Application of XGBOOST in Disentangling the Fingerprints of Global Warming and Interdecadal Pacific Oscillation on Seasonal Precipitation Trends in Ohio

Application of XGBOOST in Disentangling the Fingerprints of Global Warming and Interdecadal Pacific Oscillation on Seasonal Precipitation Trends in Ohio | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Application of XGBOOST in Disentangling the Fingerprints of Global Warming and Interdecadal Pacific Oscillation on Seasonal Precipitation Trends in Ohio Caitlin Wegener, Chibuike Chiedozie Ibebuchi This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5574842/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Global warming is a significant challenge of the 21st century, driving notable changes in weather patterns. On the other hand, the Interdecadal Pacific Oscillation (IPO) is a remarkable climatic mode of variability that impacts interdecadal climate patterns and the rate of global warming. This study introduces the extreme gradient boosting (XGBOOST) feature important metric, to disentangle and rank the fingerprints of global warming and IPO on the seasonal precipitation trends in Ohio, United States, a region characterized by variable weather. Using monthly precipitation data from 55 weather stations spanning 1960–2023, seasonal average trends for boreal winter, spring, summer, and autumn were analyzed using Theil-Sen’s Slope method, and statistical significance was tested at the 95% confidence level. Results indicate a significant increase in precipitation during winter (0.15 mm/decade) and summer (0.13 mm/decade), while no statistically significant changes were observed for spring and autumn. Correlation analysis revealed that 56.4% of the stations showed statistically significant positive correlations between global warming signals and increased winter precipitation. In comparison, 40% of the stations negatively correlated with the IPO during winter. Therefore, global warming and the negative IPO phase are associated with the observed increase in winter precipitation in most of the analyzed stations. In 60% of the stations, including stations impacted by the lake-effect snow, the XGBOOST model showed that the fingerprint of global warming ranked higher than the IPO. This indicates that global warming has a stronger association with the observed positive winter precipitation trend in most stations, and the IPO's net effect is limited to a smaller number of stations (i.e., 40%). These findings highlight that Ohio’s winters are becoming wetter with global warming remarkably contributing to it. precipitation Midwest United States winter extreme gradient boosting fingerprint global warming climate signals Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 1. Introduction Rising global temperatures represent one of the challenges the world is facing (Karl and Trenberth, 2003; Pfeiffer and Hepburn, 2016; Tcvetkov, 2021). The increase in temperature has far-reaching consequences, including altered weather patterns (Hansen et al., 2014), a rise in the frequency and intensity of extreme weather events (Haarsma et al., 2013; Seneviratne et al., 2021), disruptions to ecological balance (Bandh et al., 2021), and substantial economic disasters (Frame et al., 2021; Cruz and Rossi-Hansberg, 2024), among other impacts (Palinkas and Wong, 2020; Saini and Bhatt, 2020; Corpuz, 2024). In the United States, for example, the increase in heatwaves exacerbated by global warming contributes to high mortality rates (Habeeb et al., 2015; Casey et al., 2023). Changing rainfall patterns, leading to an increase in the frequency and severity of drought cycles, have resulted in devastating wildfires (Hanson and Weltzin, 2000; Goss et al., 2020), decreased crop yields (Schlenker and Roberts, 2009), and heavy rainfall and flooding with severe impacts on livelihoods (Swain et al., 2020). Given the recent changes in precipitation patterns and extreme weather events across the heterogeneous climates of the United States (Hoerling et al., 2016; Kunkel et al., 2020), there is a critical need to monitor regional precipitation changes and assess the role of global warming. The rise in global temperatures has been linked to anthropogenic emissions of greenhouse gases (Kumar, 2018; Olivier and Peters, 2020). Since the mid-20th century, annual carbon dioxide emissions from fossil fuels have increased from approximately 11 billion metric tons in the 1960s to an estimated 36.8 billion metric tons in 2023, marking a 1.1% rise from 2022 and setting a record high (Friedlingstein et al. 2023). Studies have linked global warming to more intense precipitations in certain regions (Lehmann et al., 2015; Myhre et al., 2019; Doan et al., 2022) and drought in some other regions (Dai, 2010; Trenberth et al., 2013). As surface temperatures rise due to global warming, the atmosphere's capacity to hold water vapor increases (Richter and Xie, 2008; Trenberth, 2011; Durack et al., 2012; Allan et al., 2020); but rising temperatures also increase surface drying and decrease the lapse rate (Colman and Power, 2010; Colman and Soden, 2021). Therefore, global precipitation patterns are likely to change with global warming. (Stephens and Ellis, 2008; Lambert et al., 2008). Precipitation changes are reported to occur at different rates in different areas across the globe due to topography, the climate of the region, and other internal climatic factors (Held and Soden, 2000; Torma and Giorgi, 2020). One such internal climatic factor that significantly impacts the rate of climate change-driven precipitation trends around the globe is the interdecadal Pacific Oscillation (IPO). The IPO is a long-term ocean-atmosphere phenomenon characterized by sea surface temperature (SST) variations across the Pacific basin, with phases lasting 20 to 30 years (Dong and Dai, 2015; Henley et al., 2015; Meehl, 2016; Henley, 2017). During its positive phase, the central and eastern tropical Pacific experience warmer SSTs, while the western Pacific and mid-latitudes are cooler; the negative phase exhibits the opposite pattern. A negative IPO phase can slow global surface temperature increases by promoting heat uptake in the deeper ocean layers; conversely, a positive phase can accelerate warming by enhancing surface heat retention (Kosaka and Xie, 2016). Reconstructions of the IPO using various proxies and instrumental records confirm its occurrence over the past two centuries, with phase shifts linked to significant climate events; these phases exhibit a global impact on climate variability (Vance et al., 2020). Moreover, the IPO contributes to spatially varied precipitation patterns across the globe, with more spatially heterogeneous impacts across the United States (Dong and Dai, 2015). In this study, we focus on introducing machine learning, specifically, the extreme gradient boosting (XGBOOST) feature important metric (Cherif and Kortebi, 2019; Ibebuchi et al., 2024), to disentangle the fingerprints of global warming and the IPO on seasonal precipitation trends in Ohio, United States, a region characterized by variable weather due to its geographic location and vulnerable to climate change (Antosch, 2023). We focused on seasonal precipitation trends, as they are most relevant for guiding individual farmers in Ohio who are currently negatively impacted by global farming (Antosch, 2023), in selecting crops and planning planting cycles. Numerous studies have examined precipitation trends across the United States under global warming (Easterling et al., 2017; Karmalkar and Bradley, 2017; Bartels et al., 2020). These studies consistently show that historical precipitation patterns and events are undergoing significant changes and are projected to shift further under future climate change scenarios (Liu et al., 2012; Wu, 2015). However, due to the spatial heterogeneity and seasonality of precipitation changes, our study is the first to specifically analyze seasonal precipitation trends in Ohio while disentangling the fingerprints of global warming and the IPO. We introduce a novel methodology, to effectively model nonlinear relationships and handle collinearity between climate signals in quantifying the distinct contributions of global warming and internal climate variability, such as the IPO, to the observed seasonal precipitation trends. Additionally, we leverage station observations to provide detailed seasonal precipitation trends in Ohio at a 95% confidence level. This research is critical for improving climate modeling efforts, enhancing extreme weather preparedness, and informing climate change mitigation strategies in Ohio. 2. Data and Methodology 2 .1 Data All station precipitation data utilized in this study were sourced from the National Oceanic and Atmospheric Administration (NOAA) and are accessible at https://www.ncei.noaa.gov/cdo-web . Stations were selected based on the completeness of their monthly precipitation records from 1960 to 2023; only those with at least 95% data completeness during this period were included. The precipitation measurements represent the liquid water equivalent, meaning that for example, snowfall is measured as the depth of water produced upon melting. This selection criterion resulted in 55 stations across Ohio being incorporated into our study (Fig. 1 ). Additionally, we obtained the Global Mean Land/Ocean Temperature Index from NOAA's dataset, available at https://psl.noaa.gov/data/climateindices/list/ , to serve as a proxy for global warming. The climate of Ohio is variable, experiencing all four distinct seasons: summer, winter, autumn, and spring. Temperatures range from freezing and below during the winter months (December, January, February) to warm and hot during the summer (June, July, August). Ohio’s climate is classified as humid continental (Pierce, 1959), characterized by pronounced seasonal changes, including diverse precipitation types and significant temperature variations across the seasons. Figure 2 shows that the seasonally averaged precipitation in Ohio is highest in summer and lowest in winter. This is primarily due to increased atmospheric moisture and convective activity during the summer months, which enhances rainfall from thunderstorms (Agel et al., 2019), while the colder winter months limit moisture availability and precipitation rates. Ohio’s climate patterns are also shaped by the interaction of warm, moist air masses from the Gulf of Mexico and cold air masses from Canada, creating dynamic weather conditions (Coleman and Rogers, 2003). Ohio's proximity to Lake Erie results in increased lake-effect snow, particularly in the northern regions, during winter (Suriano and Guercio, 2024). Additionally, Ohio is influenced by larger climatic phenomena such as El Niño and La Niña, which typically bring decreased and increased precipitation, respectively, depending on the phase (Rogers and Coleman, 2004; Ritzi et al., 2021). 2.2 Method Figure 1 shows that the selected 55 stations in Ohio cover the geographical regions across the state boundary. We organized the data by the four meteorological seasons and calculated the average seasonal precipitation per year. December-February (DJF) represents winter; March-May (MAM) represents spring; June-August (JJA) represents summer, and September-November (SON) represents autumn. By averaging the monthly precipitation, we focus on the seasonal changes. We calculated the trends of the seasonal rainfall averages from 1960 to 2023 using Theil-Sen's slope method (Agarwal et al., 2021). The Theil-Sen's slope method is robust and does not rely on assumptions about the data's statistical distribution. The seasonally averaged precipitation trends were tested for statistical significance at a 95% confidence level using the Mann-Kendall test (Hamed and Rao, 1998). We examined the relationship between global warming, IPO, and the observed trends using the Kendall correlation (Croux and Dehon, 2010) between the seasonally averaged global warming signal data, IPO index, and the seasonally averaged precipitation data from 1960 to 2023. In the next step, we applied the XGBOOST algorithm to disentangle and quantify the contributions of key climatic drivers, i.e. global warming signal and the IPO, to seasonal precipitation trends at each station in Fig. 1 . XGBOOST is a machine-learning algorithm based on gradient-boosted decision trees (Chen and Guestrin, 2016). XGBOOST is particularly well-suited for handling interactions between explanatory variables, including nonlinear relationships and potential collinearity. The algorithm’s feature importance metric is innovatively utilized in this study to evaluate the relative contribution of each climatic driver to the variability in seasonal precipitation, providing a robust framework for modeling nonlinear interactions and handling collinearity in ranking the fingerprints global warming signal and the IPO. In our study, XGBOOST was trained using global warming and IPO as input drivers and seasonal precipitation data as the target variable. The importance score for each climatic driver was calculated and scaled to reflect its percentage contribution to the variability in seasonal precipitation. Mathematically, the importance \(\:{I}_{j}\) for the climate driver \(\:j\) is defined in Eq. ( 1 ) $$\:{I}_{j}=\frac{\sum\:k\in\:{T}_{j\:}\:{G}_{k}}{\sum\:K\in\:T{G}_{k}}\times\:100$$ 1 Where \(\:{T}_{j\:}\) represents the trees where driver j is used; \(\:{G}_{k}\) is the gain from the split at node k , and T is the set of all trees in the model. By normalizing \(\:{I}_{j}\) we derived the percentage contribution of each climate driver to precipitation variability. This approach is valuable and innovative in our study because precipitation trends in Ohio are shaped by overlapping climate signals that vary across spatial and temporal scales. Traditional regression methods may fail to adequately disentangle the effects of interdependent drivers like global warming and IPO. XGBOOST effectively addresses this by iteratively isolating the contributions of each driver, even when interactions and dependencies exist. 3. Results and Discussion Figure 3 shows the trends in seasonal precipitation averages across the 55 selected stations. For DJF (top left map, Fig. 3 ), out of the 55 total stations, 41 stations representing 74.6 percent of the total stations across Ohio showed a positive trend. The stations that showed a positive trend during the winter season were fairly spread out around Ohio and were not localized to a single area (Fig. 3 ). During JJA, (top right map, Fig. 3 ) 21 out of the 55 stations (i.e., 38.2% of the total stations) showed a positive trend, and 34 stations (i.e., 61.8% of the total stations) during JJA showed no change. The positive trends during the JJA are focused on the central to some northern portions of the state (Fig. 3 ). During SON (bottom left map) 4 out of the 55 stations (i.e., 7.3% percent of the total stations) showed a positive trend in precipitation in northeast Ohio, and 51 of the stations (i.e., 92.7% of the total stations) showed no change (Fig. 3 ). Finally, during MAM, (bottom right map, Fig. 3 ), 9 out of the 55 stations (16.4% of the total stations) in the western side and northeast of the state showed a positive trend in precipitation while 46 stations (83.6% of the total stations) showed no change. None of the stations within any season showed a negative trend in seasonally averaged precipitation consistent with Bartels et al. (2020) on the increasing trend of precipitation days in the Midwest United States. During the winter season, the number of stations showing a positive trend in seasonal precipitation was greater than the number that showed no change (i.e., 25.4% of the stations). This implies that on the spatial scale, the winter season is experiencing a remarkable increase in average seasonal precipitation compared to the other seasons which show no change in most of the analyzed stations (Fig. 3 ). Figure 4 shows the trends in seasonal precipitation averaged across the 55 stations in Ohio. During winter, (top left, Fig. 4 ), there is a very definable statistically significant increase in seasonal precipitation by 0.15 mm/decade; during JJA, there was also a statistically significant increase by 0.13 mm/decade, although less than the winter increase. SON and MAM did not show statistically significant changes at a 95% confidence level. Therefore, during our analysis period the fall and spring seasons experienced no change in average seasonal precipitation trends across Ohio (Figs. 3 and 4 ). Our results on precipitation increases in Ohio are consistent with Easterling et al. (2017) - that since 1901, annual precipitation has increased in most of the Midwest and Northeast regions of the United States (Huang et al., 2017). In terms of the seasonality of the precipitation changes, Pathak et al. (2017) reported an increase in summertime precipitation in the Midwest. Further, an increase in summertime precipitation in the United States, including the Midwest, has been linked to the westward extension of the Bermuda High and the development of cut-off low-pressure systems, which facilitate the transport of moisture from the Gulf of Mexico into these regions, resulting in higher precipitation amounts (Weaver and Nigam 2008; Andresen et al. 2012; Zhu and Liang, 2013). Global warming on the other hand increases the humidity levels in the Midwest (Andresen et al. 2012; Papalexiou and Montanari, 2019), which can lead to higher rainfall amounts contributing to the observed summertime precipitation trend (Figs. 3 and 4 ). The positive trend in wintertime precipitation across Ohio is more pronounced compared to other seasons. For the northern regions, this is likely largely due to Ohio's proximity to Lake Erie, which influences local climate patterns (Schmidlin and Kosarik, 1999). During winter, cold air masses moving over the relatively warmer waters of Lake Erie pick up moisture, leading to lake-effect snow, especially in areas downwind of the lake (Schmidlin and Kosarik, 1999). This process results in increased precipitation in northeastern Ohio (Fig. 3 ). Other studies have reported increasing wintertime precipitation in the Midwest (Ellis and Johnson, 2019). For example, Wuebbles and Hayhoe (2004) projected a future increase in wintertime precipitation under climate change in the Midwest; Zhang & Villarini (2019) found that during 1948–2017 weather patterns associated with heavy precipitation, such as wave trains from the North Pacific, have shown an increasing trend in the Midwest, leading to more precipitation during winter. Furthermore, we analyzed the correlation between seasonal precipitation trends and global warming (Fig. 5 ). Out of the 55 total stations analyzed, 31, i.e., 56.5% stations showed a statistically significant positive correlation during DJF (top left map, Fig. 5 ), and 24 (i.e., 43.5% of the stations) showed no significant correlation in DJF. This means that during the winter season, more than half of the stations in Ohio returned a positive correlation between winter seasonally averaged precipitation positive trends and global warming, and the location of the positive correlation is fairly spread out across the state. During JJA, (top right map, Fig. 5 ), 13 out of the 55 stations (i.e., 23.6% of the total stations) showed a statistically significant positive correlation, and 42 stations (i.e., 76.4% of the stations) showed no statistically significant correlation. During MAM, (bottom right map, Fig. 5 ), 15 out of the 55 stations (i.e., 27.3%) showed a statistically significant positive correlation, while 40 stations (i.e., 72.7%) showed no significant correlation. Finally, during SON, (bottom left, Fig. 5 ) two out of the 55 stations (i.e., 3.6%) showed a statistically significant positive correlation while 53 (i.e., 96.4%) showed no significant correlation. None of the above stations showed a statistically significant negative correlation in any season. The relationship between global warming and increasing seasonally averaged precipitation in Ohio dominates in winter, with more than half of the stations showing statistically significant positive correlations (Fig. 5 and Figure S1). Interestingly over northeastern Ohio close to Lake Erie, all the stations show statistically significant positive correlations supporting findings that global warming is contributing to the increasing frequency of lake-effect snow (e.g., Andresen et al. 2012; Ellis and Johnson, 2019; Woolway et al., 2020). Burnett et al. (2003) indicate that increases in lake-effect snowfall across the Great Lakes, including Lake Erie, in the twentieth century are likely linked to regional manifestations of global warming; warmer lake surface temperatures reduce ice cover, enhancing moisture availability and snowfall intensity downwind of the Great Lakes. Leathers and Ellis (1996) document long-term increases in the frequency and intensity of synoptic patterns conducive to lake-effect snowfall over Lake Erie which align with warming trends. Kunkel et al. (2002) project that while future warming trends might alter snowstorm characteristics in the long-term leading to the replacement of lake-effect rain events with lake-effect snow events, current warming trends have increased conditions favorable for heavy snowfall in the region. A study by Scott and Huff (1996) discusses the effects of the Great Lakes, including Lake Superior, on regional climate conditions. It found that precipitation increases significantly downwind of Lake Superior, with up to 100% more precipitation in winter due to lake-induced effects. Besides global warming, other studies focusing on Lake Erie have identified a warming climate attributed to increased algae blooms (e.g., Kalcic et al., 2019). Algal blooms decrease water clarity leading to more heat being absorbed in the upper layers of the water. Generally, the positive correlations in Fig. 5 are consistent with Papalexiou and Montanari (2019) that global warming can contribute to increased annual precipitation in the Midwest. Figure 6 shows the correlation between the IPO and the seasonal precipitation averages; compared to other seasons, significant correlations were observed in DJF where 40% of the stations showed negative correlations between IPO and winter precipitation, dominantly in northwestern Ohio. The result in Fig. 6 indicates that the positive phase of the IPO is associated with the winter precipitation decrease in parts of Ohio and the negative phase is associated with winter precipitation increase in parts of Ohio (Dai, 2013). The observed relationship in Fig. 6 is linked to the jet stream dynamics prominent with El Niño-Southern Oscillation variability, which is modulated by the IPO (Westra et al. 2015). Figure 7 a shows results from the XGBOOST feature importance analysis, ranking stations where the winter precipitation is dominated by either the IPO or global warming signal. Out of the 55 stations, global warming signal dominated 60% of the stations including the stations in northeastern Ohio that are impacted by lake-effect snow. Table S1 shows the ranks and Fig. 7 b shows the absolute value of the difference between the ranks from IPO and global warming, presenting the magnitude of the differences. Generally, Fig. 7 highlights that the wintertime precipitation increase in Ohio is dominated by the global warming signal, and the IPO signal dominates in relatively fewer stations. In those regions where the IPO is dominant, the negative IPO phase can be expected to further slow the contribution of global warming signal to the winter precipitation changes since the negative IPO phase reduces the rate of global warming (Meehl et al., 2016). A report on Ohio’s Agriculture in a Changing Climate by Antosch (2023), highlighted that in a survey of 918 farmers in the Corn Belt region of the Midwestern United States including Ohio, 51% of the farmers have experienced warmer winters and variable rainfall. Antosch (2023) further noted that wet events have increased by 30% across Ohio and wintertime precipitation has increased, consistent with our results. These seasonal precipitation changes have implications for crop yield and agricultural activities in Ohio. Our findings have provided a more holistic analysis showing that in the historical period (1960–2023) average seasonal precipitation has increased across Ohio (Fig. 4 ). While climate patterns such as the IPO with inter-decadal influence on precipitation patterns contribute to these trends over some regions, the XGBOOST model introduced for disentangling climate signals in this study has shown that global warming is the dominant signal impacting trends in seasonal precipitation across most of the locations in Ohio (e.g., Krasting et al., 2013; Notaro et al., 2015). Therefore, there is a need for more studies monitoring global warming impacts on Ohio in the historical and future climate projections; early warning systems on seasonal precipitation forecasts, and for more adaptation strategies towards reducing the negative impacts of global warming on Ohio citizens. 4. Conclusion In this study, we analyzed seasonally averaged precipitation trends (1960–2023) across 55 weather stations in Ohio and examined the relationship between global warming, the IPO, and the observed trends. Additionally, we applied the Extreme Gradient Boosting (XGBOOST) algorithm to identify and rank the contributions of global warming and IPO to the observed seasonal precipitation trends. Our key findings are as follows: At a 95% confidence level, winter exhibited a statistically significant positive trend, with average seasonal precipitation increasing by approximately 0.15 mm/decade across Ohio. Similarly, summer showed a statistically significant increase of 0.13 mm/decade. However, no statistically significant changes were observed in spring and fall precipitation trends. The relationship between global warming and seasonally averaged precipitation was most pronounced in winter, with 56.4% of the stations showing statistically significant positive correlations. Conversely, IPO variability influenced seasonally averaged precipitation in Ohio only during winter, with 40% of stations exhibiting statistically significant negative correlations. The XGBOOST model revealed that while the IPO signal dominated in a smaller proportion of stations (40%), global warming was the dominant driver of the observed wintertime precipitation increase across most stations in Ohio. These findings highlight the relationship between global warming and internal climate variability, with global warming emerging as the more significant factor, in our study, of Ohio's changing precipitation patterns. Declarations Conflicts of Interest There are no conflicts of interest in this paper. Open Research Data availability statement: NOAA station precipitation is freely available from https://www.ncei.noaa.gov/cdo-web. Global warming proxy data is freely available from https://psl.noaa.gov/data/correlation/gmsst.data References Agarwal, S., Suchithra, A. S., & Singh, S. P. (2021). Analysis and interpretation of rainfall trends using Mann-Kendall's and Sen's slope method. Indian Journal of Ecology, 48(2) , 453–457. Agel, L., Barlow, M., Colby, F., Binder, H., Catto, J. L., Hoell, A., & Cohen, J. (2019). Dynamical analysis of extreme precipitation in the US northeast based on large-scale Allan, R. P., Barlow, M., Byrne, M. P., Cherchi, A., Douville, H. et al. (2020). Advances in understanding large-scale responses of the water cycle to climate change. Annals of the New York Academy of Sciences, 1472(1), 49–75. Andresen, J., Hilberg, S., Kunkel, K., & Center, M. R. C. (2012). Historical climate and climate trends in the Midwestern USA. US National Climate Assessment Midwest Technical Input Report, 1–18. Antosch, L. (2023). State of the Science Report: Ohio’s Agriculture in a Changing Climate. https://ofbf.org/2023/06/19/state-of-the-science-report-ohios-agriculture-in-a-changing-climate/. Assessed on 2nd December 2024. Bartels, R. J., Black, A. W., & Keim, B. D. (2020). Trends in precipitation days in the United States. International Journal of Climatology, 40(2), 1038–1048. Bandh, S. A., Shafi, S., Peerzada, M., Rehman, T., Bashir, S., Wani, S. A., & Dar, R. (2021). Multidimensional analysis of global climate change: a review. Environmental Science and Pollution Research, 28(20), 24872–24888. Burnett, A. W., Kirby, M. E., Mullins, H. T., & Patterson, W. P. (2003). Increasing Great Lake–effect snowfall during the twentieth century: A regional response to global warming?. Journal of Climate, 16(21), 3535–3542. Casey, J. A., Parks, R. M., Bruckner, T. A., Gemmill, A., & Catalano, R. (2023). Excess injury mortality in Washington State during the 2021 heat wave. American journal of public health, 113(6), 657–660. Chen, T., & Guestrin, C. (2016, August). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785–794). Cherif, I. L., & Kortebi, A. (2019). On using extreme gradient boosting (XGBoost) machine learning algorithm for home network traffic classification. In 2019 Wireless Days (WD) (pp. 1–6). IEEE. Coleman, J. S., & Rogers, J. C. (2003). Ohio River valley winter moisture conditions associated with the Pacific–North American teleconnection pattern. Journal of Climate, 16(6), 969–981.meteorological patterns. Climate Dynamics, 52, 1739–1760. Colman, R. A., & Power, S. B. (2010). Atmospheric radiative feedbacks associated with transient climate change and climate variability. Climate Dynamics, 34, 919–933. Colman, R., & Soden, B. J. (2021). Water vapor and lapse rate feedbacks in the climate system. Reviews of Modern Physics, 93(4), 045002. Corpuz, J. C. G. (2024). Heatwaves, wildfires and global warming: a call to public health action. Journal of Public Health, 46(2), e326-e327. Croux, C., & Dehon, C. (2010). Influence functions of the Spearman and Kendall correlation measures. Statistical methods & applications, 19, 497–515. Cruz, J. L., & Rossi-Hansberg, E. (2024). The economic geography of global warming. Review of Economic Studies, 91(2), 899–939. Dai, A. (2011). Drought under global warming: a review. WIREs Clim Change, 2: 45–65 Dai, A. (2013). The influence of the inter-decadal Pacific oscillation on US precipitation during 1923–2010. Climate dynamics , 41 (3), 633–646. Doan, Q. V., Chen, F., Kusaka, H., Dipankar, A., Khan, A., Hamdi, R., ... & Niyogi, D. (2022). Increased risk of extreme precipitation over an urban agglomeration with future global warming. Earth's Future, 10(6), e2021EF002563. Dong, B., & Dai, A. (2015). The influence of the interdecadal Pacific oscillation on temperature and precipitation over the globe. Climate dynamics, 45, 2667–2681. Durack, P. J., Wijffels, S. E., & Matear, R. J. (2012). Ocean salinities reveal strong global water cycle intensification during 1950 to 2000. science, 336(6080), 455–458. Easterling, D. R., Arnold, J. R., Knutson, T., Kunkel, K. E., LeGrande, A. N., et al. (2017). Precipitation change in the United States. Assessed on December 1 from https://repository.library.noaa.gov/view/noaa/32288 Ellis, A. W., & Johnson, J. J. (2004). Hydroclimatic analysis of snowfall trends associated with the North American Great Lakes. Journal of Hydrometeorology, 5(3), 471–486. Feng, Z., Leung, L., Hagos, S. et al., (2016). More frequent intense and long-lived storms dominate the springtime trend in central US rainfall. Nat Commun 7, 13429 Frame, D. J., Rosier, S. M., Noy, I., Harrington, L. J., Carey-Smith, T., Sparrow, S. N., et al. (2020). Climate change attribution and the economic costs of extreme weather events: a study on damages from extreme rainfall and drought. Climatic Change, 162, 781–797. Friedlingstein, P., O'sullivan, M., Jones, M. W., Andrew, R. M., Bakker, D. C., et al. (2023). Global carbon budget 2023. Earth System Science Data, 15(12), 5301–5369. Goss, M., Swain, D. L., Abatzoglou, J. T., Sarhadi, A., Kolden, C. A., Williams, A. P., & Diffenbaugh, N. S. (2020). Climate change is increasing the likelihood of extreme autumn wildfire conditions across California. Environmental Research Letters, 15(9), 094016. Habeeb, D., Vargo, J., & Stone, B. (2015). Rising heat wave trends in large US cities. Natural Hazards, 76, 1651–1665. Hamed, K. H., & Rao, A. R. (1998). A modified Mann-Kendall trend test for autocorrelated data. Journal of hydrology, 204(1–4), 182–196. Hansen, B. B., Isaksen, K., Benestad, R. E., Kohler, J., Pedersen, Å. Ø., et al. (2014). Warmer and wetter winters: characteristics and implications of an extreme weather event in the High Arctic. Environmental Research Letters, 9(11), 114021. Hanson, P. J., & Weltzin, J. F. (2000). Drought disturbance from climate change: response of United States forests. Science of the total environment, 262(3), 205–220. Haarsma, R. J., Hazeleger, W., Severijns, C., De Vries, H., Sterl, A., Bintanja, R., et al. (2013). More hurricanes to hit western Europe due to global warming. Geophysical Research Letters, 40(9), 1783–1788. Held, I. M., & Soden, B. J. (2000). Water vapor feedback and global warming. Annual review of energy and the environment, 25(1), 441–475. Henley, B. J., Gergis, J., Karoly, D. J., Power, S., Kennedy, J., & Folland, C. K. (2015). A tripole index for the interdecadal Pacific oscillation. Climate dynamics, 45, 3077–3090. Henley, B. J. (2017). Pacific decadal climate variability: Indices, patterns and tropical-extratropical interactions. Global and Planetary Change, 155, 42–55. Hoerling, M., Eischeid, J., Perlwitz, J., Quan, X. W., Wolter, K., & Cheng, L. (2016). Characterizing recent trends in US heavy precipitation. Journal of Climate, 29(7), 2313–2332. Huang, H., Winter, J. M., Osterberg, E. C., Horton, R. M., & Beckage, B. (2017). Total and extreme precipitation changes over the northeastern United States. Journal of hydrometeorology, 18(6), 1783–1798 Ibebuchi, C. C., Rainey, S., Obarein, O. A., Silva, A., & Lee, C. C. (2024). Comparison of machine learning models in forecasting different ENSO types. Physica Scripta, 99(8), 086007. Idso, S. B., & Balling, R. C. (1991). Recent trends in United States precipitation. Environmental Conservation, 18(1), 71–73. John M. Wallace et al., (2014). Global Warming and Winter Weather.” Science 343,729–730 DOI:10.1126/science.343.6172.729 Karl, T. R., & Trenberth, K. E. (2003). Modern global climate change. science, 302(5651), 1719–1723. Karmalkar, A. V., & Bradley, R. S. (2017). Consequences of global warming of 1.5 C and 2 C for regional temperature and precipitation changes in the contiguous United States. PloS one, 12(1), e0168697. Kosaka, Y., & Xie, S. P. (2016). The tropical Pacific as a key pacemaker of the variable rates of global warming. Nature Geoscience, 9(9), 669–673. Krasting, J. P., Broccoli, A. J., Dixon, K. W., & Lanzante, J. R. (2013). Future changes in Northern Hemisphere snowfall. Journal of Climate, 26(20), 7813–7828. Kumar, A. (2018). Global warming, climate change and greenhouse gas mitigation. Biofuels: greenhouse gas mitigation and global warming: next generation biofuels and role of biotechnology, 1–16. Kunkel, K. E., Westcott, N. E., & Kristovich, D. A. (2002). Assessment of potential effects of climate change on heavy lake-effect snowstorms near Lake Erie. Journal of Great Lakes Research, 28(4), 521–536. Kunkel, K. E., Karl, T. R., Squires, M. F., Yin, X., Stegall, S. T., & Easterling, D. R. (2020). Precipitation extremes: Trends and relationships with average precipitation and precipitable water in the contiguous United States. Journal of Applied Meteorology and Climatology, 59(1), 125–142. Lambert, F. H., Stine, A. R., Krakauer, N. Y., & Chiang, J. C. (2008). How much will precipitation increase with global warming?. EOS, Transactions American Geophysical Union, 89(21), 193–194. Leathers, D. J., & Ellis, A. W. (1996). Synoptic mechanisms associated with snowfall increases to the lee of Lakes Erie and Ontario. International Journal of Climatology, 16(10), 1117–1135. Lehmann, J., Coumou, D. & Frieler, K. (2015). Increased record-breaking precipitation events under global warming. Climatic Change 132, 501–515 Liu, L., Hong, Y., Hocker, J. E., Shafer, M. A., Carter, L. M., et al. (2012). Analyzing projected changes and trends of temperature and precipitation in the southern USA from 16 downscaled global climate models. Theoretical and Applied Climatology, 109, 345–360. Meehl, G. A., Hu, A., & Teng, H. (2016). Initialized decadal prediction for transition to positive phase of the Interdecadal Pacific Oscillation. Nature communications, 7(1), 11718. Myhre, G., Alterskjær, K., Stjern, C. W., Hodnebrog, Ø., Marelle, L., et al. (2019). Frequency of extreme precipitation increases extensively with event rareness under global warming. Scientific reports, 9(1), 16063. Notaro, M., Bennington, V., & Vavrus, S. (2015). Dynamically downscaled projections of lake-effect snow in the Great Lakes basin. Journal of Climate, 28(4), 1661–1684. Palinkas, L. A., & Wong, M. (2020). Global climate change and mental health. Current opinion in psychology, 32, 12–16. Papalexiou, S. M., & Montanari, A. (2019). Global and regional increase of precipitation extremes under global warming. Water Resources Research, 55(6), 4901–4914. Pathak, P., Kalra, A., & Ahmad, S. (2017). Temperature and precipitation changes in the Midwestern United States: implications for water management. International Journal of Water Resources Development, 33(6), 1003–1019. Pfeiffer, A., & Hepburn, C. (2016). Facing the challenge of climate change. Global Journal of Emerging Market Economies, 8(2), 201–215. Richter, I., & Xie, S. P. (2008). Muted precipitation increase in global warming simulations: A surface evaporation perspective. Journal of Geophysical Research: Atmospheres, 113(D24). Ritzi, Robert W., et al., (2021). El Niño Southern Oscillation (1896 to 2016): Quantifying Effects on Winter Precipitation and Temperature in Southwest Ohio, USA. The Ohio Journal of Science Robert W. Scott, et al., (2009). Impacts of the Great Lakes on Regional Climate Conditions. Journal of Great Lakes Research, Elsevier Rogers, Jeffrey & Coleman, Jill & Rogers, Jeffrey & Coleman, Jill. (2004). Ohio Winter Precipitation and Stream Flow Associations to Pacific Atmospheric and Oceanic Teleconnection Patterns. Ohio Journal of Science, 104. Saini, J., & Bhatt, R. (2020). Global warming-causes, impacts and mitigation strategies in agriculture. Current Journal of Applied Science and Technology, 39(7), 93–107. Schlenker, W., & Roberts, M. J. (2009). Nonlinear temperature effects indicate severe damages to US crop yields under climate change. Proceedings of the National Academy of sciences, 106(37), 15594–15598. Schmith, T. (2001). Global warming signature in observed winter precipitation in Northwestern Europe?. Climate Research, 17(3), 263–274. Schmidlin, T. W., & Kosarik, J. (1999). A record Ohio snowfall during 9–14 November 1996. Bulletin of the American Meteorological Society, 80(6), 1107–1116. Seneviratne, S. I., Zhang, X., Adnan, M., Badi, W., Dereczynski, C., Luca, A. D., et al. (2021). Weather and climate extreme events in a changing climate. Stephens, G. L., & Ellis, T. D. (2008). Controls of global-mean precipitation increases in global warming GCM experiments. Journal of Climate, 21(23), 6141–6155. Suriano, Z. J., & Guercio, H. L. (2024). A snowfall climatology of the Ohio River Valley, USA. Theoretical and Applied Climatology, 155(8), 7691–7701. Swain, D. L., Wing, O. E., Bates, P. D., Done, J. M., Johnson, K. A., & Cameron, D. R. (2020). Increased flood exposure due to climate change and population growth in the United States. Earth's Future, 8(11), e2020EF001778. Tcvetkov, P. (2021). Climate policy imbalance in the energy sector: Time to focus on the value of CO2 utilization. Energies, 14(2), 411. Torma, C., & Giorgi, F. (2020). On the evidence of orographical modulation of regional fine scale precipitation change signals: The Carpathians. Atmospheric Science Letters, 21(6), e967. Trenberth, K. E. (2011). Changes in precipitation with climate change. Climate research, 47(1–2), 123–138. Trenberth, K., Dai, A., van der Schrier, G. et al., (2014). Global warming and changes in drought. Nature Clim Change 4, 17–22 Vance, T., Kiem, A., Roberts, J., Jong, L., Plummer, C. et al.(2020, May). An annually dated Interdecadal Pacific Oscillation reconstruction spanning the last two millennia. In EGU General Assembly Conference Abstracts (p. 6218). Wahl, T., Jain, S., Bender, J., Meyers, S. D., & Luther, M. E. (2015). Increasing risk of compound flooding from storm surge and rainfall for major US cities. Nature Climate Change, 5(12), 1093–1097. Weaver, S. J., and S. Nigam, 2008. Variability of the Great Plainslow-level jet: Large-scale circulation context and hydroclimate impacts. J. Clim. 21: 1532–1551. Westra, S., Renard, B., & Thyer, M. (2015). The ENSO–precipitation teleconnection and its modulation by the interdecadal Pacific oscillation. Journal of Climate, 28(12), 4753–4773. Woolway, R.I., Kraemer, B.M., Lenters, J.D. et al., (2020). Global Lake Responses to Climate Change. Nat Rev Earth Environ 1, 388–403 Wu, S. Y. (2015). Changing characteristics of precipitation for the contiguous United States. Climatic Change, 132, 677–692. Wuebbles, D. J., & Hayhoe, K. (2004). Climate change projections for the United States Midwest. Mitigation and adaptation strategies for global change, 9, 335–363. Zhang, W., & Villarini, G. (2019). On the weather types that shape the precipitation patterns across the US Midwest. Climate Dynamics, 53(7), 4217–4232. Zhu, J., & Liang, X. Z. (2013). Impacts of the Bermuda high on regional climate and ozone over the United States. Journal of Climate, 26(3), 1018–1032. Supplementary Informations Supplementary Figure S1 and Table S1 are not available with this version. Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted 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-5574842","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":385867910,"identity":"16d3a421-1769-42bc-a365-28d365b09f37","order_by":0,"name":"Caitlin Wegener","email":"","orcid":"","institution":"Kent State University, Kent Ohio, United States","correspondingAuthor":false,"prefix":"","firstName":"Caitlin","middleName":"","lastName":"Wegener","suffix":""},{"id":385867911,"identity":"e45fcb04-b4da-4dfb-9662-8b3102815bc2","order_by":1,"name":"Chibuike Chiedozie Ibebuchi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwUlEQVRIiWNgGAWjYDACZh4GZiCVwM8D4TM2EK1FsgdIHiBKCwNUi8EZYrXwt/MefFzYZpdnfObwsccfGGxkNxwgoEXiMF+y8cy25GKzs23pBgcY0owJajFg5jGT5m07kLjtPI+ZxAGGw4nEaDH/DdKyuZ//G1DLf6K0mDGDtGzg7WEDajlAWAvIL9IzziUnzjhzzEzijAHQY4S08PefPfi5oMwusb8n+ZlERYWdbB8hLejuJE35KBgFo2AUjAIcAADuMULKhzwvQwAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0001-6010-2330","institution":"Department of Geography, Kent State University, Kent Ohio, United States","correspondingAuthor":true,"prefix":"","firstName":"Chibuike","middleName":"Chiedozie","lastName":"Ibebuchi","suffix":""}],"badges":[],"createdAt":"2024-12-03 20:15:43","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-5574842/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5574842/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":70694099,"identity":"94f9dabc-061c-4d63-a308-ca7d0dcde8ba","added_by":"auto","created_at":"2024-12-05 17:08:22","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":146479,"visible":true,"origin":"","legend":"\u003cp\u003eLocation of Ohio in the United States and the selected 55 stations across Ohio\u003c/p\u003e","description":"","filename":"Figure1.png","url":"https://assets-eu.researchsquare.com/files/rs-5574842/v1/ccb3f1b34d7c08c669c85a0f.png"},{"id":70694088,"identity":"0eb919f8-b3cb-412b-a26b-7effd4fd8815","added_by":"auto","created_at":"2024-12-05 17:08:19","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":79831,"visible":true,"origin":"","legend":"\u003cp\u003eDistribution of the seasonally averaged precipitation across the 55 stations in Figure 1. The analysis period is 1960 to 2023\u003cstrong\u003e. \u003c/strong\u003eThe median values are reported in the boxplots\u003c/p\u003e","description":"","filename":"Figure2.png","url":"https://assets-eu.researchsquare.com/files/rs-5574842/v1/4cadc954e3c38c670e420b9c.png"},{"id":70694106,"identity":"b3748637-ef36-4a2d-bbaf-52ca311bd017","added_by":"auto","created_at":"2024-12-05 17:08:24","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":110689,"visible":true,"origin":"","legend":"\u003cp\u003eSeasonal precipitation trends across Ohio from the 55 selected stations. Each map is representative of one of the four seasons\u003c/p\u003e","description":"","filename":"Figure3.png","url":"https://assets-eu.researchsquare.com/files/rs-5574842/v1/8d48a2aa4faf8e7467805817.png"},{"id":70694101,"identity":"81c25b83-afbc-4a88-96c3-42cf42173d7b","added_by":"auto","created_at":"2024-12-05 17:08:22","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":2670607,"visible":true,"origin":"","legend":"\u003cp\u003eTime series of seasonally averaged precipitation\u003cstrong\u003e \u003c/strong\u003eacross the 55 stations in Ohio. The line is the linear regression line, and the values are the slope and p-value at a 95% confidence level\u003c/p\u003e","description":"","filename":"Figure4.png","url":"https://assets-eu.researchsquare.com/files/rs-5574842/v1/5e93dbaea94cc5dba29bcd86.png"},{"id":70694100,"identity":"6968cf3e-16e3-4bf8-ae5a-9b3dfdb27b1f","added_by":"auto","created_at":"2024-12-05 17:08:22","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":112332,"visible":true,"origin":"","legend":"\u003cp\u003eCorrelation results of seasonal precipitation and global warming signals across Ohio, from the 55 stations analyzed\u003c/p\u003e","description":"","filename":"Figure5.png","url":"https://assets-eu.researchsquare.com/files/rs-5574842/v1/75fa28438a5cf3403be85b40.png"},{"id":70694093,"identity":"f3aaf923-016c-4140-a75f-6075b8e026f9","added_by":"auto","created_at":"2024-12-05 17:08:19","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":109228,"visible":true,"origin":"","legend":"\u003cp\u003eCorrelation results of seasonal precipitation and the Interdecadal Pacific Oscillation across Ohio, from the 55 stations analyzed.\u003c/p\u003e","description":"","filename":"Figure6.png","url":"https://assets-eu.researchsquare.com/files/rs-5574842/v1/4c8e6cc8e54368169a7b15c5.png"},{"id":70694092,"identity":"e4add253-1103-4b4e-8059-ffc72bbea1fb","added_by":"auto","created_at":"2024-12-05 17:08:19","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":82078,"visible":true,"origin":"","legend":"\u003cp\u003eDominant climate driver with the most explanatory power for winter precipitation in Ohio (top panel) and the difference between the ranks (bottom panel). The results are from the \u003cem\u003eXGBOOST feature importance metric\u003c/em\u003e. GW implies Global Warming.\u003c/p\u003e","description":"","filename":"Figure7.png","url":"https://assets-eu.researchsquare.com/files/rs-5574842/v1/8bb1551a7068f3e4f0559a4b.png"},{"id":70694867,"identity":"bf6d7d0a-8585-421d-ab69-340e68393ad9","added_by":"auto","created_at":"2024-12-05 17:16:37","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3635987,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5574842/v1/16337760-a272-4767-84af-5d5250af4a77.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eApplication of XGBOOST in Disentangling the Fingerprints of Global Warming and Interdecadal Pacific Oscillation on Seasonal Precipitation Trends in Ohio\u003c/strong\u003e\u003c/p\u003e","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eRising global temperatures represent one of the challenges the world is facing (Karl and Trenberth, 2003; Pfeiffer and Hepburn, 2016; Tcvetkov, 2021). The increase in temperature has far-reaching consequences, including altered weather patterns (Hansen et al., 2014), a rise in the frequency and intensity of extreme weather events (Haarsma et al., 2013; Seneviratne et al., 2021), disruptions to ecological balance (Bandh et al., 2021), and substantial economic disasters (Frame et al., 2021; Cruz and Rossi-Hansberg, 2024), among other impacts (Palinkas and Wong, 2020; Saini and Bhatt, 2020; Corpuz, 2024). In the United States, for example, the increase in heatwaves exacerbated by global warming contributes to high mortality rates (Habeeb et al., 2015; Casey et al., 2023). Changing rainfall patterns, leading to an increase in the frequency and severity of drought cycles, have resulted in devastating wildfires (Hanson and Weltzin, 2000; Goss et al., 2020), decreased crop yields (Schlenker and Roberts, 2009), and heavy rainfall and flooding with severe impacts on livelihoods (Swain et al., 2020). Given the recent changes in precipitation patterns and extreme weather events across the heterogeneous climates of the United States (Hoerling et al., 2016; Kunkel et al., 2020), there is a critical need to monitor regional precipitation changes and assess the role of global warming.\u003c/p\u003e \u003cp\u003eThe rise in global temperatures has been linked to anthropogenic emissions of greenhouse gases (Kumar, 2018; Olivier and Peters, 2020). Since the mid-20th century, annual carbon dioxide emissions from fossil fuels have increased from approximately 11\u0026nbsp;billion metric tons in the 1960s to an estimated 36.8\u0026nbsp;billion metric tons in 2023, marking a 1.1% rise from 2022 and setting a record high (Friedlingstein et al. 2023). Studies have linked global warming to more intense precipitations in certain regions (Lehmann et al., 2015; Myhre et al., 2019; Doan et al., 2022) and drought in some other regions (Dai, 2010; Trenberth et al., 2013). As surface temperatures rise due to global warming, the atmosphere's capacity to hold water vapor increases (Richter and Xie, 2008; Trenberth, 2011; Durack et al., 2012; Allan et al., 2020); but rising temperatures also increase surface drying and decrease the lapse rate (Colman and Power, 2010; Colman and Soden, 2021). Therefore, global precipitation patterns are likely to change with global warming. (Stephens and Ellis, 2008; Lambert et al., 2008). Precipitation changes are reported to occur at different rates in different areas across the globe due to topography, the climate of the region, and other internal climatic factors (Held and Soden, 2000; Torma and Giorgi, 2020). One such internal climatic factor that significantly impacts the rate of climate change-driven precipitation trends around the globe is the interdecadal Pacific Oscillation (IPO).\u003c/p\u003e \u003cp\u003eThe IPO is a long-term ocean-atmosphere phenomenon characterized by sea surface temperature (SST) variations across the Pacific basin, with phases lasting 20 to 30 years (Dong and Dai, 2015; Henley et al., 2015; Meehl, 2016; Henley, 2017). During its positive phase, the central and eastern tropical Pacific experience warmer SSTs, while the western Pacific and mid-latitudes are cooler; the negative phase exhibits the opposite pattern. A negative IPO phase can slow global surface temperature increases by promoting heat uptake in the deeper ocean layers; conversely, a positive phase can accelerate warming by enhancing surface heat retention (Kosaka and Xie, 2016). Reconstructions of the IPO using various proxies and instrumental records confirm its occurrence over the past two centuries, with phase shifts linked to significant climate events; these phases exhibit a global impact on climate variability (Vance et al., 2020). Moreover, the IPO contributes to spatially varied precipitation patterns across the globe, with more spatially heterogeneous impacts across the United States (Dong and Dai, 2015). In this study, we focus on introducing machine learning, specifically, the extreme gradient boosting (XGBOOST) feature important metric (Cherif and Kortebi, 2019; Ibebuchi et al., 2024), to disentangle the fingerprints of global warming and the IPO on seasonal precipitation trends in Ohio, United States, a region characterized by variable weather due to its geographic location and vulnerable to climate change (Antosch, 2023). We focused on seasonal precipitation trends, as they are most relevant for guiding individual farmers in Ohio who are currently negatively impacted by global farming (Antosch, 2023), in selecting crops and planning planting cycles.\u003c/p\u003e \u003cp\u003eNumerous studies have examined precipitation trends across the United States under global warming (Easterling et al., 2017; Karmalkar and Bradley, 2017; Bartels et al., 2020). These studies consistently show that historical precipitation patterns and events are undergoing significant changes and are projected to shift further under future climate change scenarios (Liu et al., 2012; Wu, 2015). However, due to the spatial heterogeneity and seasonality of precipitation changes, our study is the first to specifically analyze seasonal precipitation trends in Ohio while disentangling the fingerprints of global warming and the IPO. We introduce a novel methodology, to effectively model nonlinear relationships and handle collinearity between climate signals in quantifying the distinct contributions of global warming and internal climate variability, such as the IPO, to the observed seasonal precipitation trends. Additionally, we leverage station observations to provide detailed seasonal precipitation trends in Ohio at a 95% confidence level. This research is critical for improving climate modeling efforts, enhancing extreme weather preparedness, and informing climate change mitigation strategies in Ohio.\u003c/p\u003e"},{"header":"2. Data and Methodology","content":"\n\u003ch3\u003e2 .1 Data\u003c/h3\u003e\n\u003cp\u003eAll station precipitation data utilized in this study were sourced from the National Oceanic and Atmospheric Administration (NOAA) and are accessible at \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.ncei.noaa.gov/cdo-web\u003c/span\u003e\u003cspan address=\"https://www.ncei.noaa.gov/cdo-web\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Stations were selected based on the completeness of their monthly precipitation records from 1960 to 2023; only those with at least 95% data completeness during this period were included. The precipitation measurements represent the liquid water equivalent, meaning that for example, snowfall is measured as the depth of water produced upon melting. This selection criterion resulted in 55 stations across Ohio being incorporated into our study (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e). Additionally, we obtained the Global Mean Land/Ocean Temperature Index from NOAA's dataset, available at \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://psl.noaa.gov/data/climateindices/list/\u003c/span\u003e\u003cspan address=\"https://psl.noaa.gov/data/climateindices/list/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e, to serve as a proxy for global warming.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eThe climate of Ohio is variable, experiencing all four distinct seasons: summer, winter, autumn, and spring. Temperatures range from freezing and below during the winter months (December, January, February) to warm and hot during the summer (June, July, August). Ohio\u0026rsquo;s climate is classified as humid continental (Pierce, 1959), characterized by pronounced seasonal changes, including diverse precipitation types and significant temperature variations across the seasons.\u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e shows that the seasonally averaged precipitation in Ohio is highest in summer and lowest in winter. This is primarily due to increased atmospheric moisture and convective activity during the summer months, which enhances rainfall from thunderstorms (Agel et al., 2019), while the colder winter months limit moisture availability and precipitation rates. Ohio\u0026rsquo;s climate patterns are also shaped by the interaction of warm, moist air masses from the Gulf of Mexico and cold air masses from Canada, creating dynamic weather conditions (Coleman and Rogers, 2003). Ohio's proximity to Lake Erie results in increased lake-effect snow, particularly in the northern regions, during winter (Suriano and Guercio, 2024). Additionally, Ohio is influenced by larger climatic phenomena such as El Ni\u0026ntilde;o and La Ni\u0026ntilde;a, which typically bring decreased and increased precipitation, respectively, depending on the phase (Rogers and Coleman, 2004; Ritzi et al., 2021).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003e2.2 Method\u003c/h2\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e shows that the selected 55 stations in Ohio cover the geographical regions across the state boundary. We organized the data by the four meteorological seasons and calculated the average seasonal precipitation per year. December-February (DJF) represents winter; March-May (MAM) represents spring; June-August (JJA) represents summer, and September-November (SON) represents autumn. By averaging the monthly precipitation, we focus on the seasonal changes. We calculated the trends of the seasonal rainfall averages from 1960 to 2023 using Theil-Sen's slope method (Agarwal et al., 2021). The Theil-Sen's slope method is robust and does not rely on assumptions about the data's statistical distribution. The seasonally averaged precipitation trends were tested for statistical significance at a 95% confidence level using the Mann-Kendall test (Hamed and Rao, 1998). We examined the relationship between global warming, IPO, and the observed trends using the Kendall correlation (Croux and Dehon, 2010) between the seasonally averaged global warming signal data, IPO index, and the seasonally averaged precipitation data from 1960 to 2023.\u003c/p\u003e \u003cp\u003eIn the next step, we applied the XGBOOST algorithm to disentangle and quantify the contributions of key climatic drivers, i.e. global warming signal and the IPO, to seasonal precipitation trends at each station in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. XGBOOST is a machine-learning algorithm based on gradient-boosted decision trees (Chen and Guestrin, 2016). XGBOOST is particularly well-suited for handling interactions between explanatory variables, including nonlinear relationships and potential collinearity. The algorithm\u0026rsquo;s \u003cem\u003efeature importance metric\u003c/em\u003e is innovatively utilized in this study to evaluate the relative contribution of each climatic driver to the variability in seasonal precipitation, providing a robust framework for modeling nonlinear interactions and handling collinearity in ranking the fingerprints global warming signal and the IPO.\u003c/p\u003e \u003cp\u003eIn our study, XGBOOST was trained using global warming and IPO as input drivers and seasonal precipitation data as the target variable. The importance score for each climatic driver was calculated and scaled to reflect its percentage contribution to the variability in seasonal precipitation.\u003c/p\u003e \u003cp\u003eMathematically, the importance \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{I}_{j}\\)\u003c/span\u003e\u003c/span\u003e for the climate driver \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:j\\)\u003c/span\u003e\u003c/span\u003e is defined in Eq.\u0026nbsp;(\u003cspan refid=\"Equ1\" class=\"InternalRef\"\u003e1\u003c/span\u003e)\u003cdiv id=\"Equ1\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ1\" name=\"EquationSource\"\u003e\n$$\\:{I}_{j}=\\frac{\\sum\\:k\\in\\:{T}_{j\\:}\\:{G}_{k}}{\\sum\\:K\\in\\:T{G}_{k}}\\times\\:100$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e1\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eWhere \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{T}_{j\\:}\\)\u003c/span\u003e\u003c/span\u003e represents the trees where driver \u003cem\u003ej\u003c/em\u003e is used; \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{G}_{k}\\)\u003c/span\u003e\u003c/span\u003e is the gain from the split at node \u003cem\u003ek\u003c/em\u003e, and \u003cem\u003eT\u003c/em\u003e is the set of all trees in the model. By normalizing \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{I}_{j}\\)\u003c/span\u003e\u003c/span\u003e we derived the percentage contribution of each climate driver to precipitation variability. This approach is valuable and innovative in our study because precipitation trends in Ohio are shaped by overlapping climate signals that vary across spatial and temporal scales. Traditional regression methods may fail to adequately disentangle the effects of interdependent drivers like global warming and IPO. XGBOOST effectively addresses this by iteratively isolating the contributions of each driver, even when interactions and dependencies exist.\u003c/p\u003e \u003c/div\u003e"},{"header":"3. Results and Discussion","content":"\u003cp\u003eFigure \u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e shows the trends in seasonal precipitation averages across the 55 selected stations. For DJF (top left map, Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e), out of the 55 total stations, 41 stations representing 74.6 percent of the total stations across Ohio showed a positive trend. The stations that showed a positive trend during the winter season were fairly spread out around Ohio and were not localized to a single area (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e). During JJA, (top right map, Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e) 21 out of the 55 stations (i.e., 38.2% of the total stations) showed a positive trend, and 34 stations (i.e., 61.8% of the total stations) during JJA showed no change. The positive trends during the JJA are focused on the central to some northern portions of the state (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e). During SON (bottom left map) 4 out of the 55 stations (i.e., 7.3% percent of the total stations) showed a positive trend in precipitation in northeast Ohio, and 51 of the stations (i.e., 92.7% of the total stations) showed no change (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e). Finally, during MAM, (bottom right map, Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e), 9 out of the 55 stations (16.4% of the total stations) in the western side and northeast of the state showed a positive trend in precipitation while 46 stations (83.6% of the total stations) showed no change. None of the stations within any season showed a negative trend in seasonally averaged precipitation consistent with Bartels et al. (2020) on the increasing trend of precipitation days in the Midwest United States.\u003c/p\u003e \u003cp\u003eDuring the winter season, the number of stations showing a positive trend in seasonal precipitation was greater than the number that showed no change (i.e., 25.4% of the stations). This implies that on the spatial scale, the winter season is experiencing a remarkable increase in average seasonal precipitation compared to the other seasons which show no change in most of the analyzed stations (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e shows the trends in seasonal precipitation averaged across the 55 stations in Ohio. During winter, (top left, Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e), there is a very definable statistically significant increase in seasonal precipitation by 0.15 mm/decade; during JJA, there was also a statistically significant increase by 0.13 mm/decade, although less than the winter increase. SON and MAM did not show statistically significant changes at a 95% confidence level. Therefore, during our analysis period the fall and spring seasons experienced no change in average seasonal precipitation trends across Ohio (Figs.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e and \u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eOur results on precipitation increases in Ohio are consistent with Easterling et al. (2017) - that since 1901, annual precipitation has increased in most of the Midwest and Northeast regions of the United States (Huang et al., 2017). In terms of the seasonality of the precipitation changes, Pathak et al. (2017) reported an increase in summertime precipitation in the Midwest. Further, an increase in summertime precipitation in the United States, including the Midwest, has been linked to the westward extension of the Bermuda High and the development of cut-off low-pressure systems, which facilitate the transport of moisture from the Gulf of Mexico into these regions, resulting in higher precipitation amounts (Weaver and Nigam 2008; Andresen et al. 2012; Zhu and Liang, 2013). Global warming on the other hand increases the humidity levels in the Midwest (Andresen et al. 2012; Papalexiou and Montanari, 2019), which can lead to higher rainfall amounts contributing to the observed summertime precipitation trend (Figs.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e and \u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eThe positive trend in wintertime precipitation across Ohio is more pronounced compared to other seasons. For the northern regions, this is likely largely due to Ohio's proximity to Lake Erie, which influences local climate patterns (Schmidlin and Kosarik, 1999). During winter, cold air masses moving over the relatively warmer waters of Lake Erie pick up moisture, leading to lake-effect snow, especially in areas downwind of the lake (Schmidlin and Kosarik, 1999). This process results in increased precipitation in northeastern Ohio (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e). Other studies have reported increasing wintertime precipitation in the Midwest (Ellis and Johnson, 2019). For example, Wuebbles and Hayhoe (2004) projected a future increase in wintertime precipitation under climate change in the Midwest; Zhang \u0026amp; Villarini (2019) found that during 1948\u0026ndash;2017 weather patterns associated with heavy precipitation, such as wave trains from the North Pacific, have shown an increasing trend in the Midwest, leading to more precipitation during winter.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eFurthermore, we analyzed the correlation between seasonal precipitation trends and global warming (Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e). Out of the 55 total stations analyzed, 31, i.e., 56.5% stations showed a statistically significant positive correlation during DJF (top left map, Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e), and 24 (i.e., 43.5% of the stations) showed no significant correlation in DJF. This means that during the winter season, more than half of the stations in Ohio returned a positive correlation between winter seasonally averaged precipitation positive trends and global warming, and the location of the positive correlation is fairly spread out across the state.\u003c/p\u003e \u003cp\u003eDuring JJA, (top right map, Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e), 13 out of the 55 stations (i.e., 23.6% of the total stations) showed a statistically significant positive correlation, and 42 stations (i.e., 76.4% of the stations) showed no statistically significant correlation. During MAM, (bottom right map, Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e), 15 out of the 55 stations (i.e., 27.3%) showed a statistically significant positive correlation, while 40 stations (i.e., 72.7%) showed no significant correlation. Finally, during SON, (bottom left, Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e) two out of the 55 stations (i.e., 3.6%) showed a statistically significant positive correlation while 53 (i.e., 96.4%) showed no significant correlation. None of the above stations showed a statistically significant negative correlation in any season.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eThe relationship between global warming and increasing seasonally averaged precipitation in Ohio dominates in winter, with more than half of the stations showing statistically significant positive correlations (Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e and Figure S1). Interestingly over northeastern Ohio close to Lake Erie, all the stations show statistically significant positive correlations supporting findings that global warming is contributing to the increasing frequency of lake-effect snow (e.g., Andresen et al. 2012; Ellis and Johnson, 2019; Woolway et al., 2020). Burnett et al. (2003) indicate that increases in lake-effect snowfall across the Great Lakes, including Lake Erie, in the twentieth century are likely linked to regional manifestations of global warming; warmer lake surface temperatures reduce ice cover, enhancing moisture availability and snowfall intensity downwind of the Great Lakes. Leathers and Ellis (1996) document long-term increases in the frequency and intensity of synoptic patterns conducive to lake-effect snowfall over Lake Erie which align with warming trends. Kunkel et al. (2002) project that while future warming trends might alter snowstorm characteristics in the long-term leading to the replacement of lake-effect rain events with lake-effect snow events, current warming trends have increased conditions favorable for heavy snowfall in the region. A study by Scott and Huff (1996) discusses the effects of the Great Lakes, including Lake Superior, on regional climate conditions. It found that precipitation increases significantly downwind of Lake Superior, with up to 100% more precipitation in winter due to lake-induced effects. Besides global warming, other studies focusing on Lake Erie have identified a warming climate attributed to increased algae blooms (e.g., Kalcic et al., 2019). Algal blooms decrease water clarity leading to more heat being absorbed in the upper layers of the water. Generally, the positive correlations in Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e are consistent with Papalexiou and Montanari (2019) that global warming can contribute to increased annual precipitation in the Midwest.\u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e6\u003c/span\u003e shows the correlation between the IPO and the seasonal precipitation averages; compared to other seasons, significant correlations were observed in DJF where 40% of the stations showed negative correlations between IPO and winter precipitation, dominantly in northwestern Ohio. The result in Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e6\u003c/span\u003e indicates that the positive phase of the IPO is associated with the winter precipitation decrease in parts of Ohio and the negative phase is associated with winter precipitation increase in parts of Ohio (Dai, 2013). The observed relationship in Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e6\u003c/span\u003e is linked to the jet stream dynamics prominent with El Ni\u0026ntilde;o-Southern Oscillation variability, which is modulated by the IPO (Westra et al. 2015).\u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e7\u003c/span\u003ea shows results from the XGBOOST feature importance analysis, ranking stations where the winter precipitation is dominated by either the IPO or global warming signal. Out of the 55 stations, global warming signal dominated 60% of the stations including the stations in northeastern Ohio that are impacted by lake-effect snow. Table S1 shows the ranks and Fig.\u0026nbsp;\u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e7\u003c/span\u003eb shows the absolute value of the difference between the ranks from IPO and global warming, presenting the magnitude of the differences. Generally, Fig.\u0026nbsp;\u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e7\u003c/span\u003e highlights that the wintertime precipitation increase in Ohio is dominated by the global warming signal, and the IPO signal dominates in relatively fewer stations. In those regions where the IPO is dominant, the negative IPO phase can be expected to further slow the contribution of global warming signal to the winter precipitation changes since the negative IPO phase reduces the rate of global warming (Meehl et al., 2016).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eA report on Ohio\u0026rsquo;s Agriculture in a Changing Climate by Antosch (2023), highlighted that in a survey of 918 farmers in the Corn Belt region of the Midwestern United States including Ohio, 51% of the farmers have experienced warmer winters and variable rainfall. Antosch (2023) further noted that wet events have increased by 30% across Ohio and wintertime precipitation has increased, consistent with our results. These seasonal precipitation changes have implications for crop yield and agricultural activities in Ohio. Our findings have provided a more holistic analysis showing that in the historical period (1960\u0026ndash;2023) average seasonal precipitation has increased across Ohio (Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e). While climate patterns such as the IPO with inter-decadal influence on precipitation patterns contribute to these trends over some regions, the XGBOOST model introduced for disentangling climate signals in this study has shown that global warming is the dominant signal impacting trends in seasonal precipitation across most of the locations in Ohio (e.g., Krasting et al., 2013; Notaro et al., 2015). Therefore, there is a need for more studies monitoring global warming impacts on Ohio in the historical and future climate projections; early warning systems on seasonal precipitation forecasts, and for more adaptation strategies towards reducing the negative impacts of global warming on Ohio citizens.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e"},{"header":"4. Conclusion","content":"\u003cp\u003eIn this study, we analyzed seasonally averaged precipitation trends (1960\u0026ndash;2023) across 55 weather stations in Ohio and examined the relationship between global warming, the IPO, and the observed trends. Additionally, we applied the Extreme Gradient Boosting (XGBOOST) algorithm to identify and rank the contributions of global warming and IPO to the observed seasonal precipitation trends. Our key findings are as follows:\u003c/p\u003e \u003cp\u003e \u003col\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003eAt a 95% confidence level, winter exhibited a statistically significant positive trend, with average seasonal precipitation increasing by approximately 0.15 mm/decade across Ohio. Similarly, summer showed a statistically significant increase of 0.13 mm/decade. However, no statistically significant changes were observed in spring and fall precipitation trends.\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003eThe relationship between global warming and seasonally averaged precipitation was most pronounced in winter, with 56.4% of the stations showing statistically significant positive correlations. Conversely, IPO variability influenced seasonally averaged precipitation in Ohio only during winter, with 40% of stations exhibiting statistically significant negative correlations.\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003eThe XGBOOST model revealed that while the IPO signal dominated in a smaller proportion of stations (40%), global warming was the dominant driver of the observed wintertime precipitation increase across most stations in Ohio.\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003c/ol\u003e \u003c/p\u003e \u003cp\u003eThese findings highlight the relationship between global warming and internal climate variability, with global warming emerging as the more significant factor, in our study, of Ohio's changing precipitation patterns.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eConflicts of Interest\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThere are no conflicts of interest in this paper.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eOpen Research\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData availability statement: \u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNOAA station precipitation is freely available from https://www.ncei.noaa.gov/cdo-web. Global warming proxy data is freely available from https://psl.noaa.gov/data/correlation/gmsst.data\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eAgarwal, S., Suchithra, A. S., \u0026amp; Singh, S. P. (2021). Analysis and interpretation of rainfall trends using Mann-Kendall's and Sen's slope method. \u003cem\u003eIndian Journal of Ecology, 48(2)\u003c/em\u003e, 453\u0026ndash;457.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAgel, L., Barlow, M., Colby, F., Binder, H., Catto, J. L., Hoell, A., \u0026amp; Cohen, J. (2019). Dynamical analysis of extreme precipitation in the US northeast based on large-scale\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAllan, R. P., Barlow, M., Byrne, M. P., Cherchi, A., Douville, H. et al. (2020). Advances in understanding large-scale responses of the water cycle to climate change. Annals of the New York Academy of Sciences, 1472(1), 49\u0026ndash;75.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAndresen, J., Hilberg, S., Kunkel, K., \u0026amp; Center, M. R. C. (2012). Historical climate and climate trends in the Midwestern USA. US National Climate Assessment Midwest Technical Input Report, 1\u0026ndash;18.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAntosch, L. (2023). State of the Science Report: Ohio\u0026rsquo;s Agriculture in a Changing Climate. https://ofbf.org/2023/06/19/state-of-the-science-report-ohios-agriculture-in-a-changing-climate/. Assessed on 2nd December 2024.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBartels, R. J., Black, A. W., \u0026amp; Keim, B. D. (2020). Trends in precipitation days in the United States. International Journal of Climatology, 40(2), 1038\u0026ndash;1048.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBandh, S. A., Shafi, S., Peerzada, M., Rehman, T., Bashir, S., Wani, S. A., \u0026amp; Dar, R. (2021). Multidimensional analysis of global climate change: a review. Environmental Science and Pollution Research, 28(20), 24872\u0026ndash;24888.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBurnett, A. W., Kirby, M. E., Mullins, H. T., \u0026amp; Patterson, W. P. (2003). Increasing Great Lake\u0026ndash;effect snowfall during the twentieth century: A regional response to global warming?. Journal of Climate, 16(21), 3535\u0026ndash;3542.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCasey, J. A., Parks, R. M., Bruckner, T. A., Gemmill, A., \u0026amp; Catalano, R. (2023). Excess injury mortality in Washington State during the 2021 heat wave. American journal of public health, 113(6), 657\u0026ndash;660.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen, T., \u0026amp; Guestrin, C. (2016, August). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785\u0026ndash;794).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCherif, I. L., \u0026amp; Kortebi, A. (2019). On using extreme gradient boosting (XGBoost) machine learning algorithm for home network traffic classification. In 2019 Wireless Days (WD) (pp. 1\u0026ndash;6). IEEE.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eColeman, J. S., \u0026amp; Rogers, J. C. (2003). Ohio River valley winter moisture conditions associated with the Pacific\u0026ndash;North American teleconnection pattern. Journal of Climate, 16(6), 969\u0026ndash;981.meteorological patterns. Climate Dynamics, 52, 1739\u0026ndash;1760.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eColman, R. A., \u0026amp; Power, S. B. (2010). Atmospheric radiative feedbacks associated with transient climate change and climate variability. Climate Dynamics, 34, 919\u0026ndash;933.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eColman, R., \u0026amp; Soden, B. J. (2021). Water vapor and lapse rate feedbacks in the climate system. Reviews of Modern Physics, 93(4), 045002.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCorpuz, J. C. G. (2024). Heatwaves, wildfires and global warming: a call to public health action. Journal of Public Health, 46(2), e326-e327.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCroux, C., \u0026amp; Dehon, C. (2010). Influence functions of the Spearman and Kendall correlation measures. Statistical methods \u0026amp; applications, 19, 497\u0026ndash;515.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCruz, J. L., \u0026amp; Rossi-Hansberg, E. (2024). The economic geography of global warming. Review of Economic Studies, 91(2), 899\u0026ndash;939.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDai, A. (2011). Drought under global warming: a review. \u003cem\u003eWIREs Clim Change, 2: 45\u0026ndash;65\u003c/em\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDai, A. (2013). The influence of the inter-decadal Pacific oscillation on US precipitation during 1923\u0026ndash;2010. \u003cem\u003eClimate dynamics\u003c/em\u003e, \u003cem\u003e41\u003c/em\u003e(3), 633\u0026ndash;646.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDoan, Q. V., Chen, F., Kusaka, H., Dipankar, A., Khan, A., Hamdi, R., ... \u0026amp; Niyogi, D. (2022). Increased risk of extreme precipitation over an urban agglomeration with future global warming. Earth's Future, 10(6), e2021EF002563.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDong, B., \u0026amp; Dai, A. (2015). The influence of the interdecadal Pacific oscillation on temperature and precipitation over the globe. Climate dynamics, 45, 2667\u0026ndash;2681.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDurack, P. J., Wijffels, S. E., \u0026amp; Matear, R. J. (2012). Ocean salinities reveal strong global water cycle intensification during 1950 to 2000. science, 336(6080), 455\u0026ndash;458.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eEasterling, D. R., Arnold, J. R., Knutson, T., Kunkel, K. E., LeGrande, A. N., et al. (2017). Precipitation change in the United States. Assessed on December 1 from https://repository.library.noaa.gov/view/noaa/32288\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eEllis, A. W., \u0026amp; Johnson, J. J. (2004). Hydroclimatic analysis of snowfall trends associated with the North American Great Lakes. Journal of Hydrometeorology, 5(3), 471\u0026ndash;486.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFeng, Z., Leung, L., Hagos, S. et al., (2016). More frequent intense and long-lived storms dominate the springtime trend in central US rainfall. \u003cem\u003eNat Commun 7, 13429\u003c/em\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFrame, D. J., Rosier, S. M., Noy, I., Harrington, L. J., Carey-Smith, T., Sparrow, S. N., et al. (2020). Climate change attribution and the economic costs of extreme weather events: a study on damages from extreme rainfall and drought. Climatic Change, 162, 781\u0026ndash;797.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFriedlingstein, P., O'sullivan, M., Jones, M. W., Andrew, R. M., Bakker, D. C., et al. (2023). Global carbon budget 2023. Earth System Science Data, 15(12), 5301\u0026ndash;5369.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGoss, M., Swain, D. L., Abatzoglou, J. T., Sarhadi, A., Kolden, C. A., Williams, A. P., \u0026amp; Diffenbaugh, N. S. (2020). Climate change is increasing the likelihood of extreme autumn wildfire conditions across California. Environmental Research Letters, 15(9), 094016.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHabeeb, D., Vargo, J., \u0026amp; Stone, B. (2015). Rising heat wave trends in large US cities. Natural Hazards, 76, 1651\u0026ndash;1665.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHamed, K. H., \u0026amp; Rao, A. R. (1998). A modified Mann-Kendall trend test for autocorrelated data. Journal of hydrology, 204(1\u0026ndash;4), 182\u0026ndash;196.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHansen, B. B., Isaksen, K., Benestad, R. E., Kohler, J., Pedersen, \u0026Aring;. \u0026Oslash;., et al. (2014). Warmer and wetter winters: characteristics and implications of an extreme weather event in the High Arctic. Environmental Research Letters, 9(11), 114021.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHanson, P. J., \u0026amp; Weltzin, J. F. (2000). Drought disturbance from climate change: response of United States forests. Science of the total environment, 262(3), 205\u0026ndash;220.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHaarsma, R. J., Hazeleger, W., Severijns, C., De Vries, H., Sterl, A., Bintanja, R., et al. (2013). More hurricanes to hit western Europe due to global warming. Geophysical Research Letters, 40(9), 1783\u0026ndash;1788.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHeld, I. M., \u0026amp; Soden, B. J. (2000). Water vapor feedback and global warming. Annual review of energy and the environment, 25(1), 441\u0026ndash;475.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHenley, B. J., Gergis, J., Karoly, D. J., Power, S., Kennedy, J., \u0026amp; Folland, C. K. (2015). A tripole index for the interdecadal Pacific oscillation. Climate dynamics, 45, 3077\u0026ndash;3090.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHenley, B. J. (2017). Pacific decadal climate variability: Indices, patterns and tropical-extratropical interactions. Global and Planetary Change, 155, 42\u0026ndash;55.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHoerling, M., Eischeid, J., Perlwitz, J., Quan, X. W., Wolter, K., \u0026amp; Cheng, L. (2016). Characterizing recent trends in US heavy precipitation. Journal of Climate, 29(7), 2313\u0026ndash;2332.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHuang, H., Winter, J. M., Osterberg, E. C., Horton, R. M., \u0026amp; Beckage, B. (2017). Total and extreme precipitation changes over the northeastern United States. Journal of hydrometeorology, 18(6), 1783\u0026ndash;1798\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eIbebuchi, C. C., Rainey, S., Obarein, O. A., Silva, A., \u0026amp; Lee, C. C. (2024). Comparison of machine learning models in forecasting different ENSO types. Physica Scripta, 99(8), 086007.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eIdso, S. B., \u0026amp; Balling, R. C. (1991). Recent trends in United States precipitation. Environmental Conservation, 18(1), 71\u0026ndash;73.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJohn M. Wallace et al., (2014). Global Warming and Winter Weather.\u0026rdquo; \u003cem\u003eScience 343,729\u0026ndash;730 DOI:10.1126/science.343.6172.729\u003c/em\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKarl, T. R., \u0026amp; Trenberth, K. E. (2003). Modern global climate change. science, 302(5651), 1719\u0026ndash;1723.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKarmalkar, A. V., \u0026amp; Bradley, R. S. (2017). Consequences of global warming of 1.5 C and 2 C for regional temperature and precipitation changes in the contiguous United States. PloS one, 12(1), e0168697.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKosaka, Y., \u0026amp; Xie, S. P. (2016). The tropical Pacific as a key pacemaker of the variable rates of global warming. Nature Geoscience, 9(9), 669\u0026ndash;673.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKrasting, J. P., Broccoli, A. J., Dixon, K. W., \u0026amp; Lanzante, J. R. (2013). Future changes in Northern Hemisphere snowfall. Journal of Climate, 26(20), 7813\u0026ndash;7828.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKumar, A. (2018). Global warming, climate change and greenhouse gas mitigation. Biofuels: greenhouse gas mitigation and global warming: next generation biofuels and role of biotechnology, 1\u0026ndash;16.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKunkel, K. E., Westcott, N. E., \u0026amp; Kristovich, D. A. (2002). Assessment of potential effects of climate change on heavy lake-effect snowstorms near Lake Erie. Journal of Great Lakes Research, 28(4), 521\u0026ndash;536.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKunkel, K. E., Karl, T. R., Squires, M. F., Yin, X., Stegall, S. T., \u0026amp; Easterling, D. R. (2020). Precipitation extremes: Trends and relationships with average precipitation and precipitable water in the contiguous United States. Journal of Applied Meteorology and Climatology, 59(1), 125\u0026ndash;142.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLambert, F. H., Stine, A. R., Krakauer, N. Y., \u0026amp; Chiang, J. C. (2008). How much will precipitation increase with global warming?. EOS, Transactions American Geophysical Union, 89(21), 193\u0026ndash;194.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLeathers, D. J., \u0026amp; Ellis, A. W. (1996). Synoptic mechanisms associated with snowfall increases to the lee of Lakes Erie and Ontario. International Journal of Climatology, 16(10), 1117\u0026ndash;1135.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLehmann, J., Coumou, D. \u0026amp; Frieler, K. (2015). Increased record-breaking precipitation events under global warming. \u003cem\u003eClimatic Change 132, 501\u0026ndash;515\u003c/em\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLiu, L., Hong, Y., Hocker, J. E., Shafer, M. A., Carter, L. M., et al. (2012). Analyzing projected changes and trends of temperature and precipitation in the southern USA from 16 downscaled global climate models. Theoretical and Applied Climatology, 109, 345\u0026ndash;360.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMeehl, G. A., Hu, A., \u0026amp; Teng, H. (2016). Initialized decadal prediction for transition to positive phase of the Interdecadal Pacific Oscillation. Nature communications, 7(1), 11718.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMyhre, G., Alterskj\u0026aelig;r, K., Stjern, C. W., Hodnebrog, \u0026Oslash;., Marelle, L., et al. (2019). Frequency of extreme precipitation increases extensively with event rareness under global warming. Scientific reports, 9(1), 16063.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNotaro, M., Bennington, V., \u0026amp; Vavrus, S. (2015). Dynamically downscaled projections of lake-effect snow in the Great Lakes basin. Journal of Climate, 28(4), 1661\u0026ndash;1684.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePalinkas, L. A., \u0026amp; Wong, M. (2020). Global climate change and mental health. Current opinion in psychology, 32, 12\u0026ndash;16.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePapalexiou, S. M., \u0026amp; Montanari, A. (2019). Global and regional increase of precipitation extremes under global warming. Water Resources Research, 55(6), 4901\u0026ndash;4914.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePathak, P., Kalra, A., \u0026amp; Ahmad, S. (2017). Temperature and precipitation changes in the Midwestern United States: implications for water management. International Journal of Water Resources Development, 33(6), 1003\u0026ndash;1019.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePfeiffer, A., \u0026amp; Hepburn, C. (2016). Facing the challenge of climate change. Global Journal of Emerging Market Economies, 8(2), 201\u0026ndash;215.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRichter, I., \u0026amp; Xie, S. P. (2008). Muted precipitation increase in global warming simulations: A surface evaporation perspective. Journal of Geophysical Research: Atmospheres, 113(D24).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRitzi, Robert W., et al., (2021). El Ni\u0026ntilde;o Southern Oscillation (1896 to 2016): Quantifying Effects on Winter Precipitation and Temperature in Southwest Ohio, USA. \u003cem\u003eThe Ohio Journal of Science\u003c/em\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRobert W. Scott, et al., (2009). Impacts of the Great Lakes on Regional Climate Conditions. \u003cem\u003eJournal of Great Lakes Research, Elsevier\u003c/em\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRogers, Jeffrey \u0026amp; Coleman, Jill \u0026amp; Rogers, Jeffrey \u0026amp; Coleman, Jill. (2004). Ohio Winter Precipitation and Stream Flow Associations to Pacific Atmospheric and Oceanic Teleconnection Patterns. \u003cem\u003eOhio Journal of Science, 104.\u003c/em\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSaini, J., \u0026amp; Bhatt, R. (2020). Global warming-causes, impacts and mitigation strategies in agriculture. Current Journal of Applied Science and Technology, 39(7), 93\u0026ndash;107.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSchlenker, W., \u0026amp; Roberts, M. J. (2009). Nonlinear temperature effects indicate severe damages to US crop yields under climate change. Proceedings of the National Academy of sciences, 106(37), 15594\u0026ndash;15598.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSchmith, T. (2001). Global warming signature in observed winter precipitation in Northwestern Europe?. Climate Research, 17(3), 263\u0026ndash;274.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSchmidlin, T. W., \u0026amp; Kosarik, J. (1999). A record Ohio snowfall during 9\u0026ndash;14 November 1996. Bulletin of the American Meteorological Society, 80(6), 1107\u0026ndash;1116.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSeneviratne, S. I., Zhang, X., Adnan, M., Badi, W., Dereczynski, C., Luca, A. D., et al. (2021). Weather and climate extreme events in a changing climate.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eStephens, G. L., \u0026amp; Ellis, T. D. (2008). Controls of global-mean precipitation increases in global warming GCM experiments. Journal of Climate, 21(23), 6141\u0026ndash;6155.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSuriano, Z. J., \u0026amp; Guercio, H. L. (2024). A snowfall climatology of the Ohio River Valley, USA. Theoretical and Applied Climatology, 155(8), 7691\u0026ndash;7701.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSwain, D. L., Wing, O. E., Bates, P. D., Done, J. M., Johnson, K. A., \u0026amp; Cameron, D. R. (2020). Increased flood exposure due to climate change and population growth in the United States. Earth's Future, 8(11), e2020EF001778.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTcvetkov, P. (2021). Climate policy imbalance in the energy sector: Time to focus on the value of CO2 utilization. Energies, 14(2), 411.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTorma, C., \u0026amp; Giorgi, F. (2020). On the evidence of orographical modulation of regional fine scale precipitation change signals: The Carpathians. Atmospheric Science Letters, 21(6), e967.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTrenberth, K. E. (2011). Changes in precipitation with climate change. Climate research, 47(1\u0026ndash;2), 123\u0026ndash;138.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTrenberth, K., Dai, A., van der Schrier, G. et al., (2014). Global warming and changes in drought. \u003cem\u003eNature Clim Change 4, 17\u0026ndash;22\u003c/em\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVance, T., Kiem, A., Roberts, J., Jong, L., Plummer, C. et al.(2020, May). An annually dated Interdecadal Pacific Oscillation reconstruction spanning the last two millennia. In EGU General Assembly Conference Abstracts (p. 6218).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWahl, T., Jain, S., Bender, J., Meyers, S. D., \u0026amp; Luther, M. E. (2015). Increasing risk of compound flooding from storm surge and rainfall for major US cities. Nature Climate Change, 5(12), 1093\u0026ndash;1097.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWeaver, S. J., and S. Nigam, 2008. Variability of the Great Plainslow-level jet: Large-scale circulation context and hydroclimate impacts. J. Clim. 21: 1532\u0026ndash;1551.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWestra, S., Renard, B., \u0026amp; Thyer, M. (2015). The ENSO\u0026ndash;precipitation teleconnection and its modulation by the interdecadal Pacific oscillation. Journal of Climate, 28(12), 4753\u0026ndash;4773.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWoolway, R.I., Kraemer, B.M., Lenters, J.D. et al., (2020). Global Lake Responses to Climate Change. \u003cem\u003eNat Rev Earth Environ 1, 388\u0026ndash;403\u003c/em\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWu, S. Y. (2015). Changing characteristics of precipitation for the contiguous United States. Climatic Change, 132, 677\u0026ndash;692.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWuebbles, D. J., \u0026amp; Hayhoe, K. (2004). Climate change projections for the United States Midwest. Mitigation and adaptation strategies for global change, 9, 335\u0026ndash;363.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhang, W., \u0026amp; Villarini, G. (2019). On the weather types that shape the precipitation patterns across the US Midwest. Climate Dynamics, 53(7), 4217\u0026ndash;4232.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhu, J., \u0026amp; Liang, X. Z. (2013). Impacts of the Bermuda high on regional climate and ozone over the United States. Journal of Climate, 26(3), 1018\u0026ndash;1032.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"},{"header":"Supplementary Informations","content":"\u003cp\u003eSupplementary Figure S1 and Table S1 are not available with this version.\u003c/p\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Kent State University","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"precipitation, Midwest United States, winter, extreme gradient boosting, fingerprint, global warming, climate signals","lastPublishedDoi":"10.21203/rs.3.rs-5574842/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5574842/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eGlobal warming is a significant challenge of the 21st century, driving notable changes in weather patterns. On the other hand, the Interdecadal Pacific Oscillation (IPO) is a remarkable climatic mode of variability that impacts interdecadal climate patterns and the rate of global warming. This study introduces the extreme gradient boosting (XGBOOST) feature important metric, to disentangle and rank the fingerprints of global warming and IPO on the seasonal precipitation trends in Ohio, United States, a region characterized by variable weather. Using monthly precipitation data from 55 weather stations spanning 1960\u0026ndash;2023, seasonal average trends for boreal winter, spring, summer, and autumn were analyzed using Theil-Sen\u0026rsquo;s Slope method, and statistical significance was tested at the 95% confidence level. Results indicate a significant increase in precipitation during winter (0.15 mm/decade) and summer (0.13 mm/decade), while no statistically significant changes were observed for spring and autumn. Correlation analysis revealed that 56.4% of the stations showed statistically significant positive correlations between global warming signals and increased winter precipitation. In comparison, 40% of the stations negatively correlated with the IPO during winter. Therefore, global warming and the negative IPO phase are associated with the observed increase in winter precipitation in most of the analyzed stations. In 60% of the stations, including stations impacted by the lake-effect snow, the XGBOOST model showed that the fingerprint of global warming ranked higher than the IPO. This indicates that global warming has a stronger association with the observed positive winter precipitation trend in most stations, and the IPO's net effect is limited to a smaller number of stations (i.e., 40%). These findings highlight that Ohio\u0026rsquo;s winters are becoming wetter with global warming remarkably contributing to it.\u003c/p\u003e","manuscriptTitle":"Application of XGBOOST in Disentangling the Fingerprints of Global Warming and Interdecadal Pacific Oscillation on Seasonal Precipitation Trends in Ohio","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-12-05 17:08:07","doi":"10.21203/rs.3.rs-5574842/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"863ca97a-e645-40a0-8b0a-cb114e39b186","owner":[],"postedDate":"December 5th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-12-05T17:08:07+00:00","versionOfRecord":[],"versionCreatedAt":"2024-12-05 17:08:07","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5574842","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5574842","identity":"rs-5574842","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}