Predicting groundwater levels is challenging, especially in regions of water scarcity where data availability is often limited. However, these regions have substantial water needs and require cost-effective groundwater utilization strategies. This study uses artificial intelligence to predict groundwater levels to provide guidance for drilling shallow boreholes for subsistence irrigation. The Bilate watershed, located 80 km north of Arba Minch in southern Ethiopia and covering just over 5250 km², was selected as the study area. Bilate is typical of areas in Africa with high demand for water and limited availability of well data. Using a non-time series database of 75 boreholes, machine learning models, including multiple linear regression, multivariate adaptive regression splines, artificial neural networks, random forest regression, and gradient boosting regression (GBR), were constructed to predict the depth to the water table. The study considered 20 independent variables, including elevation, soil type, and seasonal data (spanning three seasons) for precipitation, specific humidity, wind speed, land surface temperature during day and night, and Normalized Difference Vegetation Index (NDVI). GBR performed the best of the approaches, with an average 0.77 R-squared value and a 19 m median absolute error on testing data. Finally, a map of predicted water levels in the Bilate watershed was created based on the best model, with water levels ranging from 1.6 to 245.9 m. With the limited set of borehole data, the results show a clear signal that can provide guidance for borehole drilling decisions for sustainable irrigation with additional implications for drinking water.

Crop water requirement and irrigation scheduling in Lower Kulfo Catchment of southern Ethiopia have not assessed under climate change scenarios, and the allocation of crop land also not optimal that signifcantly challenges to crop productivity.Therefore, this study was conducted to evaluate the effects of climate change on future crop water requirements, and irrigation scheduling, and to allocate cropland optimally. Bias of projected precipitation and temperature were corrected by utilizing Climate Model data with the hydrologic modeling tool (CMhyd). Alongside, crop water requirements and irrigation scheduling were assessed using Crop Water Assessment Tool. After estimating crop water requirement, crop land were allocated optimally using General Algebraic Modeling System programming with non-negativity constraints (scenario 1), and non-negativity constraints based on farmers adaptation (scenario 2). Average reference evapotranspiration from 2030 to 2050 and 2060 to 2080 was increased by 11.9 %, and 16.2 %, respectively compared with the reference period (2010–2022). The total seasonal crop water requirements were 4,529 mm, 4866.7 mm, and 5272.2 mm under 2010 to 2022, 2030 to 2050, and 2060 to 2080 climate change scenarios, respectively. The meean irrigation interval in 2010–2022, 2030 to 2050, and 2060 to 2080 climate change scenarios were 8 days, 7 days, and 5 days, respectively. This irrigation interval was decreased by 14 % (2030–2050), and 34 % (2060–2080) compared with the reference period. In 2030 to 2050 and 2026 to 2080 climate change scenarios, the required irrigation water at the inlet of main canal increased by 6.8 %, and 18 %, respectively. The optimal allocated area for tomato (60.4 %), maize (20.8 %), and watermelon (18.8 %) in scenario 1 with net benefit of 1.47*108 Ethiopian Birr. The allocated areas in scenario 2 were (48 %) for maize, (31.6 %) for tomato, and (20.4 %) for watermelon with 1.34*10⁸ Ethiopian Birr net benefit it was reduced by 19.1 % compared with the net benefit in scenario 1. Fruit crops alone may not suffice for local food needs and to address this, small farmers should grow maize, tomato, and watermelon. This research aids policymakers in encouraging climate-resilient agriculture and improving small-scale farmers' awareness through conducting workshops and training.

In water scarcity regions, using data-driven approaches to predict groundwater level is challenging due to limited data availability. However, these regions have substantial water needs and require cost-effective groundwater utilization strategies. In this study, we use artificial intelligence to predict groundwater levels to provide guidance for drilling shallow boreholes for subsistence irrigation. The Bilate watershed, which is located in southern Ethiopia, was selected as the study area. This is typical of areas in Africa with high demand for water and limited availability of well data. Using a non-time-series database of 75 boreholes, machine learning models including multiple linear regression, multivariate adaptive regression spline, artificial neural networks, random forest regression, and gradient boosting regression (GBR) were constructed to predict the depth to the water table. 20 independent variables were considered in the models. GBR performed the best of the approaches with an average 0.77 R-squared value on testing data. Finally, a map of predicted water levels in the Bilate watershed was created based on the best model with water levels ranging from 1.6 to 245.9 meters. With the limited set of borehole data, the results show a clear signal that can provide guidance for borehole drilling decisions for sustainable irrigation with additional implications for drinking water.