Assessing groundwater quality is vital for irrigation, but financial constraints in developing countries often result in infrequent sampling. This study comprehensively analyzes the groundwater quality of the El Moghra aquifer in Egypt's arid Western Desert, for its suitability for irrigation uses. Detailed hydrochemical analysis and advanced machine learning (ML) techniques, including geographic information systems, were employed to enhance spatial analysis and predictive accuracy. Various ML models, such as random forest, adaptive boosting, and extreme gradient boosting (XGBoost), were optimized using Bayesian optimization to predict the irrigation water quality index (IWQI) accurately. The evaluation incorporated visual and quantitative methods, alongside ranking analysis, to validate model effectiveness. Shapley Additive exPlanations feature importance analysis and a graphical user interface (GUI) model were developed based on the best predictive model. The results indicated that the groundwater quality is generally suitable for irrigation, with XGBoost showing the best performance, achieving a root mean square error of 5.602 and a determination coefficient (R²) of 0.872. Sodium concentration was identified as the most significant factor affecting the IWQI. The GUI facilitates easy prediction of IWQI, aiding agricultural water management and resource allocation within the region.

The Slide2 model was used to estimate seepage losses from canals after validation considering different canal geometries, lining thicknesses, and lining materials. SPSS was used to develop three models: NLR, MLP-ANN, and RBF-ANN. MATLAB software was used to write down the script code for the ANNs. Results showed that seepage losses were highly increased when the liner had high hydraulic conductivity, while with the increase of lining thickness, a noticeable reduction in seepage losses was obtained. The canal's side slope had a minimal effect on the seepage losses. Moreover, the MLP-ANN and RBF-ANN models performed better than the NLR model with determination coefficient (R²) of 0.996 and 0.965; Root-Mean-Square-Error (RMSE) of 1.172 and 0.699; Mean-Absolute-Error (MAE) of 0.139 and 0.528; index of agreement (d) = 0.999 and 0.991, respectively. The NLR model had lower values of R² = 0.906, RMSE = 1.198, MAE = 0.942, and d = 0.971. Thus, ANNs are recommended as a robust, easy, simple, and rapid tool for estimating seepage losses from lined trapezoidal irrigation canals.

The use of fertilizers in agriculture in Egypt, especially nitrogen, has increased significantly in the last decade, resulting in nonpoint contamination of the groundwater resources. This study investigated the effect of using nitrogen fertilizer on groundwater contamination with nitrate in the central southern part of the Nile Delta. NO3− concentrations in shallow groundwater were assessed based on the applied urea dose (the common nitrogen fertilizer used) in year 2014. A groundwater modeling system (GMS) comprising MODFLOW and MT3D was used to simulate the three-dimensional groundwater flow and NO3− transportation processes in El-Menoufia Governorate, located in the central region of the Nile Delta aquifer. Calibration for MODFLOW was conducted to match known head configurations to minimize the water balance differences. Calibration of MT3D was accomplished by fitting the model to the measured NO3− concentrations during the year 2014. The results highlighted areas of groundwater contamination by NO3−, which occurred at shallow depths (40 m) due to the significant loads of nitrogen fertilizer application and the flood irrigation method. While the results suggested one approach was to avoid using contaminated shallow groundwater as a water source, a more sustainable approach would be to implement best management practices to reduce and control the amount of nitrate leaching into the shallow groundwater system in the future.