values was determined by comparing them with measured ones for potato crop samples, using the same validation approach. Ultimately, the results demonstrated that the models developed utilizing hyperspectral data from ASD and SPAD chlorophyll meters can be effectively used to map chlorophyll using Sentinel-2 data across a wide area, as illustrated in Figs. 12 , 13, 14, and 15. These findings are consistent with Estimates of the chlorophyll content from hyperspectral reflectance correlated with the distribution of chlorophyll content in regions with varying applications of nitrogen fertilizer. According to (Lin et al. 2023 ). this result implies that the suggested technique, which is Utilizing comprehensive index parameters, it provides high accuracy and can track the nutritional status of potatoes in real time. The table shows the model used to predict potato crop yield using multiple linear regression (MLR) for the 2022–2023 growing season. The MLR model for the mature stage of the crop, incorporating CNDVI (Cumulative NDVI), CSAVI (Cumulative Soil Adjusted Vegetation Index), and Pre TChl (predicted total chlorophyll), achieved a high R² value of 0.847 and a root mean square error (RMSE) of 3.93 (Table 2 ). According to (Li et al. 2021 ; Salvador et al. 2020 ), the effectiveness of this model indicates that these vegetation indices, combined with pre-season estimates of chlorophyll, are valuable for assessing the crop's physiological status and predicting its productivity at maturity. In areas where soil interference can affect simpler vegetation indices like NDVI, the addition of CNDVI and CSAVI helps mitigate soil background effects, thereby enhancing the model's predictive capability (Ali et al. 2021 )(Vélez, Martínez-Peña, and Castrillo 2023; Van Wart et al. 2013; Xue and Su 2017). Conversely, the SLR model demonstrated a lower RMSE of 4.64 and an even higher R² value of 0.821, relying solely on actual and expected productivity Fig. 19 This study emphasizes the ease of use and effectiveness of establishing a direct relationship between expected and actual yield, which can yield accurate estimates during the mature development stage (Desloires 2024 ; Pham et al. 2022 ). The higher R² value suggests that this model can effectively describe the relationship between expected productivity and actual production, potentially offering a simpler and more efficient method for operational yield prediction. Spatial distribution of potato crop yield throughout the growing season can be observed from the CNDVI, CSAVI, and Predicted TChl value. The spatial distribution map (Fig. 17) illustrates the management zones where vegetation indices accurately predict yield, providing essential information for site-specific management and decision-making. The correlation between higher anticipated yields and areas with elevated CNDVI and CSAVI values showed the effectiveness of these indices in representing crop health and productivity across the field (Espe et al. 2016 ). Additionally, the geographical output aligns with previous research indicating that remote sensing indices derived from high-resolution data, such as Sentinel-2, can generate precise and reliable yield projections by capturing crop variability at the field scale (Petersen 2018 ). We note that when building the model on the training data, the R² value was 0.986, indicating minimal variation between the studied fields. However, during model building, the model's performance declined significantly, with R² = 0.645. This is likely due to heterogeneity in the climatic conditions surrounding the study area or differences in soil composition and physical and chemical properties that were not observed in the training data. Therefore, greater diversity in sampling, environmental conditions, and soil conditions should be considered in subsequent studies, which may further explain the significant drop in regression coefficient values ​​between the value inferred from the model building data and the data used to evaluate the validity of the results. 5. Conclusions This study determined the total chlorophyll content and crop yield of the potato crop using spectral reflectance. Vegetation indices were used to develop a model for estimating chlorophyll content at various growth phases and for mapping crop yield. It was found that the most accurate estimates of potato chlorophyll content and SPAD values were achieved with models based on the VIS and specific spectral bands. By utilizing hyperspectral data and Sentinel-2 images through a regression model, remote sensing (RS) and Geographic Information Systems (GIS) approaches were applied to estimate and map the chlorophyll concentration and SPAD chlorophyll values for the potato crop pivots of the 6th of October Company during the 2022–2023 season. To evaluate the model's effectiveness, in-situ measurements of a specific fixed point were conducted, employing multiple regression analysis to develop the best-fit regression models, which yielded reliable and accurate results. The R-squared (R2) and root mean squared error (RMSE) were utilized to assess the analytical models' accuracy. This investigation concludes the effectiveness of various imaging technologies in establishing an affordable routine for monitoring children's health and potato crop yield. Different organizations may consider utilizing routine remote sensing observation of potato crop concentration as an alternative to field surveys for documenting and analyzing potato crop status. Declarations Author Contributions: . Conceptualization, Adel Ibraheim Selim ., Dalia Ahmed SamiNawar, Abdel-Aziz Belal and A. Ali; Data curation, Adel Ibraheim Selim . and D. Kucher, ; Formal analysis, Adel Ibraheim Selim . and Noureldin Laban; Funding acquisition, D. Kucher, ; Investigation, Abdallah Bardisi, Abdel-Aziz Belal and A. Ali; Methodology, Abdallah Bardisi, Dalia Ahmed SamiNawar and A. Ali; Project administration, A. Ali; Software, Adel Ibraheim Selim, Abdel-Aziz Belal and Noureldin Laban; Supervision, Abdallah Bardisi, Dalia Ahmed SamiNawar and A. Ali; Validation, Noureldin Laban, D. Kucher, and A. Ali; Visualization,Abdel-Aziz Belal , Adel Ibraheim Selim .; Writing – original draft, Y Rebouh, and A. Ali; Writing – review & editing,Abdel-Aziz Belal, Abdallah Bardisi, Y Rebouh, and A. Ali.All authors have read and agreed to the published version of the manuscript. Data availability The data presented in this study are available upon request from the corresponding author. Funding : This research received no external funding. Institutional Review Board Statement: Not applicable. Informed Consent Statement: Not applicable. Acknowledgments: The authors would like to thank the National Authority of Remote Sensing and Space Science (NARSS), Cairo, Egypt, for supervising this work and for sample analysis. This research also This publication has been supported by the RUDN University Scientific Projects Grant System, project № .. The authors would like to extend their sincere appreciation to the faculty of Agriculture, at Zagazig university. References Aklilu Tesfaye, Andualem, and Berhan Gessesse Awoke. 2021. “Evaluation of the Saturation Property of Vegetation Indices Derived from Sentinel-2 in Mixed Crop-Forest Ecosystem.” Spatial Information Research 29(1):109–21. doi: 10.1007/s41324-020-00339-5. Ali, Abdelraouf M., Igor Savin, Anton Poddubskiy, Mohamed Abouelghar, Nasser Saleh, Khaled Abutaleb, Mohammed El-shirbeny, and Peter Dokukin. 2021. “The Egyptian Journal of Remote Sensing and Space Sciences Integrated Method for Rice Cultivation Monitoring Using Sentinel-2 Data and Leaf Area Index Q.” The Egyptian Journal of Remote Sensing and Space Sciences 24(3):431–41. doi: 10.1016/j.ejrs.2020.06.007. Amira, M. S., A. A. Shalaby, W. M. Omran, and H. M. Elmedalaa. 2020. “Characteristices, Classification and Evaluation of Soils in the Area Southeast El-Sadat City, Menoufia Governorate, Egypt.” Menoufia Journal of Soil Science 5(9):257–71. doi: 10.21608/mjss.2020.172392. Ashourloo, Davoud, Hamid Salehi Shahrabi, Mohsen Azadbakht, Amir Moeini Rad, Hossein Aghighi, and Soheil Radiom. 2020. “A Novel Method for Automatic Potato Mapping Using Time Series of Sentinel-2 Images.” Computers and Electronics in Agriculture 175(May):105583. doi: 10.1016/j.compag.2020.105583. Asner, Gregory P. 1998. “Biophysical and Biochemical Sources of Variability in Canopy Reflectance.” Remote Sensing of Environment 64(3):234–53. doi: 10.1016/S0034-4257(98)00014-5. Belgiu, Mariana, and Lucian Drăgu. 2016. “Random Forest in Remote Sensing: A Review of Applications and Future Directions.” ISPRS Journal of Photogrammetry and Remote Sensing 114:24–31. doi: 10.1016/j.isprsjprs.2016.01.011. Boschetti, M., D. Stroppiana, C. Giardino, and P. A. Brivio. 2007. “Proximal and Remote Sensing Observations for Precision Farming Application , the Citimap Project : Experimental Design and Preliminary Data Analysis.” 3–13. Clevers, J. G. P. W., and L. Kooistra. 2013. “Retrieving Canopy Chlorophyll Content Of Potato Crops Using Sentinel-2 Bands.” ESA Living Planet Symposium, Proceedings, 9-13 September 2013 ESA SP-722(September):1–8. Clevers, Jan G. P. W., and Lammert Kooistra. 2012. “Using Hyperspectral Remote Sensing Data for Retrieving Canopy Chlorophyll and Nitrogen Content.” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 5(2):574–83. doi: 10.1109/JSTARS.2011.2176468. Cornelissen, J. H. C., S. Lavorel, E. Garnier, S. Díaz, N. Buchmann, D. E. Gurvich, P. B. Reich, H. Ter Steege, H. D. Morgan, M. G. A. Van Der Heijden, J. G. Pausas, and H. Poorter. 2003. “A Handbook of Protocols for Standardised and Easy Measurement of Plant Functional Traits Worldwide.” Australian Journal of Botany 51(4):335–80. doi: 10.1071/BT02124. Cracknell, Arthur P., Costas A. Varotsos, Vladimir F. Krapivin, Jadunandan Dash, Paul J. Curran, and Giles M. Foody. 2009. Global Climatology and Ecodynamics: Anthropogenic Changes to Planet Earth. Curran, P. J., W. R. Windham, and H. L. Gholz. 1995. “Exploring the Relationship between Reflectance Red Edge and Chlorophyll Concentration in Slash Pine Leaves.” Tree Physiology 15(3):203–6. doi: 10.1093/treephys/15.3.203. Daughtry, C. S. T., C. L. Walthall, M. S. Kim, E. Brown De Colstoun, and J. E. McMurtrey. 2000. “Estimating Corn Leaf Chlorophyll Concentration from Leaf and Canopy Reflectance.” Remote Sensing of Environment 74(2):229–39. doi: 10.1016/S0034-4257(00)00113-9. Desloires, Johann. 2024. “Integrating Limited Data Realities : Advanced Crop Monitoring and Parcel-Level Yield Estimation Using Multispectral Satellite Data and Machine Learning To Cite This Version : HAL Id : Tel-04606831 DE L ’ UNIVERSITÉ DE MONTPELLIER Integrating Limited Data Realities : Advanced Crop Monitoring and Parcel-Level Yield Estimation Using Multispectral Satellite Data and Machine Learning Présentée Par Johann Desloires.” Devaux, André, Jean Pierre Goffart, Peter Kromann, Jorge Andrade-Piedra, Vivian Polar, and Guy Hareau. 2021. “The Potato of the Future: Opportunities and Challenges in Sustainable Agri-Food Systems.” Potato Research 64(4):681–720. doi: 10.1007/s11540-021-09501-4. Drusch, M., U. Del Bello, S. Carlier, O. Colin, V. Fernandez, F. Gascon, B. Hoersch, C. Isola, P. Laberinti, P. Martimort, A. Meygret, F. Spoto, O. Sy, F. Marchese, and P. Bargellini. 2012. Sentinel-2: ESA’s Optical High-Resolution Mission for GMES Operational Services. Vol. 120. El-Hendawy, Salah, Salah Elsayed, Nasser Al-Suhaibani, Majed Alotaibi, Muhammad Usman Tahir, Muhammad Mubushar, Ahmed Attia, and Wael M. Hassan. 2021. “Use of Hyperspectral Reflectance Sensing for Assessing Growth and Chlorophyll Content of Spring Wheat Grown under Simulated Saline Field Conditions.” Plants 10(1):1–26. doi: 10.3390/plants10010101. Espe, Matthew B., Haishun Yang, Kenneth G. Cassman, Nicolas Guilpart, Hussain Sharifi, and Bruce A. Linquist. 2016. “Estimating Yield Potential in Temperate High-Yielding, Direct-Seeded US Rice Production Systems.” Field Crops Research 193:123–32. doi: 10.1016/j.fcr.2016.04.003. Feng, Yang, Fan Yamin, and Li Jianlong. 2010. “0 引言 .” Food, World. 2020. World Food and Agriculture - Statistical Pocketbook 2019. Gilabert, María Amparo, Soledad Gandía, and Joaquín Meliá. 1996. “Analyses of Spectral-Biophysical Relationships for a Corn Canopy.” Remote Sensing of Environment 55(1):11–20. doi: 10.1016/0034-4257(95)00187-5. Giletto, Claudia Marcela, Cecilia Díaz, Jorge Edgardo Rattín, Hernán Eduardo Echeverría, and Daniel Osmar Caldiz. 2010. “Green Index to Estimate Crop Nitrogen Status in Potato Processing Varieties.” Chilean Journal of Agricultural Research 70(1):142–49. doi: 10.4067/s0718-58392010000100015. Gitelson, Anatoly A., Galina P. Keydan, and Mark N. Merzlyak. 2006. “Three-Band Model for Noninvasive Estimation of Chlorophyll, Carotenoids, and Anthocyanin Contents in Higher Plant Leaves.” Geophysical Research Letters 33(11):2–6. doi: 10.1029/2006GL026457. Herrmann, I., A. Karnieli, D. J. Bonfil, Y. Cohen, and V. Alchanatis. 2010. “SWIR-Based Spectral Indices for Assessing Nitrogen Content in Potato Fields.” International Journal of Remote Sensing 31(19):5127–43. doi: 10.1080/01431160903283892. Indices, Optimized Hyperspectral, Haibo Yang, Fei Li, Wei Wang, and Kang Yu. 2021. “Estimating Above-Ground Biomass of Potato Using Random.” Inoue, Yoshio, Martine Guérif, Frédéric Baret, Andrew Skidmore, Anatoly Gitelson, Martin Schlerf, Roshanak Darvishzadeh, and Albert Olioso. 2016. “Simple and Robust Methods for Remote Sensing of Canopy Chlorophyll Content: A Comparative Analysis of Hyperspectral Data for Different Types of Vegetation.” Plant Cell and Environment 39(12):2609–23. doi: 10.1111/pce.12815. Islam, AFM Tariqul, A. K. M. Saiful Islam, G. M. Tarekul Islam, Sujit Kumar Bala, Mashfiqus Salehin, Apurba Kanti Choudhury, M. Golam Mahboob, Nepal C. Dey, and Akbar Hossain. 2024. “Monitoring Wheat Area Using Sentinel-2 Imagery and In-Situ Spectroradiometer Data in Heterogeneous Field Conditions.” Discover Agriculture 2(1). doi: 10.1007/s44279-024-00069-4. Kamenova, Ilina, and Petar Dimitrov. 2021. “Evaluation of Sentinel-2 Vegetation Indices for Prediction of LAI, FAPAR and FCover of Winter Wheat in Bulgaria.” European Journal of Remote Sensing 54(sup1):89–108. doi: 10.1080/22797254.2020.1839359. Kaplan, Gregoriy, Lior Fine, Victor Lukyanov, Nitzan Malachy, Josef Tanny, and Offer Rozenstein. 2023. “Using Sentinel-1 and Sentinel-2 Imagery for Estimating Cotton Crop Coefficient, Height, and Leaf Area Index.” Agricultural Water Management 276(July 2022):108056. doi: 10.1016/j.agwat.2022.108056. Lago, Carlos, Juan Carlos Sepúlveda, Rogelio Barroso, Félix Óscar Fernández, Francisco Maciá, and Javier Lorenzo. 2011. “Sistema Para La Generación Automática de Mapas de Rendimiento. Aplicación En La Agricultura de Precisión.” Idesia (Arica) 29(1):59–69. Li, Dan, Yuxin Miao, Sanjay K. Gupta, Carl J. Rosen, Fei Yuan, Chongyang Wang, Li Wang, and Yanbo Huang. 2021. “Improving Potato Yield Prediction by Combining Cultivar Information and Uav Remote Sensing Data Using Machine Learning.” Remote Sensing 13(16). doi: 10.3390/rs13163322. Lichtenthaler, Hartmut K. 1987. “Chlorophylls and Carotenoids: Pigments of Photosynthetic Biomembranes.” Methods in Enzymology 148(C):350–82. doi: 10.1016/0076-6879(87)48036-1. Lin, Yongxin, Shuang Li, Shaoguang Duan, Yanran Ye, Bo Li, Guangcun Li, Dianqiu Lyv, Liping Jin, Chunsong Bian, and Jiangang Liu. 2023. “Methodological Evolution of Potato Yield Prediction: A Comprehensive Review.” Frontiers in Plant Science 14(July):1–25. doi: 10.3389/fpls.2023.1214006. Liu, H. Q., X. Q. Zhang, L. F. Chen, J. H. Fu, and H. C. Ma. 2022. “China ’ s Terrestrial UNVI Multidimensional.” 6(4):645–55. Lizarazo, Ivan, Jorge Luis Rodriguez, Omar Cristancho, Felipe Olaya, Marlon Duarte, and Flavio Prieto. 2023. “Identification of Symptoms Related to Potato Verticillium Wilt from UAV-Based Multispectral Imagery Using an Ensemble of Gradient Boosting Machines.” Smart Agricultural Technology 3(July 2022):100138. doi: 10.1016/j.atech.2022.100138. Madugundu, Rangaswamy, Khalid A. Al-Gaadi, El Kamil Tola, Salah El-Hendawy, and Samy A. Marey. 2023. “Mapping of Evapotranspiration and Determination of the Water Footprint of a Potato Crop Grown in Hyper-Arid Regions in Saudi Arabia.” Sustainability (Switzerland) 15(16). doi: 10.3390/su151612201. Morshed, Sarowar, Falguny Barua, Asura Khanom, Fahima Lokman, and H. T. Zubair. 2025. “Smart Agricultural Technology Crop Yield Prediction Using Machine Learning : An Extensive and Systematic Literature Review.” Smart Agricultural Technology 10(September 2024):100718. doi: 10.1016/j.atech.2024.100718. Mukiibi, A., A. T. B. Machakaire, A. C. Franke, and J. M. Steyn. 2024. A Systematic Review of Vegetation Indices for Potato Growth Monitoring and Tuber Yield Prediction from Remote Sensing. Springer Netherlands. Nady, Dina, Abdelraouf M. Ali, and Ali G. Mahmoud. 2022. “The Egyptian Journal of Remote Sensing and Space Sciences Developing Spatial Model to Assess Agro-Ecological Zones for Sustainable Agriculture Development in MENA Region : Case Study Northern Western.” The Egyptian Journal of Remote Sensing and Space Sciences (xxxx):1–11. doi: 10.1016/j.ejrs.2022.01.014. Ortiz, Oscar, and Victor Mares. 2017. The Potato Genome. Orynbaikyzy, Aiym, Ursula Gessner, and Christopher Conrad. 2022. “Spatial Transferability of Random Forest Models for Crop Type Classification Using Sentinel-1 and Sentinel-2.” Remote Sensing 14(6). doi: 10.3390/rs14061493. Petersen, Lillian Kay. 2018. “Real-Time Prediction of Crop Yields from MODIS Relative Vegetation Health: A Continent-Wide Analysis of Africa.” Remote Sensing 10(11):1–31. doi: 10.3390/rs10111726. Pham, Hoa Thi, Joseph Awange, Michael Kuhn, Binh Van Nguyen, and Luyen K. Bui. 2022. “Enhancing Crop Yield Prediction Utilizing Machine Learning on Satellite-Based Vegetation Health Indices.” Sensors 22(3):1–19. doi: 10.3390/s22030719. Psomiadis, Emmanouil, Nicholas Dercas, Nicolas R. Dalezios, and Nicos V. Spiropoulos. 2017. “Evaluation and Cross-Comparison of Vegetation Indices for Crop Monitoring from Sentinel-2 and Worldview-2 Images.” (November):79. doi: 10.1117/12.2278217. Pu, Ruiliang, Peng Gong, and Qian Yu. 2008. “Comparative Analysis of EO-1 ALI and Hyperion, and Landsat ETM+ Data for Mapping Forest Crown Closure and Leaf Area Index.” Sensors 8(6):3744–66. doi: 10.3390/s8063744. Ramírez, D. A., W. Yactayo, R. Gutiérrez, V. Mares, F. De Mendiburu, A. Posadas, and R. Quiroz. 2014. “Chlorophyll Concentration in Leaves Is an Indicator of Potato Tuber Yield in Water-Shortage Conditions.” Scientia Horticulturae 168(February):202–9. doi: 10.1016/j.scienta.2014.01.036. Safi, Abdur Rahim, Poolad Karimi, Marloes Mul, Abebe Chukalla, and Charlotte de Fraiture. 2022. “Translating Open-Source Remote Sensing Data to Crop Water Productivity Improvement Actions.” Agricultural Water Management 261(March):107373. doi: 10.1016/j.agwat.2021.107373. Salvador, Pablo, Diego Gómez, Julia Sanz, and José Luis Casanova. 2020. “Estimation of Potato Yield Using Satellite Data at a Municipal Level: A Machine Learning Approach.” ISPRS International Journal of Geo-Information 9(6). doi: 10.3390/ijgi9060343. Sinha, Priyakant, Andrew Robson, Derek Schneider, Talip Kilic, Harriet Kasidi Mugera, John Ilukor, and Jimmy Moses Tindamanyire. 2020. “The Potential of In-Situ Hyperspectral Remote Sensing for Differentiating 12 Banana Genotypes Grown in Uganda.” ISPRS Journal of Photogrammetry and Remote Sensing 167(July):85–103. doi: 10.1016/j.isprsjprs.2020.06.023. Sishodia, Rajendra P., Ram L. Ray, and Sudhir K. Singh. 2020. “Applications of Remote Sensing in Precision Agriculture: A Review.” Remote Sensing 12(19):1–31. doi: 10.3390/rs12193136. Song, Zhenghua, Yanfu Liu, Junru Yu, Yiming Guo, Danyao Jiang, Yu Zhang, Zheng Guo, and Qingrui Chang. 2024. “Estimation of Chlorophyll Content in Apple Leaves Infected with Mosaic Disease by Combining Spectral and Textural Information Using Hyperspectral Images.” Remote Sensing 16(12). doi: 10.3390/rs16122190. Sumanta, Nayek, Choudhury Imranul Haque, Jaishee Nishika, and Roy Suprakash. 2014. “Spectrophotometric Analysis of Chlorophylls and Carotenoids from Commonly Grown Fern Species by Using Various Extracting Solvents.” Research Journal of Chemical Sciences Res. J. Chem. Sci 4(9):2231–2606. Uddling, J., J. Gelang-Alfredsson, K. Piikki, and H. Pleijel. 2007. “Evaluating the Relationship between Leaf Chlorophyll Concentration and SPAD-502 Chlorophyll Meter Readings.” Photosynthesis Research 91(1):37–46. doi: 10.1007/s11120-006-9077-5. Vélez, Sergio, Raquel Martínez-Peña, and David Castrillo. 2023. “Beyond Vegetation: A Review Unveiling Additional Insights into Agriculture and Forestry through the Application of Vegetation Indices.” J 6(3):421–36. doi: 10.3390/j6030028. Vesali, F., M. Omid, H. Mobli, and A. Kaleita. 2017. “Feasibility of Using Smart Phones to Estimate Chlorophyll Content in Corn Plants.” Photosynthetica 55(4):603–10. doi: 10.1007/s11099-016-0677-9. Wagle, N., R. Pote, R. Shahi, S. Lamsal, S. Thapa, and T. D. Acharya. 2019. “Estimating and Mapping Chlorophyll-A Concentration of Phewa Lake of Kaski District Using Landsat Imagery.” ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 4(5/W2):127–32. doi: 10.5194/isprs-annals-IV-5-W2-127-2019. Wang, Qibing, Jianjun Chen, and Yuncong Li. 2004. “Nondestructive and Rapid Estimation of Leaf Chlorophyll and Nitrogen Status of Peace Lily Using a Chlorophyll Meter.” Journal of Plant Nutrition 27(3):557–69. doi: 10.1081/PLN-120028878. Van Wart, Justin, K. Christian Kersebaum, Shaobing Peng, Maribeth Milner, and Kenneth G. Cassman. 2013. “Estimating Crop Yield Potential at Regional to National Scales.” Field Crops Research 143:34–43. doi: 10.1016/j.fcr.2012.11.018. Xu, Xingang, Guijun Yang, Xiaodong Yang, Zhenhai Li, Haikuan Feng, Bo Xu, and Xiaoqing Zhao. 2018. “Monitoring Ratio of Carbon to Nitrogen (C/N) in Wheat and Barley Leaves by Using Spectral Slope Features with Branch-and-Bound Algorithm.” Scientific Reports 8(1):1–15. doi: 10.1038/s41598-018-28351-8. Xue, Jinru, and Baofeng Su. 2017. “Significant Remote Sensing Vegetation Indices: A Review of Developments and Applications.” Journal of Sensors 2017. doi: 10.1155/2017/1353691. Yadava, Umedi L. 2022. “A Rapid and Nondestructive Method to Determine Chlorophyll in Intact Leaves.”. Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 08 Apr, 2026 Reviews received at journal 01 Apr, 2026 Reviews received at journal 31 Mar, 2026 Reviewers agreed at journal 23 Mar, 2026 Reviewers agreed at journal 23 Mar, 2026 Reviewers agreed at journal 22 Mar, 2026 Reviewers agreed at journal 21 Mar, 2026 Reviewers agreed at journal 26 Aug, 2025 Reviewers agreed at journal 09 Aug, 2025 Reviewers invited by journal 07 Aug, 2025 Editor assigned by journal 07 Aug, 2025 Editor invited by journal 12 Jun, 2025 Submission checks completed at journal 11 Jun, 2025 First submitted to journal 31 May, 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-6790082","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":499127227,"identity":"334c8624-4de1-44bb-b9d8-87be9b5fc310","order_by":0,"name":"Abdelraouf M Ali","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABEElEQVRIiWNgGAWjYLCCCgaGBAYeIOMDXMiAgJYzUC2MM0jWwsxDjJvM2w8fkzjAUJfHz3P42GfbHXb58v0HmD/8KGCQk3fArkXmTFoaUMvhYsnetuTZuWeSLTfcSGCT7DFgMDY8gF2LBEOOmfQHhgOJG87zGDPntjEbGEgwsDED/ZK4sQGHFv43ZiCHAbXwf2a2bKs3ADnsM1BLPU4tEjkgLcyJG872MDMzth02YDiQwCAN1JIgj8P7EhLPki0OGBxOnNlzzJixt+24gcGNxDagXyQMN+DSwp988MaBirrEfp7kxww/26qBDjt8+MOPPzby8jgcBgGoEcfYAA4XgwP4tGAF+G0ZBaNgFIyCEQQA3v1UcO1gwDUAAAAASUVORK5CYII=","orcid":"","institution":"National Authority for Remote Sensing and Space Sciences (NARSS), Elnozha El-Gedidah","correspondingAuthor":true,"prefix":"","firstName":"Abdelraouf","middleName":"M","lastName":"Ali","suffix":""},{"id":499127228,"identity":"bb89ef1f-d4d4-4c92-a240-9ea930f1a876","order_by":1,"name":"Abdallah Bardisi","email":"","orcid":"","institution":"Zagazig University","correspondingAuthor":false,"prefix":"","firstName":"Abdallah","middleName":"","lastName":"Bardisi","suffix":""},{"id":499127229,"identity":"be03cd6b-75b4-4acf-9905-c39834025e66","order_by":2,"name":"Dalia Ahmed SamiNawaR","email":"","orcid":"","institution":"Zagazig University","correspondingAuthor":false,"prefix":"","firstName":"Dalia","middleName":"Ahmed","lastName":"SamiNawaR","suffix":""},{"id":499127230,"identity":"f1804e02-7b08-41af-8bf7-c665a0b44317","order_by":3,"name":"Noureldin Laban","email":"","orcid":"","institution":"National Authority for Remote Sensing and Space Sciences (NARSS), Elnozha El-Gedidah","correspondingAuthor":false,"prefix":"","firstName":"Noureldin","middleName":"","lastName":"Laban","suffix":""},{"id":499127231,"identity":"6d998f81-1a31-4764-b9d7-ac70fe0b8f60","order_by":4,"name":"D Kucher","email":"","orcid":"","institution":"RUDN University","correspondingAuthor":false,"prefix":"","firstName":"D","middleName":"","lastName":"Kucher","suffix":""},{"id":499127232,"identity":"7d48dd52-cdd4-4ef9-bbca-a2e432297d60","order_by":5,"name":"Nazih Y. Rebouh","email":"","orcid":"","institution":"RUDN University","correspondingAuthor":false,"prefix":"","firstName":"Nazih","middleName":"Y.","lastName":"Rebouh","suffix":""},{"id":499127233,"identity":"b3e3637c-a01e-42a0-a181-008a5892c727","order_by":6,"name":"Abdel-Aziz Belal","email":"","orcid":"","institution":"National Authority for Remote Sensing and Space Sciences (NARSS), Elnozha El-Gedidah","correspondingAuthor":false,"prefix":"","firstName":"Abdel-Aziz","middleName":"","lastName":"Belal","suffix":""},{"id":499127235,"identity":"8584f1a4-dc44-4845-bb29-2255a31b6264","order_by":7,"name":"Adel Ibraheim Selim","email":"","orcid":"","institution":"National Authority for Remote Sensing and Space Sciences (NARSS), Elnozha El-Gedidah","correspondingAuthor":false,"prefix":"","firstName":"Adel","middleName":"Ibraheim","lastName":"Selim","suffix":""}],"badges":[],"createdAt":"2025-05-31 09:38:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6790082/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6790082/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":89065982,"identity":"9b153903-7891-44ac-8d52-498b8516aa39","added_by":"auto","created_at":"2025-08-14 10:42:28","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":1785993,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eLocation map of the study area.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-6790082/v1/bde18375c6c8b02f43321210.png"},{"id":89065938,"identity":"f5bab7a4-eb78-4ece-8e1d-d97b2e044d4a","added_by":"auto","created_at":"2025-08-14 10:42:26","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":1522681,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eDerived methodology to estimate LCC and Potato crop yield.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-6790082/v1/9541caa00d2d97ab2cda5572.png"},{"id":89066876,"identity":"ba837779-dcea-4fd1-a0de-6fbe902dfbef","added_by":"auto","created_at":"2025-08-14 10:42:55","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":419404,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eshows the location of the sample site and field measurements.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-6790082/v1/852e78621b3d066e8a9022b3.png"},{"id":89066268,"identity":"4243840c-d72b-4e37-9a6f-72f156ba1915","added_by":"auto","created_at":"2025-08-14 10:42:38","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":126954,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eAverage canopy spectral curve per potato growth stages.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-6790082/v1/9474a9659c6e84554a5d7c95.png"},{"id":89066303,"identity":"56f2f27c-a4d7-4cd8-9512-6cda651e0051","added_by":"auto","created_at":"2025-08-14 10:42:38","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":97505,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eA statistical box line graph depicting chlorophyll concentration during the various growth stages of potatoes for the modeling dataset gathered in the winter growing season (2022-2023)\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-6790082/v1/099b5baa3bb01baf188d759b.png"},{"id":89066231,"identity":"33e41acb-04e9-459e-b944-dab77d7695ee","added_by":"auto","created_at":"2025-08-14 10:42:37","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":20813,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eA statistical box line graph depicting chlorophyll concentration during the various growth stages of potatoes for the modeling dataset gathered in the winter growing season (2022-2023\u003c/strong\u003e)\u003c/p\u003e","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-6790082/v1/77c24569793dd0b7a734fca8.png"},{"id":89066545,"identity":"f381ebdc-f3ba-41e4-aca5-43d24ffc50af","added_by":"auto","created_at":"2025-08-14 10:42:43","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":783856,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eSpatial distribution of Normalized Deference vegetative Index (NDVI) for winter Potato crop during growth stages.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-6790082/v1/581e7b6cbd5780695fe69890.png"},{"id":89066872,"identity":"c5543205-03c8-4160-93e8-108b0fefd94d","added_by":"auto","created_at":"2025-08-14 10:42:54","extension":"png","order_by":8,"title":"Figure 8","display":"","copyAsset":false,"role":"figure","size":783728,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eSpatial distribution of Modified Chlorophyll Absorption Ratio Index (MCARI) for winter Potato crop during growth stages, pivot 11-s\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-6790082/v1/a5cd720521921c7517e0573c.png"},{"id":89066636,"identity":"8f191907-6442-4d61-9e6a-956e646e1dee","added_by":"auto","created_at":"2025-08-14 10:42:46","extension":"png","order_by":9,"title":"Figure 9","display":"","copyAsset":false,"role":"figure","size":867743,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eSpatial distribution of Leaf Chlorophyll Index (LCI) for winter Potato crop during growth stages\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-6790082/v1/f9785d2d155e43d0bd3ac190.png"},{"id":89066078,"identity":"d5871bce-9411-4944-8106-873271900b9a","added_by":"auto","created_at":"2025-08-14 10:42:32","extension":"png","order_by":10,"title":"Figure 10","display":"","copyAsset":false,"role":"figure","size":732189,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eMap of crop types in 6th of October company winter season (2022-2023).\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-6790082/v1/7427249a361c3463263684a3.png"},{"id":89065959,"identity":"86710eb0-1d4c-4ce4-88a8-5904635db0d5","added_by":"auto","created_at":"2025-08-14 10:42:27","extension":"png","order_by":11,"title":"Figure 11","display":"","copyAsset":false,"role":"figure","size":446437,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eSpatial distribution of potato crop at 6th of October Company during the winter season(2022-23).\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage11.png","url":"https://assets-eu.researchsquare.com/files/rs-6790082/v1/c00b14b3372d36e4fe76725b.png"},{"id":89066190,"identity":"04922e36-5e28-43bb-979e-a107cdea145d","added_by":"auto","created_at":"2025-08-14 10:42:36","extension":"png","order_by":12,"title":"Figure 12","display":"","copyAsset":false,"role":"figure","size":806254,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eSpatial distribution map of TChl for the potato crop at 6th of October Company (2022-2023) based on band spectral bands\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage12.png","url":"https://assets-eu.researchsquare.com/files/rs-6790082/v1/8a0ccd455369cb35854de131.png"},{"id":89066059,"identity":"5b2643dc-4c50-4b07-9cdd-a144b22fd339","added_by":"auto","created_at":"2025-08-14 10:42:30","extension":"png","order_by":13,"title":"Figure 13","display":"","copyAsset":false,"role":"figure","size":777167,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eChlt map for potato crop at 6th of October Company (2022-2023) based on VIS.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage13.png","url":"https://assets-eu.researchsquare.com/files/rs-6790082/v1/c41098b57dbdf2480e99eedb.png"},{"id":89066083,"identity":"5c18d1e2-3281-4cc5-8293-9aec1a477bdf","added_by":"auto","created_at":"2025-08-14 10:42:33","extension":"png","order_by":14,"title":"Figure 14","display":"","copyAsset":false,"role":"figure","size":724347,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eSPAD Chlorophyll values map for potato crop at 6th of October Company (2022-2023) based on spectral bands\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage14.png","url":"https://assets-eu.researchsquare.com/files/rs-6790082/v1/0fd8d0cdd492a94c46e13dc4.png"},{"id":89066873,"identity":"f608f307-1d82-44b9-acfe-2ac6512356fd","added_by":"auto","created_at":"2025-08-14 10:42:55","extension":"png","order_by":15,"title":"Figure 15","display":"","copyAsset":false,"role":"figure","size":728409,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eSPAD Chlorophyll values map for potato crop at 6th of October Company (2022-2023) based on VIS\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage15.png","url":"https://assets-eu.researchsquare.com/files/rs-6790082/v1/059644bce9bfd9f04defb395.png"},{"id":89066621,"identity":"87388f98-7ab0-447e-944e-3ea57c540cba","added_by":"auto","created_at":"2025-08-14 10:42:45","extension":"png","order_by":16,"title":"Figure 16","display":"","copyAsset":false,"role":"figure","size":1513769,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eValidation of the predicted map of (Chlt) concentration measured in field (µg/gm. fw) A) based on VIS and B) selected bands\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage16.png","url":"https://assets-eu.researchsquare.com/files/rs-6790082/v1/ed03ec68bb8c4a39f3b5ddab.png"},{"id":89066877,"identity":"6d8a18c7-6827-436a-b7cc-616af13811b8","added_by":"auto","created_at":"2025-08-14 10:42:55","extension":"png","order_by":17,"title":"Figure 17","display":"","copyAsset":false,"role":"figure","size":1452708,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eValidation map of estimating SPAD chlorophyll values measured in field based on A) VIS and B) spectral bands\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage17.png","url":"https://assets-eu.researchsquare.com/files/rs-6790082/v1/016b166dbeaa27346a2fadb2.png"},{"id":89066460,"identity":"95718a88-b43b-4bd9-bcb6-7ccc0d380330","added_by":"auto","created_at":"2025-08-14 10:42:41","extension":"png","order_by":18,"title":"Figure 18","display":"","copyAsset":false,"role":"figure","size":1117547,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eSpatial distribution of potato crop yield from CNDVI, CSAVI and Pre TChl model during 2022-2023 season\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage18.png","url":"https://assets-eu.researchsquare.com/files/rs-6790082/v1/57f5f82c38d76d4849c78eff.png"},{"id":89066626,"identity":"db417a9e-fe39-46e6-a005-2088041fee21","added_by":"auto","created_at":"2025-08-14 10:42:45","extension":"png","order_by":19,"title":"Figure 19","display":"","copyAsset":false,"role":"figure","size":29994,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eRelationship between predicted vs. actual yield (ton. ha-1) for potato crop\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"floatimage19.png","url":"https://assets-eu.researchsquare.com/files/rs-6790082/v1/0c3b76b28cbf5ebd10ac9ce1.png"},{"id":89070177,"identity":"bd7deec7-8102-4d5a-8e77-0d927b5ffc2e","added_by":"auto","created_at":"2025-08-14 10:58:51","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":17564311,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6790082/v1/a8b95f04-7968-4424-9c06-399017883b7d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Comparative Analysis Between Sentinel-2 And Proximal Sensors to Study the Spatial Distribution of Chlorophyll Content and Potato Crop Yield Using Artificial Intelligence: A Case Study of Salheia, Egypt","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003ePotato crop (Solanum tuberosum L.) is one of the most important and widely consumed non-grain foods. Many countries have seen this crop rise to prominence. Due to their significance in the food industry's supply chain.(Ortiz and Mares 2017). Over the past decade, potato production in Egypt has steadily increased due to the expansion of both the farmed area and the yield. Out of Egypt's 27 governorates, 25 are engaged in potato cultivation. In 2019, a total of 171,000 hectares were cultivated, resulting in a yield of 5.2\u0026nbsp;million tons of potatoes, with an average output of about 30.3 tons per hectare(Food \u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e2020\u003c/span\u003e).Mapping potato crops using Sentinel-2 imagery has become crucial for improving agricultural monitoring, particularly on large-scale farms(Ashourloo et al. \u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e2020\u003c/span\u003e). With its multispectral imaging capabilities, Sentinel-2 facilitates accurate and timely crop growth and health observation, making it an essential tool\u003c/p\u003e\u003cp\u003e. Their frequent revisit time (every 5 days) allows for consistent and detailed monitoring of crop fields, which is vital for precise crop mapping. According to (Cornelissen et al. \u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e2003\u003c/span\u003e), Sentinel-2 imagery is commonly used to compute vegetation indices (VIs), including the Normalized Difference Vegetation Index (NDVI) and the Enhanced Vegetation Index (EVI), both of which are closely linked to crop health. These indices are crucial in identifying early growth stages, recognizing stress conditions, crop area estimation, and forecasting yields(Islam et al. \u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e2024\u003c/span\u003e; Kamenova and Dimitrov 2021; Mukiibi et al. \u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). Recent research has shown that Sentinel-2 can effectively map potato cultivation by analyzing these indices to assess chlorophyll content, a key factor affecting photosynthesis and crops' overall health(Islam et al. \u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e2024\u003c/span\u003e; Mukiibi et al. \u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e2024\u003c/span\u003e; Zheng et al. 2018). Another significant application of Sentinel-2 imagery is estimating the area covered by potato crops and predicting their yields. Several studies have used machine learning algorithms and Sentinel-2 imagery to predict crop yields(Kaplan et al. \u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e2023\u003c/span\u003e; Morshed et al. \u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Zheng et al. 2018). These models used data from different spectral bands of Sentinel-2 and spectroradiometry to forecast yields depending on crop features like biomass and chlorophyll contents. A notable study by (Kaplan et al. \u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e2023\u003c/span\u003e; Morshed et al. \u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Mukiibi et al. \u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e2024\u003c/span\u003e)(Nady, Ali, and Mahmoud \u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e2022\u003c/span\u003e) demonstrated that combining spectral data from Sentinel-2 with machine learning techniques can estimate yields for potato crops, providing a non-invasive approach for large-scale yield assessments. The biochemical characteristics of plants are crucial in regulating their overall photosynthetic and physiological functions. Among these characteristics, chlorophyll pigments play a significant role in photosynthetic activities, making them the most important biochemical features in leaves(Clevers and Kooistra 2012; Cracknell et al. \u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e2009\u003c/span\u003e; Gitelson, Keydan, and Merzlyak 2006; Inoue et al. \u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e2016\u003c/span\u003e). For crops to absorb and store the energy necessary for developing their tissues, leaf chlorophyll content (LCC) is essential for plant growth. LCC is a crucial indicator of plant health, helping to evaluate the rate of photosynthetic energy production and overall plant productivity, and nutrient content.(Clevers and Kooistra 2012)and (Vesali et al. \u003cspan citationid=\"CR55\" class=\"CitationRef\"\u003e2017\u003c/span\u003e). Crops' chlorophyll content is positively correlated with their nitrogen levels, photosynthetic capacity, and developmental stages, This technology is a valuable tool for evaluating crop growth. Traditional methods for estimating chlorophyll, such as spectrophotometry, atomic absorption, and HPLC, are time-consuming and destructive. In contrast, analyzing the spectral properties of crops allows for quick, non-destructive, and large-scale estimation of chlorophyll content. This method has been applied to various crops, including corn, soybeans, bananas, potatoes, and sugarcane, to monitor development stages and yield estimates.(Sinha et al. \u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e2020\u003c/span\u003e) Conducted a study to identify the most effective vegetation indices for assessing the density of chlorophyll content (CCD). in rice and wheat during various growth stages. Linear regression models used to calculate CCD demonstrated determination coefficients greater than 0.85, providing valuable insights for agricultural production management and monitoring crop dynamics across different growing environments.(Feng, Yamin, and Jianlong 2010). (El-Hendawy et al. \u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e2021\u003c/span\u003e) Multivariate regression to evaluate spectral reflectivity and determine chlorophyll concentrations in winter wheat. Numerous studies indicate that ratio and normalized difference indices, especially those utilizing red-edge bands, can effectively estimate chlorophyll content, can derive the REP using the red-edge bands from MERIS and the recommended bands from Sentinel-2 and Sentinel-3 using a straightforward linear model to analyze the red-infrared slope(Boschetti et al. \u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e2007\u003c/span\u003e). To create a model for estimating chlorophyll content using spectral data,(Yang et al. 2022; Yin et al. 2021)(Liu et al. \u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e2022\u003c/span\u003e) developed vegetation indices and studied the correlations between these indices and chlorophyll levels in plant canopies. This work resulted in the creation of a general model for estimating chlorophyll content. they can estimate the amount of chlorophyll present by analyzing variations in the crop's distinctive features, such as spectral position and area. Studies (Curran, Windham, and Gholz \u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e1995\u003c/span\u003e; Gilabert, Gand\u0026iacute;a, and Meli\u0026aacute; 1996; Xu et al. \u003cspan citationid=\"CR59\" class=\"CitationRef\"\u003e2018\u003c/span\u003e)investigated the relationship between chlorophyll levels in plants and the location of the spectral red edge. The researchers found that as leaf maturity progresses, the amplitude of the red edge increases, the position of the red edge shifts forward consistently, and the area of the red edge expands and then declines while the blue edge area continues to grow.\u003c/p\u003e\u003cp\u003eTo build a model for estimating chlorophyll content, (Song et al. \u003cspan citationid=\"CR51\" class=\"CitationRef\"\u003e2024\u003c/span\u003e)examined the relationship between apple leaf chlorophyll content and hyperspectral reflectance. The Minolta company created a handheld dual wavelength chlorophyll meter, known as the SPAD models 501 and 502. The SPAD-502 measures the transmittance of red (650 nm) and infrared (940 nm) radiation through leaves to determine a relative value indicating chlorophyll content. This portable, non-destructive tool, called the Soil Plant Analysis Development (SPAD) chlorophyll meter, provides a quick and precise method for measuring leaf chlorophyll concentration in various crops(Uddling et al. \u003cspan citationid=\"CR53\" class=\"CitationRef\"\u003e2007\u003c/span\u003e). Plant health status and nitrogen concentrations have been successfully inferred from this device's readings in potato remote sensing (Giletto et al. \u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e2010\u003c/span\u003e; Ram\u0026iacute;rez et al. \u003cspan citationid=\"CR46\" class=\"CitationRef\"\u003e2014\u003c/span\u003e). For many years, researchers have studied remote sensing imaging techniques to detect changes in the chlorophyll content of crops. Several vegetation indices (VIs) have been proposed to estimate the chlorophyll levels in the canopy. Significant advancements have been made in the biophysical characterization of vegetation using remote sensing technology. Research shows a strong correlation between satellite sensor data and key biophysical variables, including leaf area index, leaf chlorophyll content, plant cover, and pest presence.(Lago et al. \u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e2011\u003c/span\u003e; Lizarazo et al. \u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e2023\u003c/span\u003e; Madugundu et al. \u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e2023\u003c/span\u003e; Safi et al. \u003cspan citationid=\"CR47\" class=\"CitationRef\"\u003e2022\u003c/span\u003e; Sishodia, Ray, and Singh 2020). The primary objectives of this study are to analyze the spatial distributions of chlorophyll content and potato crop yield utilizing spectral vegetation indices obtained from both a spectroradiometer and Sentinel-2 satellite data.\u003c/p\u003e"},{"header":"2. Materials and Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003e2.1. Study site, Climate and Soil Condition\u003c/h2\u003e\u003cp\u003eThe study is in the east-south region of El-Kassaseen City, southwest of Ismailia City. As shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e, its geographical boundaries are defined by latitudes of 30O 22' 02\" and 30O 31' 16\" and longitudes of 31O 52' 36\" and 32O 06' 26\". The project began operations in 1982 and was established in 1981, covering 12,500 hectares. The project employs two irrigation systems: drip irrigation and central pivot irrigation. Drip irrigation is used for orchard trees, while central pivot irrigation is used for field crops. The region generally experiences a desert climate, where precipitation satisfies less than 50% of potential evapotranspiration, according to the K\u0026ouml;ppen Climate Classification System. The average yearly temperature in the area exceeds 18\u0026deg;C, and it receives an average annual rainfall of only 20 millimeters. January serves as the month with the most rainfall, averaging 6.9 millimeters of precipitation, which can benefit the surrounding ecosystems. The highest month of temperatures is June, with average maximums 41. 8\u0026deg;C.while the lowest month was January ranging between 8.0\u0026deg;C and 17.0\u0026deg;C, resulting in a diverse climate throughout the year. By August, temperatures pleasantly drop to around 21.5\u0026deg;C, contributing to a milder environment. The soil types in the study area are clay loams. Sandy loam is especially beneficial for drainage and is mainly made up of sand particles along with moderate amounts of clay and silt, enhancing its moisture retention capabilities. The soil's pH level in the study area varies from 7.5 to 8.5, indicating it is neutral to slightly alkaline; this pH range can support the growth of specific plants. a higher pH can sometimes lead to challenges with nutrient availability, especially regarding micronutrients,(Amira et al. \u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e2020\u003c/span\u003e).\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec4\" class=\"Section2\"\u003e\u003ch2\u003e2.2. Data\u003c/h2\u003e\u003cp\u003eThis study used three types of data remote sensing data (Sentinel 2 and ASD spectroradiometer), proximal sensors (SPAD chlorophyll), and in situ measurements for winter potato crop. also, crop areas were determined to validate the crop yield map. As shown In Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e, Sentinel-2 data was used to estimate crop area using a random forest algorism to estimate the spatial distribution of potato crops. A spectroradiometer was used to derive vegetation indices to predict LCC and crop yield models using the stepwise multi-linear regression model SWML. derived vegetation indices from Sentinel 2 were used to validate potato LCC and crop yield.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cdiv id=\"Sec5\" class=\"Section3\"\u003e\u003ch2\u003e2.2.1. Remote sensing data\u003c/h2\u003e\u003cdiv id=\"Sec6\" class=\"Section4\"\u003e\u003ch2\u003e2.2.1.1. Satellite Imagery\u003c/h2\u003e\u003cp\u003eThe Sentinel-2 polar-orbiting satellite is scheduled to launch in 2014 by ESA. the spatial resolution of sentinel are Four bands at 10 m, six bands at 20 m, and three bands at 60 m., spatial resolution are equipped with the Multi-Spectral Instrument (MSI) (Drusch et al. \u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e2012\u003c/span\u003e)., swath width is 290 km is achieved using a 20\u0026deg; The total field of view, with two spectral bands with a spatial resolution of 20 m and a bandwidth of 15 nm, specifically targeting 705 and 740 nm in the red-edge area. Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. Three free-of-cloud Sentinel-2 images were processed and projected in WGS84 UTM zone 36N. Sentinel-2 images covering the period from November 2022 to February 2023 were downloaded concurrently with the same dates of field measurements using the ASD field spectroradiometer and SPAD measurements. Samples were collected for the entire phonological cycle on cloud-free days (Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e). Data from the Sentinel-2 Level 2A satellite were used in this study to produce vegetation indices(VIS), specifically the Normalized Difference Vegetation Index (NDVI), Modified Chlorophyll Absorption Ratio index (MCARI), and Leaf Chlorophyll Index (LCI). These data were geomrtric and atmospheric corrected via the Sen2Cor processor, which correct atmospheric disturbances and converts atmospheric surface reflectivity to reflectance of the surface of the target. All images were selected to correspond to the potato crop growth stages in the study area and at the specified dates, and these data were uniformly processed to maintain data quality throughout the analysis and modeling phases.\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\u003eSentinel-2 satellite date acquisition during study season.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"3\"\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\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eFieldwork\u003c/p\u003e\u003cp\u003eDate\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSeason\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eSentinel-2 Image Code\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eNovember\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003e2022\u0026ndash;2023\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eS2B_MSIL1C_20221119T083139_N0400_R021_T36RUU_20221119T091634\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eDecember\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eS2A_MSIL1C_20221214T083341_N0509_R021_T36RUU_20221214T092251\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eJanuary\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eS2B_MSIL1C_20230108T083229_N0509_R021_T36RUU_20230108T090814\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv id=\"Sec7\" class=\"Section3\"\u003e\u003ch2\u003e2.2.2. Field Radiometry Measurements\u003c/h2\u003e\u003cp\u003eFigure \u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e shows the grid samples designed to collect the spectral data for chlorophyll measurements using SPAD and leaf samples for laboratory measurements and crop yield data. spectral measurements and plant samples were collected through three potato crop stages (S1) (vegetation and tuber formation, (Stage 2)tuber expansion stage after flowers fell, and (Stage 3) tuber maturation stage during leaves turning yellow, as described in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e.\u003c/p\u003e\u003cp\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\u003eField measurements and spectral data acquisition during potato crop growth stages.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"3\"\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\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePotato Growth stage\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eCharacteristics of the crop\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eacquisition date\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eStage 1\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eVegetation and tuber formation stage\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eNovember 19\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eStage 2\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eTuber expansion stage after the flowers fall\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eDecember14\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eStage 3\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eTuber maturation stage during leaves turning yellow\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eJanuary 8\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\u003eThe ASD 4 FieldSpec spectroradiometer, manufactured by ASD Analytical Spectral Devices, was used to assess the leaf reflectance from chosen potato crops. Data collection was conducted on sunny days from 10:00 a.m. to 2:00 p.m. to reduce the impact of atmospheric fluctuations and changes in solar angle. The spectroradiometer captured reflectance data across the entire optical spectrum, including the visible (VIS), near-infrared (NIR), and short-wave infrared (SWIR) regions, covering wavelengths from 350 nm to 2500 nm, with an output resolution of 1 nm increments. The device spectral resolution with a sampling interval of 1.4 nm for the 350\u0026ndash;1050 nm range and 2 nm for the 1000\u0026ndash;2500 nm range. It includes automatic interpolation to provide a consistent 1 nm spectral resolution throughout the full spectrum. Spectral data were collected by measuring the spectrometer\u0026rsquo;s irradiance on a calibration panel. A contact probe, linked through a fiber optic cable, was employed to ensure consistent ambient conditions during the reflectance measurements.\u003c/p\u003e\u003cp\u003eUsing the View Spec 3 software, the spectral reflectance curves were examined, and the average spectrum of each stage was used to study the dynamic variations between the various stages. The reflectance of each level is displayed in Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e. Both the visible region (400\u0026ndash;680 nm) and the near-infrared region (700\u0026ndash;1150 nm) showed comparable patterns. Due to the pigment's significant absorption, the minimum reflectance in the visible spectrum appeared between 400 and 680 nm. Since the reflectance surface is located in the mesophyll's spongy structure, the reflectance increased from 700 to 960 nm in the near-infrared range. While there was a considerable reflection between 960 and 1300 nm, the absorption of leaf water content caused a weak reflectance valley to form between 1400 and 2500 nm.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eA SPAD-502 meter was used to measure the identical potato leaves for every sample at the same times and dates of the ASD measurements. SPAD-502 meters The Soil Plant Analysis Development chlorophyll meter (SPAD), a portable non-imaging tool, offers a quick, precise, and non-destructive method of measuring the LCC for various crops. This device's readings have been effectively applied to potato remote sensing as an indication of nitrogen concentrations and plant health status (Giletto et al. \u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e2010\u003c/span\u003e).\u003c/p\u003e\u003cdiv id=\"Sec8\" class=\"Section4\"\u003e\u003ch2\u003e2.2.2.1. Vegetation indices\u003c/h2\u003e\u003cp\u003eBased on the acquisition date shown in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e, three vegetation indices (VIs) were derived for every Sentinel-2 image by spectral analysis. The indices were created using software called SNAP 9.0. The VIs studied in this letter and their definitions are provided in Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e. The NDVI, MCARI, and LCI were mainly used as LCC estimators for estimating LCC. The same vegetation indices were calculated from ASD spectra data, as shown in Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e. Bands centered at 490 nm, 560 nm, 665 nm, 705 nm, 740 nm, and 783 nm were used for this study. The investigated vegetation indices were calculated using 842 nm, 865 nm, 1610 nm, and 2190 nm wavelength.\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\u003eDerived vegetation indices from ASD spectroradiometer\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"5\"\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\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAbbreviation\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eName\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eFormula from ASD\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eFormula from Sentenil-2 Images\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eReference\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eNDVI\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eNormalized Difference Vegetation Index\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e(R800 - R670) / (R800\u0026thinsp;+\u0026thinsp;R670)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:\\frac{\\text{B}8-\\text{B}4}{\\text{B}8+\\text{B}4}\\)\u003c/span\u003e\u003c/span\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e(Devaux et al. \u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e2021\u003c/span\u003e)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eMCARI\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eModified Chlorophyll Absorption Ratio Index\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e(R701 - R670) \u0026minus;\u0026thinsp;0.2 * (R701 - R550)) * (R701/R670)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:\\left[(\\text{B}5\\:-\\:\\text{B}4)\\:-\\:0.2\\:\\text{*}\\:(\\text{B}5\\:-\\:\\text{B}3)\\right]\\text{*}\\:(\\text{B}5\\:/\\:\\text{B}4)\\)\u003c/span\u003e\u003c/span\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e(Herrmann et al. \u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e2010\u003c/span\u003e)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eLCI\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLeaf Chlorophyll Index\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e(R850 \u0026ndash; R710) / (R850\u0026thinsp;+\u0026thinsp;R680)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:\\frac{\\text{B}8-\\text{B}5}{\\text{B}8+\\text{B}4}\\)\u003c/span\u003e\u003c/span\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e(Pu, Gong, and Yu 2008)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv id=\"Sec9\" class=\"Section3\"\u003e\u003ch2\u003e2.2.3. Potato Leaves Samples\u003c/h2\u003e\u003cp\u003eleave samples of the potato crop were taken from pivot11-s. The ENVI software version 5.3's was used to plan the pre-planning of the sample field survey that was gathered. The Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e shows that the spatial distribution based on a prescription map created using soil categorization variability, A number of samples were taken from this axis: 23 samples with two replications for each point, for a total of 69 samples, which were divided into 50 samples for applying the model and 19 samples for validation. The same samples were taken at each of the three growth stages. GPS receivers made the precise location inside the field. To determine total chlorophyll, these leaf samples were gathered from various locations. Every sample plant canopy had three randomly selected leaves, which were then placed in a freshness protection bag, numbered, and kept in a transportable thermal insulation box. Next, using conventional chemical techniques in the lab, the chlorophyll concentration was ascertained (Sumanta et al. \u003cspan citationid=\"CR52\" class=\"CitationRef\"\u003e2014\u003c/span\u003e)The amounts of carotenoid and chlorophyll were measured using spectrophotometry in accordance with (Lichtenthaler \u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e1987\u003c/span\u003e)Following filtration, the absorbance of 0.2 g of fresh plant leaf tissue was measured using a Jenway 6800 UV/Vis Spectrophotometer at 663.2, 646.8, and 470 nm in comparison to a blank sample of acetone 80%. The concentration of chlorophyll (Chl) was calculated using the following formulas:\u003c/p\u003e\u003cp\u003e\u003cb\u003eChla\u0026thinsp;=\u0026thinsp;12.25A 663.2\u0026ndash;2.79 A 646.8 (1)\u003c/b\u003e\u003c/p\u003e\u003cp\u003e\u003cb\u003eChlb\u0026thinsp;=\u0026thinsp;21.50 A 646.8\u0026ndash;5.1A 663.2 (2\u003c/b\u003e)\u003c/p\u003e\u003cp\u003eThe absorbances at 646.8 nanometers and 663.2 nanometers are marked as A646.8 and A663.2. Chla refers to the concentration of chlorophyll-a, and Chlb refers to the concentration of chlorophyll-b. Chlt is the total chlorophyll concentration, reported in micrograms per gram. Fw is used in the study.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec10\" class=\"Section3\"\u003e\u003ch2\u003e2.2.4. in-situ potato yield collection sampling strategy\u003c/h2\u003e\u003cp\u003eIn this study, a centrally irrigated pivot field (11-S) was used as a field sample. Potato (tuber) yield data were collected at Site using stratified random sampling based on the year 2023 for the study season, with three replicates per point location (50 points were used for the generated model and 19 points for validation). A GPS receiver (Trimble GeoXH) was used to locate sample locations in the field and distributed throughout each experimental field using the randomization feature of the ENVI software (version 5.3) according to a recipe map generated based on vegetation variability. A simple random sample was then selected from each subset. At each sampling site, potatoes were harvested over an area of ​​1 m\u0026sup2; to obtain the actual crop yield at the site. Weighting and upscaling to the common yield unit (tons ha-1) were performed on the harvested potatoes. Actual yield and remote sensing-generated variation indices (NDVI, SAVI, CNDVI, CSAVI, and LCI) were plotted against each other during the growing period to demonstrate the correlation between the two and produce an empirical equation for predicting potato yield. Pearson's correlation coefficient (linear) was used. To estimate crop yield, 50 samples were used to build the model between the dissimilarity indices (CNDVI and CSAVI) and the single-date dissimilarity indices (NDVI, SAVI, and LCI). The most suitable dissimilarity indices for prediction were determined by analyzing the growth-gradient correlation coefficients to obtain the best-fit empirical equations. The optimal growth stage, at which the dissimilarity indices were most closely related to yield, was evaluated to determine the appropriate timing for predicting potato yield before harvest.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec11\" class=\"Section3\"\u003e\u003ch2\u003e2.2.4. Image classification using AI\u003c/h2\u003e\u003cp\u003eThe use of remote sensing techniques, GIS, and artificial intelligence to obtain information on crop distribution and cultivated areas is important for making optimal agricultural planning and management decisions. Satellite data is used as a data source, based on machine learning methodology, as a tool for static and dynamic crop classification. In this study, the Google Earth Engine (GEE) platform was used for AI image classification based on remote sensing images and vegetation indices. GEE provided by Google, which is a geospatial analysis platform that works based on electronic cloud and can perform geospatial analysis on a global scale. Summer crop classification were done by the Random Forest (RF) method (Indices et al. \u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e2021\u003c/span\u003e; Orynbaikyzy, Gessner, and Conrad 2022), which is a machine learning (ML) method.\u003c/p\u003e\u003cdiv id=\"Sec12\" class=\"Section4\"\u003e\u003ch2\u003e2.2.4.1.Validation of image classification and accuracy assessment\u003c/h2\u003e\u003cp\u003eField observations were carried out in the studied area to collect ground control points that were used to discriminate summer crops. 160 Sampleas were collected To determine the accuracy of image classification at a pixel level, it was necessary to distribute ground truth data at various locations and different crops throughout the study region. This was carried out through field trip observations that were carried out during the crop-growing season for summer crops 2023. The efficacy of RF is often evaluated by Overall Accuracy (OA) and the Kappa Coefficient according to (Belgiu and Drăgu 2016)\u003cdiv id=\"Equ1\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ1\" name=\"EquationSource\"\u003e\n$$\\:\\varvec{K}=\\frac{\\varvec{N}\\sum\\:_{\\varvec{i}-1}^{\\varvec{r}}{\\varvec{x}}_{\\varvec{i}\\varvec{i}}-\\sum\\:_{\\varvec{i}-1}^{\\varvec{r}}\\left({\\varvec{x}}_{\\varvec{i}+.}{\\varvec{x}}_{+\\varvec{i}}\\right)}{{\\varvec{N}}^{2}-\\sum\\:_{\\varvec{i}-1}^{\\varvec{r}}\\left({\\varvec{x}}_{\\varvec{i}+}.{\\varvec{x}}_{+\\varvec{i}}\\right)}$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e3\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003eK represents the Kappa coefficient, r denotes the total number of rows in a matrix, xii indicates the count of observations in row i and column i, while xi\u0026thinsp;+\u0026thinsp;and x\u0026thinsp;+\u0026thinsp;i signify the marginal totals for row i and column i, respectively, and N refers to the overall number of observations.\u003c/p\u003e\u003cp\u003eThe percentage of all reference pixels that are accurately classified (i.e., where the class assignment for the classification and the reference classification agree) is known as overall accuracy. The calculation involves dividing the entire number of reference pixels by the total number of correctly categorized pixels, which is the sum of the elements along the main diagonal (5).\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv id=\"Sec13\" class=\"Section3\"\u003e\u003ch2\u003e2.2.5. Regression analysis models\u003c/h2\u003e\u003cp\u003eOne method for analyzing the relationship between variables is through regression analysis. This research utilized spectral reflectance data from several bands (490 nm, 560 nm, 665 nm, 705 nm, 740 nm, 783 nm, 842 nm, 865 nm, 1610 nm, and 2190 nm) collected from ASD, along with calculated vegetation indices shown in Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e, as independent variables. The chlorophyll concentration at the corresponding locations was used as the dependent variable, and multiple regression models were applied to assess the data. The coefficient of determination (R2) between the mean spectral bands, vegetation indices, and Chlt concentration parameters was then calculated based on the estimated associations. In addition, the RMSE was used to assess the developed regression model. The optimal model was selected for the Chlt concentration estimation because it had the highest R2 and the lowest RMSE value (which is calculated as the difference between the field values observed and the projected values).\u003c/p\u003e\u003cp\u003eThe optimal model between actual chlorophyll concentration (\u0026micro;g/g. fw) and selected bands separately, as well as between chlorophyll concentration (\u0026micro;g/g. fw) and vegetation indices separately, was created using the stepwise multiple linear regression approach. as well as SPAD chlorophyll values was estimated, the stepwise method was calculated using the following formulas:\u003c/p\u003e\u003cp\u003e\u003cimg src=\"data:image/png;base64,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\" style=\"width: 439px; height: 28.7644px;\" width=\"439\" height=\"28.7644\"\u003e\u003c/p\u003e\u003cp\u003eWhere Y is the actual chlorophyll concentration (\u0026micro;g/g. fw) and predicted yield, and are vegetation indices or selected bands, a is the intercept and and are the regression coefficients.\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e"},{"header":"3. Results","content":"\u003cdiv id=\"Sec15\" class=\"Section2\"\u003e\u003ch2\u003e3.1. Statistical analysis of Chemical Chlorophyll Concentration\u003c/h2\u003e\u003cp\u003eThe concentrations of chlorophyll were measured from stages S1 to S3. To assess potato growth dynamics, the average chlorophyll values at each stage were calculated. The results are presented in Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e. The maximum chlorophyll concentration was recorded at S1, with a value of 627.2 (\u0026micro;g/g fw). This decreased to 523.2 (\u0026micro;g/g fw) at S2 and further declined to the lowest value of 495.8 (\u0026micro;g/g fw) at S3, indicating a gradual reduction in chlorophyll concentration.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec16\" class=\"Section2\"\u003e\u003ch2\u003e3.2. Statistics of SPAD Chlorophyll Values of Modeling Data\u003c/h2\u003e\u003cp\u003eThe SPAD chlorophyll values from stages S1 to S3 were measured, showing a consistent pattern in the chemical composition of chlorophyll across the three growth phases. To assess potato growth dynamics, the average chlorophyll values at each stage were calculated. These results are illustrated in Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e6\u003c/span\u003e. Chlorophyll readings declined progressively, starting from a maximum value of 55 at S1, decreasing to 48 at S2, and finally reaching 43 at S3.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec17\" class=\"Section2\"\u003e\u003ch2\u003e3.3. Multitemporal Analysis of the vegetation Indices for winter season for potato crop\u003c/h2\u003e\u003cp\u003eGenerally, the average spectral vegetative display values rise with crop development and never fall below the value of 0.8, indicating that the vegetation is not saturated. Figures\u0026nbsp;\u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e7\u003c/span\u003e, 8, and \u003cspan refid=\"Fig8\" class=\"InternalRef\"\u003e9\u003c/span\u003e illustrate the geographical spread that occurs in vegetative indices. The uncultivated portion, which is shown diagonally in the field's middle, is recognized by all markers. In contrast to the MCARI index, which displays values between 0.03 and 0.19 and understates the presence of vegetation, the NDVI and LCI indices display values that are consistent with the predominate vegetation. Visualizing the variability in crop yields is also made possible by the NDVI's spatial distribution. The data series obtained following the sprouting, growth, and maturity periods exhibited varying degrees of association with vegetative indicators when analyzed temporally. Based on the vegetative development progress, the NDVI value calculated from sentinel-2 images through the potato growing stages revealed that the first and fourth stages had the lowest values, 0.27 and 0.64, respectively, while the second and third stages had the highest values, 0.78 and 0.68, respectively. The other vegetation MCARI and LCI indices followed the NDVI trend.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec18\" class=\"Section2\"\u003e\u003ch2\u003e3.4. Regression models Analysis\u003c/h2\u003e\u003cdiv id=\"Sec19\" class=\"Section3\"\u003e\u003ch2\u003e3.4.1. Multiple Linear regression models between SVIs and chemical total chlorophyll\u003c/h2\u003e\u003cp\u003eMultiple regression models were employed to establish the relationship between three spectral vegetation indices (SVIs) derived from spectroradiometer (ASD) reflectance data, which served as independent variables, and the chemical total chlorophyll (Chlt) concentration (\u0026micro;g/gm. fw) at the same point, which served as the dependent variable, as shown in Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e. The results indicated that the model using all three VIS-NDVI, LCI, and MCARI at the third growth stage achieved the highest R\u0026sup2; value of 0.983. The next best model, which included two VIS (LCI and NDVI) at the second stage, obtained an R\u0026sup2; value of 0.978. The model with the lowest R\u0026sup2;, which was 0.92, was at the first stage and used two VIS (LCI and MCARI).\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\u003eMultiple Linear regression models between SVIs and chemical total chlorophyll (Chlt) concentration (\u0026micro;g/gm. fw) for winter potato crop\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"4\"\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\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGrowth Stage\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eModel\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eR2\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eRMSE\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eS1 (19-11-2022)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eY\u0026thinsp;=\u0026thinsp;52.9\u0026thinsp;+\u0026thinsp;814*LCI\u0026thinsp;+\u0026thinsp;423*MCARI\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.92\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e12.7\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eS2 (14-12-2022)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eY = -1818\u0026thinsp;+\u0026thinsp;1764*LCI\u0026thinsp;+\u0026thinsp;1608*NDVI\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.978\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e9.57\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eS3 (8-1-2023)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eY = -1052.3\u0026thinsp;+\u0026thinsp;1542.3*NDVI\u0026thinsp;+\u0026thinsp;406*LCI\u0026thinsp;+\u0026thinsp;127.8*MCARI\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.983\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e6.2\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec20\" class=\"Section3\"\u003e\u003ch2\u003e3.4.2. Multiple Linear regression models between SVIs and SPAD chlorophyll values\u003c/h2\u003e\u003cp\u003eVarious multiple regression models were employed to establish the connection between three vegetation indices, VIS obtained from a spectroradiometer device. (ASD) reflectance data as the independent variable and SPAD chlorophyll values for the same point as the dependent variable as showed in Table \u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e5\u003c/span\u003e, to find the best model to predict by Chlt depending on the high coefficient of determination (R2). the result showed that the model which one (LCI) VIS at the 2nd growth stage had a highest R2\u0026thinsp;=\u0026thinsp;0.966, the next model had a high R2\u0026thinsp;=\u0026thinsp;0.934 was at 3rd stage which used the same VIS (LCI) and the lowest model had R2\u0026thinsp;=\u0026thinsp;0.928 was at the 1st stage which used two VIS (LCI and MCARI).\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 5\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eMultiple Linear regression models between the SVIs and SPAD chlorophyll values for winter potato crop (2022\u0026ndash;2023)\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"4\"\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\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGrowth Stage\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eModel\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eR2\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eRMSE\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eS1 (19-11-2022)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eY\u0026thinsp;=\u0026thinsp;7.483\u0026thinsp;+\u0026thinsp;60.645*LCI\u0026thinsp;+\u0026thinsp;25.716*MCARI\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.928\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.826\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eS2 (14-12-2022)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eY\u0026thinsp;=\u0026thinsp;\u0026minus;\u0026thinsp;39.77\u0026thinsp;+\u0026thinsp;156.566*LCI\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.966\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.619\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eS3 (8-1-2023)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eY\u0026thinsp;=\u0026thinsp;11.178\u0026thinsp;+\u0026thinsp;68.445*LCI\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.934\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.643\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec21\" class=\"Section3\"\u003e\u003ch2\u003e3.4.3. Multiple Linear regression models between selected spectral bands and chemical total chlorophyll\u003c/h2\u003e\u003cp\u003eMultiple regression models were used to define the relationship between selected spectral bands derived from spectroradimeter device (ASD) reflectance data as the independent variable these bands were selected depending on the same bands which related with vegetation in sentenil-2 bands as shown in Table \u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e and the chemical total chlorophyll (Chlt) concentration (\u0026micro;g/gm. fw) For the same point being used as the dependent variable as shown in Table \u003cspan refid=\"Tab6\" class=\"InternalRef\"\u003e6\u003c/span\u003e, to find the best model to predict by Chlt depending on the high coefficient of determination (R2).the result showed that the model which used two bands ( B4 and B8 ) at the 2nd growth stage had a highest R2\u0026thinsp;=\u0026thinsp;0.986, the next model had a high R2\u0026thinsp;=\u0026thinsp;0.984 was at 3rd stage which used two bands (B6 and B8A) and the lowest model had R2\u0026thinsp;=\u0026thinsp;0.89 was at the 1st stage which used one band for correlation(B4).\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 6\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eMultiple Linear regression models between selected spectral bands and chemical total chlorophyll (Chlt) concentration (\u0026micro;g/gm. fw) for winter potato crop (2022\u0026ndash;2023) pivot 11-s\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"4\"\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\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGrowth Stage\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eModel\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eR2\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eRMSE\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eS1 (19-11-2022)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eY\u0026thinsp;=\u0026thinsp;461.46\u0026thinsp;+\u0026thinsp;3454.5*B4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.89\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e14.42\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eS2 (14-12-2022)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eY = -1423.8\u0026thinsp;+\u0026thinsp;4520.5*B4\u0026thinsp;+\u0026thinsp;2759.4*B8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.986\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e7.53\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eS3 (8-1-2023)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eY = -1073\u0026thinsp;+\u0026thinsp;1659.9*B6\u0026thinsp;+\u0026thinsp;1015*B8A\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.984\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e5.77\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec22\" class=\"Section3\"\u003e\u003ch2\u003e3.4.4. Multiple Linear regression models between selected spectral bands and SPAD chlorophyll values\u003c/h2\u003e\u003cp\u003eMultiple regression models were used to define the relationship between selected spectral bands derived from spectroradimeter device (ASD) reflectance data as the independent variable these bands were selected depending on the same bands which related with vegetation in sentenil-2 bands as shown in Table \u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e and the SPAD chlorophyll values for the same point as the dependent variable as shown in Table \u003cspan refid=\"Tab7\" class=\"InternalRef\"\u003e7\u003c/span\u003e, to find the best model to predict by Chlt depending on the high coefficient of determination (R2).the result showed that the model which used two bands ( B8 and B11 ) at the 2nd growth stage had a highest R2\u0026thinsp;=\u0026thinsp;0.974, the next model had a high R2\u0026thinsp;=\u0026thinsp;0.96 was at 3rd stage which used three bands (B3, B5 and B7) and the lowest model had R2\u0026thinsp;=\u0026thinsp;0.884 was at the 1st stage which used one band for correlation(B4).\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 7\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eMultiple Linear regression models between selected spectral bands and SPAD chlorophyll values for winter potato crop (2022\u0026ndash;2023) pivot 11-s\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"4\"\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\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGrowth Stage\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eModel\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eR2\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eRMSE\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eS1 (19-11-2022)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eY\u0026thinsp;=\u0026thinsp;37.957\u0026thinsp;+\u0026thinsp;232.405*B4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.884\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e1.05\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eS2 (14-12-2022)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eY = -71.66\u0026thinsp;+\u0026thinsp;137.54*B8\u0026thinsp;+\u0026thinsp;107.23*B11\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.974\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.542\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eS3 (8-1-2023)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eY\u0026thinsp;=\u0026thinsp;\u0026minus;\u0026thinsp;41.9\u0026thinsp;+\u0026thinsp;317.17*B3\u0026ndash;194.8*B5\u0026thinsp;+\u0026thinsp;142.4*B7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.96\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.52\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv id=\"Sec23\" class=\"Section2\"\u003e\u003ch2\u003e3.5. spatial distribution of potato crop in the study area\u003c/h2\u003e\u003cp\u003ecrop types are identified and distinguished within agricultural fields through crop discrimination byusing random forest classification methods. The underlying assumption of this claim stems from the finding that each crop has a unique spectrum signature. Compared to the summer, it is noted that a large percentage of the lands covered by center pivot irrigation systems are under cultivation throughout the winter. The reason for this discrepancy is that there is more water available in the winter. As shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig9\" class=\"InternalRef\"\u003e10\u003c/span\u003e, a classification study during the winter season (2022\u0026ndash;2023) revealed that spatial distribustion of several winter crops were grown in addition to horticultural crops: potatoes, wheat, sugar beet, and onions., we were able to extract the potato crop patches depicted in Fig.\u0026nbsp;11 using Arc GIs software. The evaluation of crop classification accuracy for the winter season of 2022\u0026ndash;2023 employed remotely sensed data, particularly Sentinel-2 imagery. The findings displayed in Table\u0026nbsp;\u003cspan refid=\"Tab8\" class=\"InternalRef\"\u003e8\u003c/span\u003e feature a confusion matrix that details the ground truth values for various crop types: Fallow Land, Grape, Onion, Palm Trees, Sugar Beet, Summer Potato, Winter Potato, and Wheat. Table\u0026nbsp;\u003cspan refid=\"Tab9\" class=\"InternalRef\"\u003e9\u003c/span\u003e showed the user and producer accuracy for each crop. User accuracy indicates how well the classification model identified each category, while producer accuracy demonstrates the effectiveness of the model in capturing the true crop distribution. while Table\u0026nbsp;\u003cspan refid=\"Tab10\" class=\"InternalRef\"\u003e10\u003c/span\u003e, the Kappa coefficient is presented, reflecting the level of agreement between the classification results and the ground truth data, with a reported value of 0.79, indicating strong concordance. The overall accuracy rate of the classification stands at 82.5%, which positively reflects the model's performance.\u003c/p\u003e\u003cp\u003eThese results are vital for precision agriculture, as they empower farmers to make informed decisions based on the dependability of crop classification outcomes. In the end, this fosters enhanced resource management and more precise crop yield forecasts.\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\u003econfusion matrix of crop classification for winter season 2022\u0026ndash;2023\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=\"char\" char=\".\" 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\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eClass\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eCitrus\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eFallow Land\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eGrape\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eOnion\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003ePalm trees\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003eSugar beet\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c8\"\u003e\u003cp\u003eSummer Potato\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c9\"\u003e\u003cp\u003eWinter Potato\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c10\"\u003e\u003cp\u003eWheat\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c11\"\u003e\u003cp\u003eTotal User\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eCitrus\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e20\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0\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\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e22\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eFallow Land\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e23\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\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e27\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eGrape\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e2\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\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eOnion\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0\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\u003e9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e12\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003ePalm trees\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0\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\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eSugar beet\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0\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\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e27\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e34\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eSummer Potato\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\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\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e7\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eWinter Potato\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0\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\u003e4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e33\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e40\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eWheat\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0\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\u003e3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e\u003cp\u003e12\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e15\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eTotal Producer\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e20\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e25\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e18\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e32\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e\u003cp\u003e9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e\u003cp\u003e38\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c10\"\u003e\u003cp\u003e13\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c11\"\u003e\u003cp\u003e160\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=\"Tab9\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 9\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eUser accuracy and Producer accuracy ground check point for winter season 2022\u0026ndash;2023\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"3\"\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\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eClass\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eUser Accuracy %\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eProducer Accuracy %\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eCitrus\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e90.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e100\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eFallow Land\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e85.185\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e92\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eGrape\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e100\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e100\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eOnion\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e75\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e50\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003ePalm trees\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e100\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e33.33\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eSugar beet\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e79.41\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e84.37\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eSummer Potato\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e71.42\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e55.55\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eWinter Potato\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e82.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e86.84\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eWheat\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e80\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e92.3\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=\"Tab10\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 10\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eKappa Coefficient and Overall Accuracy ground check point for winter season 2022\u0026ndash;2023\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"2\"\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\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eKappa Coefficient\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.79\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eOverall Accuracy (%)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e82.5%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec24\" class=\"Section2\"\u003e\u003ch2\u003e3.6. Mapping and visualization\u003c/h2\u003e\u003cp\u003e\u003cb\u003e3.6.1. Chemical total chlorophyll (Chlt) concentration (\u0026micro;g/gm. fw) for winter potato crop pivots in 6th of October Company (2022\u0026ndash;2023) based on band combinations\u003c/b\u003e\u003c/p\u003e\u003cp\u003eVarious band combinations were evaluated to produce a regression equation along with their corresponding R\u0026sup2; values to ascertain the relationship that most accurately estimates the spatial variability of Chlt concentration across the 6th of October Company, as shown in Table\u0026nbsp;\u003cspan refid=\"Tab6\" class=\"InternalRef\"\u003e6\u003c/span\u003e. The band combination represented by the equation (Y = -1423.8\u0026thinsp;+\u0026thinsp;4520.5*B4\u0026thinsp;+\u0026thinsp;2759.4*B8) achieved the highest R\u0026sup2; value, which is highlighted in bold in the table. Figure\u0026nbsp;\u003cspan refid=\"Fig10\" class=\"InternalRef\"\u003e12\u003c/span\u003e shows the spatial variations of Chlt concentration over the 6th of October Company, which were mapped using the emphasized regression equation. The major reason for selecting this model was its impressive coefficient of determination of 0.986.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003e\u003cb\u003e3.6.2. Total Chemical chlorophyll (TChl) concentration (\u0026micro;g/gm. fw) for winter potato crop pivots in 6th of October Company (2022\u0026ndash;2023) based on VIS\u003c/b\u003e\u003c/p\u003e\u003cp\u003eVarious VIS combinations were evaluated to develop a regression equation along with their respective R2 values to identify the relationship that most accurately represents the spatial variability of Chlt concentration across the 6th of October Company, as shown in Table \u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e. The band combination (Y = -1052.3\u0026thinsp;+\u0026thinsp;1542.3*NDVI\u0026thinsp;+\u0026thinsp;406*LCI\u0026thinsp;+\u0026thinsp;127.8*MCARI) resulted in the highest R2 value, emphasized in bold in the table. Figure\u0026nbsp;13 showed the spatial variations of Chlt concentration in the 6th of October Company, which were mapped using the regression equation. The primary reason for selecting this model was its superior coefficient of determination, which was 0.983.\u003c/p\u003e\u003cp\u003e\u003cb\u003e3.6.3. SPAD chlorophyll Values for winter potato crop pivots in 6th of October Company (2022\u0026ndash;2023) based on band combinations\u003c/b\u003e\u003c/p\u003e\u003cp\u003eVarious band combinations were examined to develop a regression equation along with their corresponding R\u0026sup2; values to determine the best relationship for estimating the spatial variability of SPAD chlorophyll values over the 6th of October Company, as shown in Table\u0026nbsp;\u003cspan refid=\"Tab7\" class=\"InternalRef\"\u003e7\u003c/span\u003e. The band combination (Y = -71.66\u0026thinsp;+\u0026thinsp;137.54*B8\u0026thinsp;+\u0026thinsp;107.23*B11) produced the highest R\u0026sup2; value, Fig.\u0026nbsp;14 showed the spatial variation of SPAD chlorophyll values over the 6th of October project, which were mapped using the emphasized regression equation. The primary reason for selecting this model was its exceptional coefficient of determination of 0.974.\u003c/p\u003e\u003cp\u003e\u003cb\u003e3.6.4. SPAD chlorophyll Values for winter potato crop pivots in 6th of October Company (2022\u0026ndash;2023) based on VIS\u003c/b\u003e\u003c/p\u003e\u003cp\u003eVarious visual information systems (VIS) were analyzed to create a regression equation along with their corresponding R\u0026sup2; values to determine the relationship that best estimates the spatial variability of SPAD chlorophyll values over the 6th of October Company, as shown in Table\u0026nbsp;\u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e5\u003c/span\u003e. The band combination represented by the equation (Y = -39.77\u0026thinsp;+\u0026thinsp;166.566*LCI) yielded the highest R\u0026sup2; value,. Figure\u0026nbsp;15 shows the spatial distribution of SPAD chlorophyll values across the 6th of October Company, which was mapped using the emphasized regression equation. The primary reason for selecting this model was its superior coefficient of determination, which stood at 0.966.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec25\" class=\"Section2\"\u003e\u003ch2\u003e3.7. Model Calibration\u003c/h2\u003e\u003cdiv id=\"Sec26\" class=\"Section3\"\u003e\u003ch2\u003e3.7.1. Calibration for chemical total chlorophyll (Chlt) concentration\u003c/h2\u003e\u003cp\u003eDatasets utilized for model validation included chemical total chlorophyll (Chlt) concentration measured in field (\u0026micro;g/gm. fw) versus predicted (Chlt). Root mean square error (RMSE) is a statistical index was used to assess the model\u0026rsquo;s correctness in Fig.\u0026nbsp;\u003cspan refid=\"Fig11\" class=\"InternalRef\"\u003e16\u003c/span\u003e. Results show that these models were successfully validated using the correlation coefficient between actual and predicted map of chemical total chlorophyll (Chlt) concentration (\u0026micro;g/gm. fw). R2 was 0.82 and RMSE was 43.62 for the best model derived from VIS indices shown in Table \u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e\u003c/p\u003e\u003cp\u003e(Y = -1052.3\u0026thinsp;+\u0026thinsp;1542.3*NDVI\u0026thinsp;+\u0026thinsp;406*LCI\u0026thinsp;+\u0026thinsp;127.8*MCARI).while R2 was 0.645 and RMSE was 58.26 for the best model derived from selected bands shown in Table \u003cspan refid=\"Tab6\" class=\"InternalRef\"\u003e6\u003c/span\u003e (Y = -1423.8\u0026thinsp;+\u0026thinsp;4520.5*B4\u0026thinsp;+\u0026thinsp;2759.4*B8).\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec27\" class=\"Section3\"\u003e\u003ch2\u003e3.7.2. Calibration for predicted chl using SPAD chlorophyll values\u003c/h2\u003e\u003cp\u003eDatasets utilized for model validation included SPAD chlorophyll values measured in field versus predicted (SPAD chlorophyll values). Root mean square error (RMSE) is a statistical index was used to assess the model\u0026rsquo;s correctness in Fig.\u0026nbsp;17A and B. The findings indicate that these models were effectively confirmed through the use of a simple regression model, and that this validation produced precise insights regarding the relationships between the SPAD chlorophyll values recorded in the field and the predicted Map (SPAD chlorophyll values).R2 was 0.689 and RMSE was 4.92 for the best model derived from VIS indices shown in Table \u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e5\u003c/span\u003e (Y\u0026thinsp;=\u0026thinsp;\u0026minus;\u0026thinsp;39.77\u0026thinsp;+\u0026thinsp;166.566*LCI). while R2 was 0.723 and RMSE was 2.26 for the best model derived from selected bands shown in Table \u003cspan refid=\"Tab7\" class=\"InternalRef\"\u003e7\u003c/span\u003e (Y = -71.66\u0026thinsp;+\u0026thinsp;137.54*B8\u0026thinsp;+\u0026thinsp;107.23*B11).\u003c/p\u003e\u003cp\u003e\u003cb\u003e3.8. Multiple Linear regression models between selected SVIs and chemical total chlorophyll to estimate potato crop yield\u003c/b\u003e\u003c/p\u003e\u003cp\u003eMultiple regression models was used to define the relationship between selected SVIs derived from spectroradimeter device (ASD) reflectance data as the independent variable these bands were selected depending on the same bands which related with vegetation in sentenil-2 bands as shown in Table\u003cspan refid=\"Tab11\" class=\"InternalRef\"\u003e11\u003c/span\u003e and the chemical total chlorophyll (Chlt) concentration (\u0026micro;g/gm. fw) for the same point as the dependent variable as shown in Table \u003cspan refid=\"Tab6\" class=\"InternalRef\"\u003e6\u003c/span\u003e, to find the best model to predict crop yield depending on the high coefficient of determination (R2).the result showed that the model which used CNDVI, CSAVI and total chlorophyl that was predicted model in section at the 2nd growth stage had a highest R2\u0026thinsp;=\u0026thinsp;0.847.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab11\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 11\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eMultiple Linear regression model between thevegetation indices, predicted total chlorophyll and actual productivity for second season (2022\u0026ndash;2023)\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"4\"\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\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGrowth Stage\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eModel\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eR2\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eRMSE\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eMature stage\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eY = -10.12\u0026thinsp;+\u0026thinsp;10.54*CNDVI\u0026thinsp;+\u0026thinsp;6.4*CSAVI \u0026minus;\u0026thinsp;0.205*Pre TChl\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.879\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e2.77\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec28\" class=\"Section3\"\u003e\u003ch2\u003e3.8.2. Crop yield map\u003c/h2\u003e\u003cp\u003eAccording to the crop yield model that was driven to estimate crop yield and the crop map spatial distribution of crop yield map was derived as showed in Fig.\u0026nbsp;18. This map was used to study the spatial variability of crop yield for each pixel. Figure\u0026nbsp;18 showed the expected distribution of potato crop yields based on data from Sentinel-2 satellite images. It uses a color scale to indicate different yield levels across the field green and blue represent highst yields, whereas cooler shades such as red and orange indicate lower yields. The forecasted yield varies from 13.4 tons per hectare to 104.8 tons per hectare across a 5 km area as showed in Fig.\u0026nbsp;18. Such crop yield maps provide essential insights for recognizing yield variability at a detailed, pixel-level scale. a method that utilizes data and remote sensing technology to enhance farming efficiency and sustainability. Precision agriculture focuses on managing the differences within a field to maximize crop yield and reducing resource consumption. The crop yield distribution as showed in the map allows farmers and agronomists to study the variability of crop yield in the whole study area of both high and low productivity.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec29\" class=\"Section3\"\u003e\u003ch2\u003e3.8.3. Validation of crop yield map\u003c/h2\u003e\u003cp\u003eThe datasets used for validating the model included both the actual yield and the predicted map. The root mean square error (RMSE) serves as a statistical metric to evaluate the accuracy of the model as illustrated in Fig.\u0026nbsp;19. The results indicate that the models were effectively validated through the relationship between actual and predicted values (R2), leading to accurate assessments of the correlations between the field-measured actual crop yield and the predicted map (predicted crop yield). The highest R2 value achieved was 0.821, with an RMSE of 4.64.\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e"},{"header":"4. Discussion","content":"\u003cp\u003eThe levels of Chlt often vary and fluctuate based on weather and climate conditions. During the winter months, the ample sunlight leads to an elevated Chlt value, as depicted in Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e. at the first stage of the growing season (19-11-2022), in addition to this stage have a strong and speed in the plant vigor versus the second stage and third stage (14-12-2022),(8-1-2023) There is reduced sunlight, leading to decreased photosynthesis and ultimately less Chlt.and maturing of plants increases catabolic processes in plants which reduces Chlt. SPAD chlorophyll values took the same trend of chemical chlorophyll at the three stages as shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e for the same reasons. This suggests that Chl-a is directly influenced by growth state and sunshine (Wagle et al. \u003cspan citationid=\"CR56\" class=\"CitationRef\"\u003e2019\u003c/span\u003e). The majority of research investigations (Wang, Chen, and Li \u003cspan citationid=\"CR57\" class=\"CitationRef\"\u003e2004\u003c/span\u003e; Yadava \u003cspan citationid=\"CR61\" class=\"CitationRef\"\u003e2022\u003c/span\u003e; Yamamoto et al. 2002)The relationship between [chl] and SPAD values is measured using linear regression. This work shows that foliar chlorophyll may be successfully recovered from high spatial resolution Sentinel-2 pictures. Retrieving leaf biochemical characteristics from canopy spectral reflectance is difficult because, in general, signal diffusion from the leaf to the canopy is low (Asner \u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e1998\u003c/span\u003e)and (Daughtry et al. \u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e2000\u003c/span\u003e). Tables\u0026nbsp;\u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e5\u003c/span\u003e, \u003cspan refid=\"Tab6\" class=\"InternalRef\"\u003e6\u003c/span\u003e demonstrate that foliar chlorophyll was estimated with reasonable accuracy (R2\u0026thinsp;=\u0026thinsp;0.983) using best fit spectra from ASD data and SPAD data (R2\u0026thinsp;=\u0026thinsp;0.966). The same trend was shown in Tables \u003cspan refid=\"Tab7\" class=\"InternalRef\"\u003e7\u003c/span\u003e and \u003cspan refid=\"Tab8\" class=\"InternalRef\"\u003e8\u003c/span\u003e to the relation between selected spectral bands from ASD and values of chlt and SPAD meter, where the highest R2) 0.986 and 0.974. We used the models with highest R2 ) which were extracted from data acquired from pivot 11-s at the winter season (2022\u0026ndash;2023) for potato crop as a case study to map and generalize it all over the 6th of October company for all other pivots in the same season which cultivated with the potato crop. According to (Psomiadis et al. \u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e2017\u003c/span\u003e), Their mathematical model revealed the most robust and linear relationships with the canopy concentration per unit area of carotenoids, chlorophyll a, and chlorophyll b. The significance of the red-edge bands of the MSI sensor on Sentinel-2 for assessing chlorophyll levels in potato crops is clarified.\u003c/p\u003e\u003cp\u003eMSI spectral bands recovering the canopy chlorophyll content are promising for thesa, which have a width of 15 nm and are centered at 705 nm and 740 nm. Due to its short revisit period (Theapproximately weekly) and high spatial resolution (20 m) provided by a pair of identical satellites, it can be utilized for more precise agriculture and various other applications (Clevers and Kooistra \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e2013\u003c/span\u003e). According to a previous study one of the most effective indices for evaluating canopy chlorophyll or nitrogen content is the CI red edge. The specific location of the spectral bands within the CI red edge is not particularly This was further explained in this study by analyzing which spectral bands should be utilized in the CI red edge to achieve the lowest coefficient of variation (CV) when estimating chlorophyll levels in potato crop canopies across three different growth seasons. The optimal results were obtained using a spectral band in the range of 695 nm to 725 nm in the denominator and a spectral band in the numerator of the CI red edge. Throughout the growth season, VIS achieved an impressive accuracy with R\u0026sup2; = 0.983; these findings are comparable to those of (Aklilu Tesfaye and Gessesse Awoke 2021). Our study's chlt and SPAD chlorophyll value prediction models performed well when validated using root mean square error (RMSE). The simple regression between actual and predicted chlt was used to validate the developed models. The accuracy of the predicted SPAD chlorophyll values was determined by comparing them with measured ones for potato crop samples, using the same validation approach. Ultimately, the results demonstrated that the models developed utilizing hyperspectral data from ASD and SPAD chlorophyll meters can be effectively used to map chlorophyll using Sentinel-2\u003c/p\u003e\u003cp\u003edata across a wide area, as illustrated in Figs.\u0026nbsp;\u003cspan refid=\"Fig10\" class=\"InternalRef\"\u003e12\u003c/span\u003e, 13, 14, and 15. These findings are consistent with Estimates of the chlorophyll content from hyperspectral reflectance correlated with the distribution of chlorophyll content in regions with varying applications of nitrogen fertilizer. According to (Lin et al. \u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e2023\u003c/span\u003e). this result implies that the suggested technique, which is Utilizing comprehensive index parameters, it provides high accuracy and can track the nutritional status of potatoes in real time. The table shows the model used to predict potato crop yield using multiple linear regression (MLR) for the 2022\u0026ndash;2023 growing season. The MLR model for the mature stage of the crop, incorporating CNDVI (Cumulative NDVI), CSAVI (Cumulative Soil Adjusted Vegetation Index), and Pre TChl (predicted total chlorophyll), achieved a high R\u0026sup2; value of 0.847 and a root mean square error (RMSE) of 3.93 (Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e). According to (Li et al. \u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e2021\u003c/span\u003e; Salvador et al. \u003cspan citationid=\"CR48\" class=\"CitationRef\"\u003e2020\u003c/span\u003e), the effectiveness of this model indicates that these vegetation indices, combined with pre-season estimates of chlorophyll, are valuable for assessing the crop's physiological status and predicting its productivity at maturity. In areas where soil interference can affect simpler vegetation indices like NDVI, the addition of CNDVI and CSAVI helps mitigate soil background effects, thereby enhancing the model's predictive capability (Ali et al. \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2021\u003c/span\u003e)(V\u0026eacute;lez, Mart\u0026iacute;nez-Pe\u0026ntilde;a, and Castrillo 2023; Van Wart et al. 2013; Xue and Su 2017).\u003c/p\u003e\u003cp\u003eConversely, the SLR model demonstrated a lower RMSE of 4.64 and an even higher R\u0026sup2; value of 0.821, relying solely on actual and expected productivity Fig.\u0026nbsp;19 This study emphasizes the ease of use and effectiveness of establishing a direct relationship between expected and actual yield, which can yield accurate estimates during the mature development stage (Desloires \u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e2024\u003c/span\u003e; Pham et al. \u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e2022\u003c/span\u003e). The higher R\u0026sup2; value suggests that this model can effectively describe the relationship between expected productivity and actual production, potentially offering a simpler and more efficient method for operational yield prediction. Spatial distribution of potato crop yield throughout the growing season can be observed from the CNDVI, CSAVI, and Predicted TChl value. The spatial distribution map (Fig.\u0026nbsp;17) illustrates the management zones where vegetation indices accurately predict yield, providing essential information for site-specific management and decision-making. The correlation between higher anticipated yields and areas with elevated CNDVI and CSAVI values showed the effectiveness of these indices in representing crop health and productivity across the field (Espe et al. \u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e2016\u003c/span\u003e). Additionally, the geographical output aligns with previous research indicating that remote sensing indices derived from high-resolution data, such as Sentinel-2, can generate precise and reliable yield projections by capturing crop variability at the field scale (Petersen \u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e2018\u003c/span\u003e). We note that when building the model on the training data, the R\u0026sup2; value was 0.986, indicating minimal variation between the studied fields. However, during model building, the model's performance declined significantly, with R\u0026sup2; = 0.645. This is likely due to heterogeneity in the climatic conditions surrounding the study area or differences in soil composition and physical and chemical properties that were not observed in the training data. Therefore, greater diversity in sampling, environmental conditions, and soil conditions should be considered in subsequent studies, which may further explain the significant drop in regression coefficient values ​​between the value inferred from the model building data and the data used to evaluate the validity of the results.\u003c/p\u003e"},{"header":"5. Conclusions","content":"\u003cp\u003eThis study determined the total chlorophyll content and crop yield of the potato crop using spectral reflectance. Vegetation indices were used to develop a model for estimating chlorophyll content at various growth phases and for mapping crop yield. It was found that the most accurate estimates of potato chlorophyll content and SPAD values were achieved with models based on the VIS and specific spectral bands. By utilizing hyperspectral data and Sentinel-2 images through a regression model, remote sensing (RS) and Geographic Information Systems (GIS) approaches were applied to estimate and map the chlorophyll concentration and SPAD chlorophyll values for the potato crop pivots of the 6th of October Company during the 2022\u0026ndash;2023 season. To evaluate the model's effectiveness, in-situ measurements of a specific fixed point were conducted, employing multiple regression analysis to develop the best-fit regression models, which yielded reliable and accurate results. The R-squared (R2) and root mean squared error (RMSE) were utilized to assess the analytical models' accuracy. This investigation concludes the effectiveness of various imaging technologies in establishing an affordable routine for monitoring children's health and potato crop yield. Different organizations may consider utilizing routine remote sensing observation of potato crop concentration as an alternative to field surveys for documenting and analyzing potato crop status.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eAuthor Contributions:\u0026nbsp;\u003c/strong\u003e. Conceptualization, Adel Ibraheim Selim ., Dalia Ahmed SamiNawar, Abdel-Aziz Belal and A. Ali; Data curation, Adel Ibraheim Selim . and D. Kucher, ; Formal analysis, Adel Ibraheim Selim . and Noureldin Laban; Funding acquisition, D. Kucher, ; Investigation, Abdallah Bardisi, Abdel-Aziz Belal \u0026nbsp;and A. Ali; Methodology, Abdallah Bardisi, Dalia Ahmed SamiNawar and A. Ali; Project administration, A. Ali; Software, Adel Ibraheim Selim, Abdel-Aziz Belal and Noureldin Laban; Supervision, Abdallah Bardisi, Dalia Ahmed SamiNawar and A. Ali; Validation, Noureldin Laban, D. Kucher, and A. Ali; Visualization,Abdel-Aziz Belal , \u0026nbsp;Adel Ibraheim Selim .; Writing – original draft, Y Rebouh, and A. Ali; Writing – review \u0026amp; editing,Abdel-Aziz Belal, \u0026nbsp;Abdallah Bardisi, Y Rebouh, and A. Ali.All authors have read and agreed to the published version of the manuscript.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData availability\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe data presented in this study are available upon request from the corresponding author.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003cstrong\u003e:\u0026nbsp;\u003c/strong\u003eThis research received no external funding.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eInstitutional Review Board Statement:\u0026nbsp;\u003c/strong\u003eNot applicable.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eInformed Consent Statement:\u0026nbsp;\u003c/strong\u003eNot applicable.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAcknowledgments:\u003c/strong\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThe authors would like to thank the National Authority of Remote Sensing and Space Science (NARSS), Cairo, Egypt, for supervising this work and for sample analysis. This research also \u0026nbsp;This publication has been supported by the RUDN University Scientific Projects Grant System, project № \u0026lt;202787-2-000\u0026gt;.. The authors would like to extend their sincere appreciation to the faculty of \u0026nbsp; Agriculture, at Zagazig university.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eAklilu Tesfaye, Andualem, and Berhan Gessesse Awoke. 2021. \u0026ldquo;Evaluation of the Saturation Property of Vegetation Indices Derived from Sentinel-2 in Mixed Crop-Forest Ecosystem.\u0026rdquo; Spatial Information Research 29(1):109\u0026ndash;21. doi: 10.1007/s41324-020-00339-5.\u003c/li\u003e\n\u003cli\u003eAli, Abdelraouf M., Igor Savin, Anton Poddubskiy, Mohamed Abouelghar, Nasser Saleh, Khaled Abutaleb, Mohammed El-shirbeny, and Peter Dokukin. 2021. \u0026ldquo;The Egyptian Journal of Remote Sensing and Space Sciences Integrated Method for Rice Cultivation Monitoring Using Sentinel-2 Data and Leaf Area Index Q.\u0026rdquo; The Egyptian Journal of Remote Sensing and Space Sciences 24(3):431\u0026ndash;41. doi: 10.1016/j.ejrs.2020.06.007.\u003c/li\u003e\n\u003cli\u003eAmira, M. S., A. A. Shalaby, W. M. Omran, and H. M. Elmedalaa. 2020. \u0026ldquo;Characteristices, Classification and Evaluation of Soils in the Area Southeast El-Sadat City, Menoufia Governorate, Egypt.\u0026rdquo; Menoufia Journal of Soil Science 5(9):257\u0026ndash;71. doi: 10.21608/mjss.2020.172392.\u003c/li\u003e\n\u003cli\u003eAshourloo, Davoud, Hamid Salehi Shahrabi, Mohsen Azadbakht, Amir Moeini Rad, Hossein Aghighi, and Soheil Radiom. 2020. \u0026ldquo;A Novel Method for Automatic Potato Mapping Using Time Series of Sentinel-2 Images.\u0026rdquo; Computers and Electronics in Agriculture 175(May):105583. doi: 10.1016/j.compag.2020.105583.\u003c/li\u003e\n\u003cli\u003eAsner, Gregory P. 1998. \u0026ldquo;Biophysical and Biochemical Sources of Variability in Canopy Reflectance.\u0026rdquo; Remote Sensing of Environment 64(3):234\u0026ndash;53. doi: 10.1016/S0034-4257(98)00014-5.\u003c/li\u003e\n\u003cli\u003eBelgiu, Mariana, and Lucian Drăgu. 2016. \u0026ldquo;Random Forest in Remote Sensing: A Review of Applications and Future Directions.\u0026rdquo; ISPRS Journal of Photogrammetry and Remote Sensing 114:24\u0026ndash;31. doi: 10.1016/j.isprsjprs.2016.01.011.\u003c/li\u003e\n\u003cli\u003eBoschetti, M., D. Stroppiana, C. Giardino, and P. A. Brivio. 2007. \u0026ldquo;Proximal and Remote Sensing Observations for Precision Farming Application , the Citimap Project : Experimental Design and Preliminary Data Analysis.\u0026rdquo; 3\u0026ndash;13.\u003c/li\u003e\n\u003cli\u003eClevers, J. G. P. W., and L. Kooistra. 2013. \u0026ldquo;Retrieving Canopy Chlorophyll Content Of Potato Crops Using Sentinel-2 Bands.\u0026rdquo; ESA Living Planet Symposium, Proceedings, 9-13 September 2013 ESA SP-722(September):1\u0026ndash;8.\u003c/li\u003e\n\u003cli\u003eClevers, Jan G. P. W., and Lammert Kooistra. 2012. \u0026ldquo;Using Hyperspectral Remote Sensing Data for Retrieving Canopy Chlorophyll and Nitrogen Content.\u0026rdquo; IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 5(2):574\u0026ndash;83. doi: 10.1109/JSTARS.2011.2176468.\u003c/li\u003e\n\u003cli\u003eCornelissen, J. H. C., S. Lavorel, E. Garnier, S. D\u0026iacute;az, N. Buchmann, D. E. Gurvich, P. B. Reich, H. Ter Steege, H. D. Morgan, M. G. A. Van Der Heijden, J. G. Pausas, and H. Poorter. 2003. \u0026ldquo;A Handbook of Protocols for Standardised and Easy Measurement of Plant Functional Traits Worldwide.\u0026rdquo; Australian Journal of Botany 51(4):335\u0026ndash;80. doi: 10.1071/BT02124.\u003c/li\u003e\n\u003cli\u003eCracknell, Arthur P., Costas A. Varotsos, Vladimir F. Krapivin, Jadunandan Dash, Paul J. Curran, and Giles M. Foody. 2009. Global Climatology and Ecodynamics: Anthropogenic Changes to Planet Earth.\u003c/li\u003e\n\u003cli\u003eCurran, P. J., W. R. Windham, and H. L. Gholz. 1995. \u0026ldquo;Exploring the Relationship between Reflectance Red Edge and Chlorophyll Concentration in Slash Pine Leaves.\u0026rdquo; Tree Physiology 15(3):203\u0026ndash;6. doi: 10.1093/treephys/15.3.203.\u003c/li\u003e\n\u003cli\u003eDaughtry, C. S. T., C. L. Walthall, M. S. Kim, E. Brown De Colstoun, and J. E. McMurtrey. 2000. \u0026ldquo;Estimating Corn Leaf Chlorophyll Concentration from Leaf and Canopy Reflectance.\u0026rdquo; Remote Sensing of Environment 74(2):229\u0026ndash;39. doi: 10.1016/S0034-4257(00)00113-9.\u003c/li\u003e\n\u003cli\u003eDesloires, Johann. 2024. \u0026ldquo;Integrating Limited Data Realities : Advanced Crop Monitoring and Parcel-Level Yield Estimation Using Multispectral Satellite Data and Machine Learning To Cite This Version : HAL Id : Tel-04606831 DE L \u0026rsquo; UNIVERSIT\u0026Eacute; DE MONTPELLIER Integrating Limited Data Realities : Advanced Crop Monitoring and Parcel-Level Yield Estimation Using Multispectral Satellite Data and Machine Learning Pr\u0026eacute;sent\u0026eacute;e Par Johann Desloires.\u0026rdquo;\u003c/li\u003e\n\u003cli\u003eDevaux, Andr\u0026eacute;, Jean Pierre Goffart, Peter Kromann, Jorge Andrade-Piedra, Vivian Polar, and Guy Hareau. 2021. \u0026ldquo;The Potato of the Future: Opportunities and Challenges in Sustainable Agri-Food Systems.\u0026rdquo; Potato Research 64(4):681\u0026ndash;720. doi: 10.1007/s11540-021-09501-4.\u003c/li\u003e\n\u003cli\u003eDrusch, M., U. Del Bello, S. Carlier, O. Colin, V. Fernandez, F. Gascon, B. Hoersch, C. Isola, P. Laberinti, P. Martimort, A. Meygret, F. Spoto, O. Sy, F. Marchese, and P. Bargellini. 2012. Sentinel-2: ESA\u0026rsquo;s Optical High-Resolution Mission for GMES Operational Services. Vol. 120.\u003c/li\u003e\n\u003cli\u003eEl-Hendawy, Salah, Salah Elsayed, Nasser Al-Suhaibani, Majed Alotaibi, Muhammad Usman Tahir, Muhammad Mubushar, Ahmed Attia, and Wael M. Hassan. 2021. \u0026ldquo;Use of Hyperspectral Reflectance Sensing for Assessing Growth and Chlorophyll Content of Spring Wheat Grown under Simulated Saline Field Conditions.\u0026rdquo; Plants 10(1):1\u0026ndash;26. doi: 10.3390/plants10010101.\u003c/li\u003e\n\u003cli\u003eEspe, Matthew B., Haishun Yang, Kenneth G. Cassman, Nicolas Guilpart, Hussain Sharifi, and Bruce A. Linquist. 2016. \u0026ldquo;Estimating Yield Potential in Temperate High-Yielding, Direct-Seeded US Rice Production Systems.\u0026rdquo; Field Crops Research 193:123\u0026ndash;32. doi: 10.1016/j.fcr.2016.04.003.\u003c/li\u003e\n\u003cli\u003eFeng, Yang, Fan Yamin, and Li Jianlong. 2010. \u0026ldquo;0 引言 .\u0026rdquo;\u003c/li\u003e\n\u003cli\u003eFood, World. 2020. World Food and Agriculture - Statistical Pocketbook 2019.\u003c/li\u003e\n\u003cli\u003eGilabert, Mar\u0026iacute;a Amparo, Soledad Gand\u0026iacute;a, and Joaqu\u0026iacute;n Meli\u0026aacute;. 1996. \u0026ldquo;Analyses of Spectral-Biophysical Relationships for a Corn Canopy.\u0026rdquo; Remote Sensing of Environment 55(1):11\u0026ndash;20. doi: 10.1016/0034-4257(95)00187-5.\u003c/li\u003e\n\u003cli\u003eGiletto, Claudia Marcela, Cecilia D\u0026iacute;az, Jorge Edgardo Ratt\u0026iacute;n, Hern\u0026aacute;n Eduardo Echeverr\u0026iacute;a, and Daniel Osmar Caldiz. 2010. \u0026ldquo;Green Index to Estimate Crop Nitrogen Status in Potato Processing Varieties.\u0026rdquo; Chilean Journal of Agricultural Research 70(1):142\u0026ndash;49. doi: 10.4067/s0718-58392010000100015.\u003c/li\u003e\n\u003cli\u003eGitelson, Anatoly A., Galina P. Keydan, and Mark N. Merzlyak. 2006. \u0026ldquo;Three-Band Model for Noninvasive Estimation of Chlorophyll, Carotenoids, and Anthocyanin Contents in Higher Plant Leaves.\u0026rdquo; Geophysical Research Letters 33(11):2\u0026ndash;6. doi: 10.1029/2006GL026457.\u003c/li\u003e\n\u003cli\u003eHerrmann, I., A. Karnieli, D. J. Bonfil, Y. Cohen, and V. Alchanatis. 2010. \u0026ldquo;SWIR-Based Spectral Indices for Assessing Nitrogen Content in Potato Fields.\u0026rdquo; International Journal of Remote Sensing 31(19):5127\u0026ndash;43. doi: 10.1080/01431160903283892.\u003c/li\u003e\n\u003cli\u003eIndices, Optimized Hyperspectral, Haibo Yang, Fei Li, Wei Wang, and Kang Yu. 2021. \u0026ldquo;Estimating Above-Ground Biomass of Potato Using Random.\u0026rdquo;\u003c/li\u003e\n\u003cli\u003eInoue, Yoshio, Martine Gu\u0026eacute;rif, Fr\u0026eacute;d\u0026eacute;ric Baret, Andrew Skidmore, Anatoly Gitelson, Martin Schlerf, Roshanak Darvishzadeh, and Albert Olioso. 2016. \u0026ldquo;Simple and Robust Methods for Remote Sensing of Canopy Chlorophyll Content: A Comparative Analysis of Hyperspectral Data for Different Types of Vegetation.\u0026rdquo; Plant Cell and Environment 39(12):2609\u0026ndash;23. doi: 10.1111/pce.12815.\u003c/li\u003e\n\u003cli\u003eIslam, AFM Tariqul, A. K. M. Saiful Islam, G. M. Tarekul Islam, Sujit Kumar Bala, Mashfiqus Salehin, Apurba Kanti Choudhury, M. Golam Mahboob, Nepal C. Dey, and Akbar Hossain. 2024. \u0026ldquo;Monitoring Wheat Area Using Sentinel-2 Imagery and In-Situ Spectroradiometer Data in Heterogeneous Field Conditions.\u0026rdquo; Discover Agriculture 2(1). doi: 10.1007/s44279-024-00069-4.\u003c/li\u003e\n\u003cli\u003eKamenova, Ilina, and Petar Dimitrov. 2021. \u0026ldquo;Evaluation of Sentinel-2 Vegetation Indices for Prediction of LAI, FAPAR and FCover of Winter Wheat in Bulgaria.\u0026rdquo; European Journal of Remote Sensing 54(sup1):89\u0026ndash;108. doi: 10.1080/22797254.2020.1839359.\u003c/li\u003e\n\u003cli\u003eKaplan, Gregoriy, Lior Fine, Victor Lukyanov, Nitzan Malachy, Josef Tanny, and Offer Rozenstein. 2023. \u0026ldquo;Using Sentinel-1 and Sentinel-2 Imagery for Estimating Cotton Crop Coefficient, Height, and Leaf Area Index.\u0026rdquo; Agricultural Water Management 276(July 2022):108056. doi: 10.1016/j.agwat.2022.108056.\u003c/li\u003e\n\u003cli\u003eLago, Carlos, Juan Carlos Sep\u0026uacute;lveda, Rogelio Barroso, F\u0026eacute;lix \u0026Oacute;scar Fern\u0026aacute;ndez, Francisco Maci\u0026aacute;, and Javier Lorenzo. 2011. \u0026ldquo;Sistema Para La Generaci\u0026oacute;n Autom\u0026aacute;tica de Mapas de Rendimiento. Aplicaci\u0026oacute;n En La Agricultura de Precisi\u0026oacute;n.\u0026rdquo; Idesia (Arica) 29(1):59\u0026ndash;69.\u003c/li\u003e\n\u003cli\u003eLi, Dan, Yuxin Miao, Sanjay K. Gupta, Carl J. Rosen, Fei Yuan, Chongyang Wang, Li Wang, and Yanbo Huang. 2021. \u0026ldquo;Improving Potato Yield Prediction by Combining Cultivar Information and Uav Remote Sensing Data Using Machine Learning.\u0026rdquo; Remote Sensing 13(16). doi: 10.3390/rs13163322.\u003c/li\u003e\n\u003cli\u003eLichtenthaler, Hartmut K. 1987. \u0026ldquo;Chlorophylls and Carotenoids: Pigments of Photosynthetic Biomembranes.\u0026rdquo; Methods in Enzymology 148(C):350\u0026ndash;82. doi: 10.1016/0076-6879(87)48036-1.\u003c/li\u003e\n\u003cli\u003eLin, Yongxin, Shuang Li, Shaoguang Duan, Yanran Ye, Bo Li, Guangcun Li, Dianqiu Lyv, Liping Jin, Chunsong Bian, and Jiangang Liu. 2023. \u0026ldquo;Methodological Evolution of Potato Yield Prediction: A Comprehensive Review.\u0026rdquo; Frontiers in Plant Science 14(July):1\u0026ndash;25. doi: 10.3389/fpls.2023.1214006.\u003c/li\u003e\n\u003cli\u003eLiu, H. Q., X. Q. Zhang, L. F. Chen, J. H. Fu, and H. C. Ma. 2022. \u0026ldquo;China \u0026rsquo; s Terrestrial UNVI Multidimensional.\u0026rdquo; 6(4):645\u0026ndash;55.\u003c/li\u003e\n\u003cli\u003eLizarazo, Ivan, Jorge Luis Rodriguez, Omar Cristancho, Felipe Olaya, Marlon Duarte, and Flavio Prieto. 2023. \u0026ldquo;Identification of Symptoms Related to Potato Verticillium Wilt from UAV-Based Multispectral Imagery Using an Ensemble of Gradient Boosting Machines.\u0026rdquo; Smart Agricultural Technology 3(July 2022):100138. doi: 10.1016/j.atech.2022.100138.\u003c/li\u003e\n\u003cli\u003eMadugundu, Rangaswamy, Khalid A. Al-Gaadi, El Kamil Tola, Salah El-Hendawy, and Samy A. Marey. 2023. \u0026ldquo;Mapping of Evapotranspiration and Determination of the Water Footprint of a Potato Crop Grown in Hyper-Arid Regions in Saudi Arabia.\u0026rdquo; Sustainability (Switzerland) 15(16). doi: 10.3390/su151612201.\u003c/li\u003e\n\u003cli\u003eMorshed, Sarowar, Falguny Barua, Asura Khanom, Fahima Lokman, and H. T. Zubair. 2025. \u0026ldquo;Smart Agricultural Technology Crop Yield Prediction Using Machine Learning : An Extensive and Systematic Literature Review.\u0026rdquo; Smart Agricultural Technology 10(September 2024):100718. doi: 10.1016/j.atech.2024.100718.\u003c/li\u003e\n\u003cli\u003eMukiibi, A., A. T. B. Machakaire, A. C. Franke, and J. M. Steyn. 2024. A Systematic Review of Vegetation Indices for Potato Growth Monitoring and Tuber Yield Prediction from Remote Sensing. Springer Netherlands.\u003c/li\u003e\n\u003cli\u003eNady, Dina, Abdelraouf M. Ali, and Ali G. Mahmoud. 2022. \u0026ldquo;The Egyptian Journal of Remote Sensing and Space Sciences Developing Spatial Model to Assess Agro-Ecological Zones for Sustainable Agriculture Development in MENA Region : Case Study Northern Western.\u0026rdquo; The Egyptian Journal of Remote Sensing and Space Sciences (xxxx):1\u0026ndash;11. doi: 10.1016/j.ejrs.2022.01.014.\u003c/li\u003e\n\u003cli\u003eOrtiz, Oscar, and Victor Mares. 2017. The Potato Genome.\u003c/li\u003e\n\u003cli\u003eOrynbaikyzy, Aiym, Ursula Gessner, and Christopher Conrad. 2022. \u0026ldquo;Spatial Transferability of Random Forest Models for Crop Type Classification Using Sentinel-1 and Sentinel-2.\u0026rdquo; Remote Sensing 14(6). doi: 10.3390/rs14061493.\u003c/li\u003e\n\u003cli\u003ePetersen, Lillian Kay. 2018. \u0026ldquo;Real-Time Prediction of Crop Yields from MODIS Relative Vegetation Health: A Continent-Wide Analysis of Africa.\u0026rdquo; Remote Sensing 10(11):1\u0026ndash;31. doi: 10.3390/rs10111726.\u003c/li\u003e\n\u003cli\u003ePham, Hoa Thi, Joseph Awange, Michael Kuhn, Binh Van Nguyen, and Luyen K. Bui. 2022. \u0026ldquo;Enhancing Crop Yield Prediction Utilizing Machine Learning on Satellite-Based Vegetation Health Indices.\u0026rdquo; Sensors 22(3):1\u0026ndash;19. doi: 10.3390/s22030719.\u003c/li\u003e\n\u003cli\u003ePsomiadis, Emmanouil, Nicholas Dercas, Nicolas R. Dalezios, and Nicos V. Spiropoulos. 2017. \u0026ldquo;Evaluation and Cross-Comparison of Vegetation Indices for Crop Monitoring from Sentinel-2 and Worldview-2 Images.\u0026rdquo; (November):79. doi: 10.1117/12.2278217.\u003c/li\u003e\n\u003cli\u003ePu, Ruiliang, Peng Gong, and Qian Yu. 2008. \u0026ldquo;Comparative Analysis of EO-1 ALI and Hyperion, and Landsat ETM+ Data for Mapping Forest Crown Closure and Leaf Area Index.\u0026rdquo; Sensors 8(6):3744\u0026ndash;66. doi: 10.3390/s8063744.\u003c/li\u003e\n\u003cli\u003eRam\u0026iacute;rez, D. A., W. Yactayo, R. Guti\u0026eacute;rrez, V. Mares, F. De Mendiburu, A. Posadas, and R. Quiroz. 2014. \u0026ldquo;Chlorophyll Concentration in Leaves Is an Indicator of Potato Tuber Yield in Water-Shortage Conditions.\u0026rdquo; Scientia Horticulturae 168(February):202\u0026ndash;9. doi: 10.1016/j.scienta.2014.01.036.\u003c/li\u003e\n\u003cli\u003eSafi, Abdur Rahim, Poolad Karimi, Marloes Mul, Abebe Chukalla, and Charlotte de Fraiture. 2022. \u0026ldquo;Translating Open-Source Remote Sensing Data to Crop Water Productivity Improvement Actions.\u0026rdquo; Agricultural Water Management 261(March):107373. doi: 10.1016/j.agwat.2021.107373.\u003c/li\u003e\n\u003cli\u003eSalvador, Pablo, Diego G\u0026oacute;mez, Julia Sanz, and Jos\u0026eacute; Luis Casanova. 2020. \u0026ldquo;Estimation of Potato Yield Using Satellite Data at a Municipal Level: A Machine Learning Approach.\u0026rdquo; ISPRS International Journal of Geo-Information 9(6). doi: 10.3390/ijgi9060343.\u003c/li\u003e\n\u003cli\u003eSinha, Priyakant, Andrew Robson, Derek Schneider, Talip Kilic, Harriet Kasidi Mugera, John Ilukor, and Jimmy Moses Tindamanyire. 2020. \u0026ldquo;The Potential of In-Situ Hyperspectral Remote Sensing for Differentiating 12 Banana Genotypes Grown in Uganda.\u0026rdquo; ISPRS Journal of Photogrammetry and Remote Sensing 167(July):85\u0026ndash;103. doi: 10.1016/j.isprsjprs.2020.06.023.\u003c/li\u003e\n\u003cli\u003eSishodia, Rajendra P., Ram L. Ray, and Sudhir K. Singh. 2020. \u0026ldquo;Applications of Remote Sensing in Precision Agriculture: A Review.\u0026rdquo; Remote Sensing 12(19):1\u0026ndash;31. doi: 10.3390/rs12193136.\u003c/li\u003e\n\u003cli\u003eSong, Zhenghua, Yanfu Liu, Junru Yu, Yiming Guo, Danyao Jiang, Yu Zhang, Zheng Guo, and Qingrui Chang. 2024. \u0026ldquo;Estimation of Chlorophyll Content in Apple Leaves Infected with Mosaic Disease by Combining Spectral and Textural Information Using Hyperspectral Images.\u0026rdquo; Remote Sensing 16(12). doi: 10.3390/rs16122190.\u003c/li\u003e\n\u003cli\u003eSumanta, Nayek, Choudhury Imranul Haque, Jaishee Nishika, and Roy Suprakash. 2014. \u0026ldquo;Spectrophotometric Analysis of Chlorophylls and Carotenoids from Commonly Grown Fern Species by Using Various Extracting Solvents.\u0026rdquo; Research Journal of Chemical Sciences Res. J. Chem. Sci 4(9):2231\u0026ndash;2606.\u003c/li\u003e\n\u003cli\u003eUddling, J., J. Gelang-Alfredsson, K. Piikki, and H. Pleijel. 2007. \u0026ldquo;Evaluating the Relationship between Leaf Chlorophyll Concentration and SPAD-502 Chlorophyll Meter Readings.\u0026rdquo; Photosynthesis Research 91(1):37\u0026ndash;46. doi: 10.1007/s11120-006-9077-5.\u003c/li\u003e\n\u003cli\u003eV\u0026eacute;lez, Sergio, Raquel Mart\u0026iacute;nez-Pe\u0026ntilde;a, and David Castrillo. 2023. \u0026ldquo;Beyond Vegetation: A Review Unveiling Additional Insights into Agriculture and Forestry through the Application of Vegetation Indices.\u0026rdquo; J 6(3):421\u0026ndash;36. doi: 10.3390/j6030028.\u003c/li\u003e\n\u003cli\u003eVesali, F., M. Omid, H. Mobli, and A. Kaleita. 2017. \u0026ldquo;Feasibility of Using Smart Phones to Estimate Chlorophyll Content in Corn Plants.\u0026rdquo; Photosynthetica 55(4):603\u0026ndash;10. doi: 10.1007/s11099-016-0677-9.\u003c/li\u003e\n\u003cli\u003eWagle, N., R. Pote, R. Shahi, S. Lamsal, S. Thapa, and T. D. Acharya. 2019. \u0026ldquo;Estimating and Mapping Chlorophyll-A Concentration of Phewa Lake of Kaski District Using Landsat Imagery.\u0026rdquo; ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 4(5/W2):127\u0026ndash;32. doi: 10.5194/isprs-annals-IV-5-W2-127-2019.\u003c/li\u003e\n\u003cli\u003eWang, Qibing, Jianjun Chen, and Yuncong Li. 2004. \u0026ldquo;Nondestructive and Rapid Estimation of Leaf Chlorophyll and Nitrogen Status of Peace Lily Using a Chlorophyll Meter.\u0026rdquo; Journal of Plant Nutrition 27(3):557\u0026ndash;69. doi: 10.1081/PLN-120028878.\u003c/li\u003e\n\u003cli\u003eVan Wart, Justin, K. Christian Kersebaum, Shaobing Peng, Maribeth Milner, and Kenneth G. Cassman. 2013. \u0026ldquo;Estimating Crop Yield Potential at Regional to National Scales.\u0026rdquo; Field Crops Research 143:34\u0026ndash;43. doi: 10.1016/j.fcr.2012.11.018.\u003c/li\u003e\n\u003cli\u003eXu, Xingang, Guijun Yang, Xiaodong Yang, Zhenhai Li, Haikuan Feng, Bo Xu, and Xiaoqing Zhao. 2018. \u0026ldquo;Monitoring Ratio of Carbon to Nitrogen (C/N) in Wheat and Barley Leaves by Using Spectral Slope Features with Branch-and-Bound Algorithm.\u0026rdquo; Scientific Reports 8(1):1\u0026ndash;15. doi: 10.1038/s41598-018-28351-8.\u003c/li\u003e\n\u003cli\u003eXue, Jinru, and Baofeng Su. 2017. \u0026ldquo;Significant Remote Sensing Vegetation Indices: A Review of Developments and Applications.\u0026rdquo; Journal of Sensors 2017. doi: 10.1155/2017/1353691.\u003c/li\u003e\n\u003cli\u003eYadava, Umedi L. 2022. \u0026ldquo;A Rapid and Nondestructive Method to Determine Chlorophyll in Intact Leaves.\u0026rdquo;.\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Chlorophyll, VIs, Sentinel-2, AI, RS, Potato crop yield","lastPublishedDoi":"10.21203/rs.3.rs-6790082/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6790082/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eLeaf Chlorophyll Concentration (LCC) is a vital biochemical parameter for assessing plant status due to its essential role in physiological activities, photosynthesis, and overall plant health. In order to illustrate the development of potato crops and offer advice for precision agriculture management, research was conducted on non-invasive testing methods for chlorophyll levels and methods for mapping crop yield in potatoes. The objective of this study is to examine the spatial distribution of chlorophyll content and yield of potato crops using Sentinel 2 data, SPAD chlorophyll measurements, and laboratory analyses. Artificial intelligence (AI) using the Random forest (RF) classification method was used to study the spatial distribution of crop type and discriminate the potato crop. The overall accuracy and kappa statistics for the spatial distribution derived from Sentinel 2 satellite imagery for potato crops in the study area were 0.79 and 82.5%, respectively. Stepwise Multilinear regression model (SWMLR) between Spectral vegetation indices (Normalized Difference Vegetation Indexed NDVI, Modified Chlorophyll Absorption Ratio Index (MCARI), Leaf Chlorophyll Index (LCI), derived from spectral vegetation indices (SVI), (SPAD chlorophyll and chemical analysis through potato crop growth stages (S1, S2 and S3) were correlated to estimate chlorophyll content and crop yield map. The model accuracy between vegetation indices and Total chlorophyll showed that models based on VIS and selected spectral bands derived from ASD to predict total chlorophyll(chlt) and SPAD chlorophyll values achieved a high coefficient of determination (R\u003csup\u003e2\u003c/sup\u003e) at the different growth stages, which were 0.983 and 0.986. The produced map for the potato crop, total chlorophyll derived from Sentinel 2, showed high accuracy at 0.966 and 0.974 based on SPAD, VIS, and selected spectral bands, respectively. The study showed that the estimation and mapping of Chlt and SPAD values of a potato crop under an irrigation system pivot can be done with the help of RS and AI techniques.\u003c/p\u003e","manuscriptTitle":"Comparative Analysis Between Sentinel-2 And Proximal Sensors to Study the Spatial Distribution of Chlorophyll Content and Potato Crop Yield Using Artificial Intelligence: A Case Study of Salheia, Egypt","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-14 09:58:07","doi":"10.21203/rs.3.rs-6790082/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-08T06:12:23+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-02T00:07:24+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-31T20:34:57+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"155515993910115384728561431815458870650","date":"2026-03-23T18:33:38+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"182101934904581358684399890257904343126","date":"2026-03-23T18:08:16+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"165985996336160835914149248334846081294","date":"2026-03-23T02:17:47+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"16540306607382274494393596232228753610","date":"2026-03-21T15:08:20+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"338709508351598612004369054783569056369","date":"2025-08-26T16:40:33+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"60132184690927557485408998195063652134","date":"2025-08-09T14:09:53+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-08-07T11:58:02+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-08-07T11:43:58+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-06-12T12:51:43+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-06-11T14:51:58+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-05-31T09:34:25+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"30052f32-39c9-42ac-acc2-93378f5ab401","owner":[],"postedDate":"August 14th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[{"id":53012256,"name":"Biological sciences/Ecology/Agri ecology"},{"id":53012257,"name":"Biological sciences/Plant sciences/Plant ecology"}],"tags":[],"updatedAt":"2026-04-08T06:25:00+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-14 09:58:07","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6790082","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6790082","identity":"rs-6790082","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}