Atif Foufou

In semi-arid regions, sustainable groundwater management for irrigation is critical for agricultural productivity and food security. This study presents an integrated methodological framework combining hydrochemical characterization, machine learning (ML) modeling, and explainable artificial intelligence (XAI) to predict the Irrigation Water Quality Index (IWQI) in the Ain Oussera plain, Djelfa Province, Algeria. A total of 191 groundwater samples were collected from November 2023 to September 2024 and analyzed for major ions and physicochemical parameters. Multiple irrigation suitability indices were calculated, including Sodium Adsorption Ratio (SAR), Sodium Percentage (Na%), Magnesium Hazard (MH), Permeability Index (PI), Residual Sodium Carbonate (RSC), Soluble Sodium Percentage (SSP), and Kelly’s Ratio (KR). Five ML models were developed and evaluated for IWQI prediction: Random Forest, Gradient Boosting, XGBoost, K-Nearest Neighbors, and Support Vector Regression. Results showed that 55% of groundwater samples exhibited low to no restrictions for irrigation use, while 19% required high to severe restrictions. The XGBoost model demonstrated superior performance, with the highest R² (0.95) and the lowest RMSE (3.22) among all tested algorithms. SHAP (SHapley Additive exPlanations) analysis provided a transparent interpretation of model predictions, identifying electrical conductivity and Sodium Adsorption Ratio as the most influential parameters affecting IWQI, while chloride, sodium, total hardness, and magnesium had minimal impact. Spatial mapping using Inverse Distance Weighting (IDW) interpolation in ArcGIS 10.8 revealed considerable spatial variability in water quality throughout s the plain. This research addresses a critical gap in North African groundwater management by integrating ML predictive capabilities with XAI transparency, providing water resource managers and agricultural stakeholders with interpretable, data-driven tools for sustainable irrigation planning in water-stressed semi-arid environments.

The massive dune aquifer of Bouteldja is one of the most exploited aquifers in Algeria; as a result, its piezometric level has declined. Such pressure on the dune aquifer, in addition to its moderate-to-severe vulnerability to pollution, may lead to deterioration of groundwater quality. This...

Drought is considered a natural hazard and has become a recurrent phenomenon in Algeria since the 1970s. Algeria is characterized by three different climates, namely, sub-humid, semi-arid and arid climates. In this study, we aimed to spatiotemporally assess drought hazard, vulnerability and risk in the three climates of three sub-basins, namely, the Seybouse Maritime, Wadi Djelfa-Hadjia and Wadi M’Zi sub-basins. To this end, the standardized precipitation index (SPI) and the reconnaissance drought index (RDI) were used to evaluate drought physical characteristics on a 12-month timescale, based on precipitation and temperature monthly data covering the period of 1979–2019. High values of the coefficient of determination (R²) (0.76–0.99) confirmed by low values of the root-mean-square error (RMSE) (0.08–0.49) proved that the drought indices displayed a high correlation. Drought hazard and vulnerability were evaluated based on physical characteristics and socioeconomic aspects, respectively. The results led to the determination of a high correlation between the two indices used; the determination of the main drought events; and the mapping of the drought hazard, vulnerability and risk using a geographic information system (GIS). These findings suggest that the SPI provided the highest intensities, while the longest periods and the strongest magnitudes were given by the RDI. The spatiotemporal drought distributions varied with time from station to station and from sub-basin to sub-basin. Risk maps revealed that vulnerability based on socioeconomic factors controls drought risk.