Evaluating water quality indicators is a crucial issue in integrated water resource management, since potable water is an essential resource for the world’s health and sustainable development. The current study was developed using a coupled model of MODFLOW and MT3DMS (Mass Transport 3-Dimension Multi-Species) to integrate two water supply systems, surface water (polluted drains and canals) and ground water, to identify the contamination process of the groundwater from drains as fresh water is polluted and the contamination level exceeds the standard limits. The study was applied to two cases: the first was a hypothetical simulation and the second was the real case of the Nile Delta Aquifer (NDA). Four different scenarios were simulated to first identify groundwater contamination by total dissolved solids (TDS), and then select the more efficient protection process. The first scenario involved changing polluted drain and canal boundary conditions regarding head and concentration; the second consisted of studying the location of the polluted drain in a low permeability layer or a confined aquifer; the third was based on installing a cut-off wall in the polluted drain sides; and the fourth investigated the use of lining materials for polluted drains. The results reveal that aquifer contamination was decreased by increasing the water head of canals by 50 cm and decreasing the drain head by 50 cm and concentration by 25%, whereby large quantities of groundwater were protected. The percentages of salt repulsion in the hypothetical case were +10.66, +12.89, and +24.99%, while in NDA they were +6.29, +8.71, and +25% respectively compared with the base case. Decreasing the aquifer hydraulic conductivity led to decrease in aquifer contamination, in which the confined aquifer pollution was less than the unconfined aquifers due to the clay cap, which plays a significant role in minimizing the solute transport into the groundwater reservoir, and to reduction of the aquifer salt variation by +19.01% for the hypothetical case. The results indicate that the cut-off wall is effective for contamination management in shallow aquifers (hypothetical case) and the reduction in aquifer salt was +28.49%, whereas it had no effect in the deep aquifer (NDA), where the salt was reduced by just +0.34%. Using the drain lining scenario prevented contamination from the polluted drains and protected the freshwater in the aquifer, so that the aquifer salt mass reductions were +91.02 and +70.13% for the hypothetical case and NDA respectively, indicating that this method is more effective for controlling groundwater contamination. Polluted drains should be located in a low permeability layer to minimize the water degradation. This study represents a new contribution to groundwater protection techniques by changing the boundary conditions, installing a cut-off wall and using linings for polluted drains, and shows the way forward for the future treatment of polluted stream networks.

Water quality assessment is paramount for environmental monitoring and resource management, particularly in regions experiencing rapid urbanization and industrialization. This study introduces Artificial Neural Networks (ANN) and its hybrid machine learning models, namely ANN-RF (Random Forest), ANN-SVM (Support Vector Machine), ANN-RSS (Random Subspace), ANN-M5P (M5 Pruned), and ANN-AR (Additive Regression) for water quality assessment in the rapidly urbanizing and industrializing Bagh River Basin, India. The Relief algorithm was employed to select the most influential water quality input parameters, including Nitrate (NO₃⁻), Magnesium (Mg²⁺), Sulphate (SO₄²⁻), Calcium (Ca²⁺), and Potassium (K⁺). The comparative analysis of developed ANN and its hybrid models was carried out using statistical indicators (i.e., Nash-Sutcliffe Efficiency (NSE), Pearson Correlation Coefficient (PCC), Coefficient of Determination (R²), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Relative Root Square Error (RRSE), Relative Absolute Error (RAE), and Mean Bias Error (MBE)) and graphical representations (i.e., Taylor diagram). Results indicate that the integration of support vector machine (SVM) with ANN significantly improves performance, yielding impressive statistical indicators: NSE (0.879), R² (0.904), MAE (22.349), and MBE (12.548). The methodology outlined in this study can serve as a template for enhancing the predictive capabilities of ANN models in various other environmental and ecological applications, contributing to sustainable development and safeguarding natural resources.

The estimation of reference evapotranspiration (ET_o), a crucial step in the hydrologic cycle, is essential for system design and management, including the balancing, planning, and scheduling of agricultural water supply and water resources. When climates vary from arid to semi-arid, and there are problems with a lack of meteorological data and a lack of future information on ET_o, as is the case in Egypt, it is more important to estimate ET_o precisely. To address this, the current study aimed to model ET_o for Egypt’s most important agricultural governorates (Al Buhayrah, Alexandria, Ismailiyah, and Minufiyah) using four machine learning (ML) algorithms: linear regression (LR), random subspace (RSS), additive regression (AR), and reduced error pruning tree (REPTree). The Climate Forecast System Reanalysis (CFSR) of the National Centers for Environmental Prediction (NCEP) was used to gather daily climate data variables from 1979 to 2014. The datasets were split into two sections: the training phase, i.e., 1979–2006, and the testing phase, i.e., 2007–2014. Maximum temperature (T_max), minimum temperature (T_min), and solar radiation (SR) were found to be the three input variables that had the most influence on the outcome of subset regression and sensitivity analysis. A comparative analysis of ML models revealed that REPTree outperformed competitors by achieving the best values for various performance matrices during the training and testing phases. The study’s novelty lies in the use of REPTree to estimate and predict ET_o, as this algorithm has not been commonly used for this purpose. Given the sparse attempts to use this model for such research, the remarkable accuracy of the REPTree model in predicting ET_o highlighted the rarity of this study. In order to combat the effects of aridity through better water resource management, the study also cautions Egypt’s authorities to concentrate their policymaking on climate adaptation.