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.

As part of environmental preservation and sustainable water resource management actions, particularly in a semi-arid region, an annual monitoring program was carried out in 2024 to assess the treatment performance and environmental compliance of the Djelfa city wastewater treatment plant. This...

Despite global efforts to reduce landfill use for municipal waste, many sites remain active, and older closed sites still require management, particularly regarding leachate. Landfill leachate contains varying levels of organic and inorganic pollutants, generated through biological and physicochemical processes following water infiltration. Its complex composition—including COD, inorganic macro-components, heavy metals, and xenobiotics—necessitates effective treatment technologies to enable safe discharge into surface waters. This study compares low-cost, eco-sustainable adsorbents for the removal of ammonium, trace elements (Cd, Be, Fe, Cu, Ni, Pb, Cr, As, Sn, Sb, Se), and color (as an indirect measure of organic compounds) from urban landfill leachate. In more detail, six biochars from different biomass feedstocks and pyro-gasification conditions as well as natural chabazite and synthetic zeolite 13X (FAU-type) were investigated. After characterization, biochars were characterized and adsorption performance was assessed. Removal performance was comparatively evaluated after 24 h batch contact under fixed experimental conditions. Results showed that gasified biochars achieved high removal efficiency for metals and color but were ineffective for ammonium. Instead, both zeolites demonstrated efficient ammonium removal (~50%) but were less efficient for metals, reflecting the mechanism-driven selectivity of the adsorbents studied. Finally, a principal component analysis (PCA) revealed correlations between biochar physicochemical properties and contaminant retention, providing insight into key factors governing adsorption and informing the design of sustainable leachate treatment strategies.

In this investigation, we studied the removal of two cationic dyes, methyl green MG and malachite green Mc G, by a commercial adsorbent. This adsorbent is a F400 activated carbon with a specific surface area of 1203 m2. g-1, which is expected to be high compared with ordinary adsorbents. Adsorption tests were carried out on both dyes in batch mode. The results show that both kinetics are fast, with equilibrium reached after 20 minutes and 30 minutes respectively for Methyl Green and Malachite Green. The kinetics of both dyes are well adapted to pseudo-second order, and for the intraparticle diffusion model, two lines can be distinguished for each dye, proving the existence of two adsorption steps. The isotherm for this system reveals an L-type shape for both dyes, in line with the classification of Giles & al. so there is little competition for sorption sites between solvent and adsorbate. The adsorption isotherms for methyl green by PAC obeyed the Langmuir, Freundlich and Temkin models, while that for malachite green followed only the Langmuir isotherm, with a much higher maximum amount.