Elias Getahun

Accurate prediction of nitrate‑nitrogen (NO₃‑N) and total phosphorus (TP) loads is critical for managing water quality in agricultural watersheds, where excess nutrient runoff can contribute to downstream eutrophication. This study applies Random Forest (RF) regression and conditional inference RF to predict monthly NO₃‑N and TP loads at eight monitoring gages within Conservation Reserve Enhancement Program (CREP) watersheds in the Illinois River and Kaskaskia River basins. The machine learning (ML) models were trained using hydroclimatic, land‑use, and nutrient datasets from 2000–2022 and validated with 2023 observations.The predictor variables included discharge, precipitation, temperature, land use, total Kjeldahl nitrogen (TKN), suspended sediment, and septic system density in the watersheds. Multiple modeling strategies were evaluated, including full‑feature, reduced‑feature (i.e., derived through importance thresholds or removal of collinear nutrient variables), and hyperparameter‑tuned configurations. Model performance was assessed using Nash–Sutcliffe Efficiency (NSE), R², and RMSE, and interpretability was evaluated through feature‑importance metrics and SHAP analyses.Monthly Random Forest models effectively captured seasonal nutrient dynamics. Discharge consistently emerged as the dominant predictor of NO₃‑N loads, while interactions among variables, particularly TKN and suspended sediment, played major roles in predicting TP. Land use and septic system density exhibited limited predictive influence. Model performance was strong across configurations, with training NSE values exceeding 0.95 and validation NSE frequently above 0.9. However, reduced skill during summer and fall suggested the influence of unrepresented processes such as evapotranspiration. The most stable performance across sites and seasons was achieved with hyperparameter‑tuned, full‑feature models. SHAP analyses revealed clear linkages between hydrologic and biogeochemical processes, while Spearman correlation heatmaps highlighted strong covariation among nutrient loads and moderate coupling with climatic variables.These results demonstrate the value of machine‑learning approaches such as RF as complementary alternatives to process‑based models like SWAT, offering robust tools for informing nutrient‑reduction strategies and supporting policy decisions in impaired agricultural watersheds.

Climate change and increasing water demand are critical factors influencing water availability and the hydrologic cycle. This study examines their combined impacts on the Kaskaskia River watershed in Illinois, USA, using a comprehensive hydrologic modeling approach. The model integrates key watershed components, including existing reservoirs, multiple water withdrawal sources, and point source discharges, with necessary modifications to the governing algorithms to accurately represent system processes. A daily target release method was implemented for routing water through the watershed’s two main reservoirs, significantly improving the accuracy of storage and outflow simulations. A total of 68 hydrologic scenarios were simulated, combining 17 climate projections with four water demand patterns. Results reveal that climate change exerts a substantial influence on river flows and reservoir storages, while the effects of projected water demand are comparatively minor. Under RCP2.6, RCP4.5, and RCP8.5 scenarios, minimum storage volumes in both reservoirs are projected to decline over the next 25 to 50 years, while maximum storage volumes are expected to increase, indicating greater variability in reservoir levels. Despite these changes, future water yields from both reservoirs are projected to exceed current yields across all scenarios. These findings underscore the importance of adopting sustainable water resource management strategies to address the challenges posed by climate variability and evolving water demands, ensuring long-term water security in the region. Furthermore, as water availability is also constrained by water quality, future enhancements to the model should incorporate water quality simulations to assess the impacts of sediment and nutrient loads on overall water availability.

Global climate change can alter precipitation patterns and temperatures, impacting regional hydrologic cycles and river flows, potentially leading to supply deficits during peak use periods. Future water use patterns may shift due to increased demand for food and energy production driven by population growth. Anthropogenic activities, such as agriculture and power generation, can degrade water quality, affecting its availability for various uses. This study evaluates the impacts of climate change and water demand on water availability in the Kaskaskia River watershed, Illinois, USA. The Kaskaskia River, the second largest river in Illinois, flows southwest to its confluence with the Mississippi River. Lake Shelbyville and Carlyle Lake, the two principal reservoirs on the mainstem of the Kaskaskia River, serve as primary sources of water supply in the region. Both reservoirs, federally owned, are operated and managed by the United States Army Corps of Engineers (USACE) to meet water demand in the watershed, including water supply, flood control, navigation, and recreational needs. The land use of the Kaskaskia River watershed is primarily agricultural, with row crops covering more than 60 percent of the area. Two-thirds of the watershed soil has moderately low infiltration capacity. The region receives an average annual precipitation of 1,041 millimeters. A detailed hydrologic model of the Kaskaskia River watershed was developed, incorporating modifications to watershed process algorithms and implementing a daily target release method for the reservoirs, which significantly improved storage and outflow simulations. The modeling process involved developing four subwatershed models with HUC12 as their subbasins and further subdividing subbasins into hydrologic response units (HRUs) to enhance simulation granularity. The model also incorporated Lake Shelbyville and Carlyle Lake, along with point sources and water withdrawals. Calibration and validation across the models and reservoirs, involving sensitivity analysis and automatic calibration, yielded good performance metrics. The model accurately simulated streamflow and reservoir dynamics, providing reliable predictions. The calibrated models were integrated into a single Kaskaskia River watershed model, which was then applied to simulate future water use and climate scenarios, offering insights into potential hydrologic impacts. The findings revealed that climate change significantly impacts river flows and reservoir storages, while water use has minimal effects. Under RCP2.6, RCP4.5, and RCP8.5 scenarios, minimum storage volumes of both reservoirs are projected to decrease over the next 25 and 50 years, while maximum storage volumes are expected to increase. Future water yields of both reservoirs are anticipated to exceed current yields, underscoring the need for sustainable water resource management amidst climate variability and changing demands. The study highlights the importance of adaptive water resource management to mitigate climate change impacts and ensure long-term sustainability.

Applying road salt to melt ice on urban roads and pavements has raised the chloride levels in streams and rivers in the U.S. over time, which can damage aquatic life. High chloride levels in the waterbodies of the Fox River watershed, where one-third of the land is urban, are mainly caused by road salt application for deicing. This study analyzed how the chloride levels changed over the years and seasons in the Fox River watershed – from Stratton Dam to Illinois River. The Seasonal Kendall Tau (SKT) method was used to estimate the annual and seasonal trends in chloride concentration at 44 monitoring sites on the Fox River and its tributaries for three time periods (2017–2021, 2012–2021, and 1997–2021), after conducting exploratory data analysis and assessing the data suitability. The chloride concentration in the watershed varied over time, space, and season. From 2012 to 2021, it declined or remained stable at most of the monitoring sites, but it rose slightly from 1997 to 2021. The 5-year trend from 2017 to 2021 was similar, except that some sites showed an increase in summer and fall. The chloride concentration along the Fox River and Tyler Creek showed a longitudinal pattern, decreasing from upstream to downstream in most seasons and periods, except for the 5-year annual and fall trends, which increased. Weighted Regression on Time Discharge and Season (WRTDS) models were developed to estimate the trends in flow-normalized chloride flux for one site on the Fox River and two sites on its tributaries with daily flow data. The resulting trends indicate that the chloride fluxes dropped significantly at the Fox River and Polar Creek sites, mainly in the winter of 2012–2021. However, the site on Blackberry Creek had an opposite trend of increasing chloride flux, except for the winter flux, which also declined. Trends in selected streamflow statistics including mean, 7-day minimum, and 1-day maximum flows were also analyzed for the three monitoring sites to provide insight into how hydrologic variability affects chloride trends. The trends in annual and seasonal flow statistics exhibited a steep slope for low flows but a gradual slope for high flows, indicating more variability in the low flow statistics during the periods of analysis. The changes in chloride concentration and flux were partly related to the changes in flow, but other factors affecting water quality, such as watershed conservation, may also play a role. Assessing trends over distinct periods provides a nuanced understanding of how mitigation strategies may influence water quality improvements through the years and serves as a crucial guide for initiatives aimed at enhancing the overall health of the Fox River ecosystem. Choosing deicing methods that balance cost, performance, and environmental impacts should be a vital part of a mitigation plan. Moreover, monitoring and evaluating trends can help assess the current status of chloride levels in the watershed and inform future actions.

A nutrient loss reduction strategy is necessary to guide the efforts of improving water quality downstream of an agricultural watershed. In this study, the effectiveness of two winter cover crops, namely cereal rye and annual ryegrass, is explored as a loss reduction strategy in a watershed that ultimately drains into a water supply reservoir. Using a coupled optimization‐watershed model, optimal placements of the cover crops were identified that would result in the tradeoffs between nitrate‐N losses reduction and adoption levels. Analysis of the 10%, 25%, 50%, and 75% adoption levels extracted from the optimal tradeoffs showed that the cover crop placements would provide annual nitrate‐N loss reductions of 3.0%–3.7%, 7.8%–8.8%, 15%–17.5%, and 20.9%–24.3%, respectively. In addition, for the same adoption levels (i.e., 10%–75%), sediment (1.8%–17.7%), and total phosphorus losses (0.8%–8.6%) could be achieved. Results also indicate that implementing each cover crop on all croplands of the watershed could cause annual water yield reduction of at least 4.8%, with greater than 28% in the months of October and November. This could potentially be detrimental to the storage volume of the downstream reservoir, especially in drought years, if cover crops are adopted in most of the reservoir's drainage area. Evaluating water yield impacts, particularly in periods of low flows, is thus critical if cover crops are to be considered as best management practices in water supply watersheds.

Reservoir outflow is an important variable for understanding hydrological processes and water resource management. Natural streamflow variation, in addition to the streamflow regulation provided by dams and reservoirs, can make streamflow difficult to understand and predict. This makes them a challenge to accurately simulate hydrologic processes at a daily scale. In this study, three Machine Learning (ML) algorithms, Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Network (ANN), were examined and compared to model reservoir outflow. Past, current, and future hydrologic and meteorological data were used as model inputs, and the outflow of next day was used as prediction. Simulation results demonstrated that all three models can reasonably simulate reservoir outflow. For Carlyle Lake, the coefficient of determination and Nash–Sutcliffe efficiency were each close to one for the three models. The coefficient of determination, relative mean bias, and root mean square error indicated that the SVM performed better than the RF and ANN, but the SVM output displayed a larger relative mean bias than that from RF and ANN. For Lake Shelbyville, the ANN model performed better than RF and SVM when considering the coefficient of determination, Nash–Sutcliffe efficiency, relative mean bias, and root mean square error. The study results demonstrate that the three ML algorithms (RF, SVM, and ANN) are all promising tools for simulating reservoir outflow. Both the accuracy and efficacy of the three ML algorithms are considered to support practitioners in planning reservoir management.

Ensuring an adequate, reliable, clean, and affordable water supply for citizens and industries requires informed, long‐range water supply planning, which is critically important for water security. A balance between water supply and demand must be considered for a long‐term plan. However, water demand projections are often highly uncertain. Climate change could impact the hydrologic processes, and consequently, threaten water supply. Thus, understanding the uncertainties in future water demand and climate is critical for developing a sound water supply plan. In Illinois, regional water supply planning attempts to explore the impacts of future water demand and climate on water supply using scenario analyses and hydrologic modeling. This study is aimed at developing a water supply planning framework that considers both future water demand and climate change impacts. This framework is based on the Soil and Water Assessment Tool to simulate the watershed hydrology and conduct scenario analyses that consider the uncertainties in both future water demand and climate as well as their impacts on water supply. The framework was applied to water supply planning efforts in the Kankakee River watershed. The Kankakee River watershed model was calibrated and validated to observed streamflow records at four long‐term United States Geological Survey streamflow gages. Because of the many model parameters involved, the calibration process was automated and was followed by a manual refinement, resulting in good model performance. Long‐range water demand projections were prepared by the Illinois State Water Survey. Six future water demand scenarios were established based on a suite of assumptions. Climate scenarios were obtained from the Coupled Model Intercomparison Projection Phase 5 datasets. Three representative concentration pathways (RCPs), RCP2.6, RCP4.5, and RCP8.5, are used in the study. The scenario simulation results demonstrated that climate change appears to have a greater impact on water availability in the study area than water demand. The framework developed in this study can also be used to explore the impacts of uncertainties of water demand and climate on water supply and can be extended to other regions and watersheds.

This paper presents the use of evolutionary computation for simulating reservoir release rates that are central to developing hydrologic reservoir routing models for Lake Shelbyville and Carlyle Lake. The two lakes, which are located in the Kaskaskia River watershed in Illinois, are multipurpose reservoirs operated by the U.S. Army Corps of Engineers to meet flood control, water supply, navigation, recreation, and conservation needs. To date, the reservoir storages apportioned for water supply and navigation needs have not been fully utilized. The objective of the current study is to develop a model for examining the potential impacts of increased water supply and navigation uses on lake levels during severe drought conditions. The reservoirs have their own operating schedules that include ranges of seasonal release rates based on reservoir pool elevations. In this study, storage routing and multi-objective evolutionary algorithms were coupled to simulate reservoir release rates on weekly basis using long-term historical records of daily inflows, storages, reservoir pool elevations and outflows. The simulated weekly release rates for the two lakes complement their respective reservoir routing models and the modified reservoir routing models will ultimately be coupled with previously developed Kaskaskia River watershed model. The resulting coupled model will be able to provide simulations of storages and reservoir pool elevations for the two lakes under varying climate and water use conditions, in addition to simulating flows at different location in the Kaskaskia River watershed. The multiobjective evolutionary algorithm used in this study was effective in simulating the reservoir release rates and its application was instrumental in developing the modified reservoir routing models for Lake Shelbyville and Carlyle Lake.