This study focuses on assessing the hydrogeochemical characteristics and irrigation suitability of groundwater in the Ras El Aioun and Merouana districts, using an integrated approach that combines physicochemical analysis, machine learning (ML), and Geographic Information Systems (GISs). Thirty groundwater samples were collected in June 2023 and subjected to extensive analyses, including major ions (Ca²⁺, Mg²⁺, Na⁺, K⁺, HCO₃⁻, Cl⁻, SO₄²⁻), pH, TDS, alkalinity, and hardness. Hydrochemical facies analysis revealed that the Ca-HCO₃ type was dominant (93.33%), with some samples exceeding FAO limits, particularly for Na⁺, K⁺, SO₄²⁻, Cl⁻, Mg²⁺, and HCO₃⁻. Assessment of groundwater irrigation suitability revealed generally favorable conditions based on three key parameters: all samples (100%) were classified as excellent based on the Sodium Adsorption Ratio (SAR < 10), 70% showed good-to-permissible status by Sodium Percentage (Na% < 60), and 83.3% were within safe limits for Residual Sodium Carbonate (RSC < 1.25 meq/L). However, the Permeability Index (PI > 75%) categorized 96.7% of samples as unsuitable for long-term irrigation due to potential soil permeability reduction. Additionally, Total Hardness (TH < 75 mg/L) indicated predominantly soft water characteristics (90% of samples), particularly in the central study area, suggesting possible limitations for certain agricultural applications that require mineral-rich water. GIS-based spatial analysis showed that irrigation suitability was higher in the eastern and western regions than in the central zone. Advanced machine learning algorithms provide superior predictive capability for water quality parameters by effectively modeling complex, non-linear feature interactions that conventional statistical approaches frequently fail to capture. Three ML models—Support Vector Regression (SVR), Random Forest (RF), and Extreme Gradient Boosting (XGBoost)—were used to predict the Irrigation Water Quality Index (IWQI). XGBoost outperformed the others (RMSE = 2.83, R² = 0.957), followed by RF (RMSE = 3.12, R² = 0.93) and SVR (RMSE = 3.45, R² = 0.92). Integrating ML and GIS improved groundwater quality assessment and provided a robust framework for sustainable irrigation management. These findings provide critical insights for optimizing agricultural water use in water-scarce regions.

Considering three sites under different climate conditions (arid, semi-arid, and subhumid), this study aims to use the vadose-zone water stable isotope profiles to estimate the groundwater recharge rate. High-resolution vertical subsurface soil sampling along the vadose zone of the investigated sites was conducted. The collected samples were analysed to determine their stable isotope ratios (δ²H and δ¹⁸O) that were used along with the piston displacement method to estimate recharge. Annual recharge rates of 0.2% (± 0.1%), 2.5%, and 18% of the total annual precipitation were obtained for the arid, semi-arid, and subhumid sites, respectively. Recharge rates at the semi-arid and subhumid sites are comparable to those previously estimated using water balance-based methods. The recharge rate at the arid site is lower than that previously estimated for that site using the water budget-based method, revealing difficulties in applying the piston displacement method under an arid regime.

Most Middle Eastern and North African regions are characterized by an arid and semi-arid climate. As such, the drinking water supply and management have become a challenging task for local and regional authorities. The Mio-Plio Quaternary aquifer of the Barika area is the only drinking and irrigation water reservoir in the region. The objective of this paper is to identify the origin and evolution process of the groundwater mineralization of this aquifer using major elements as indicators. To achieve this objective water samples were collected, from several boreholes drilled in the aquifer, in June 2018 and March 2019, and subsequently analyzed. The results obtained in terms of Gibbs plot, Piper, chemical correlation, and statistical analysis of chemical data identified the origins of groundwater mineralization. The dissolution of evaporated minerals, precipitation of carbonates, evapotranspiration, and ion exchange reactions have been identified as the primary processes of mineralization. The results of the physicochemical analysis showed that these waters consisted mainly of chloride, calcium sulfate, and magnesium facies types with a slight change of facies in some boreholes during the two sampling periods. This is due to the interactions with the-aquifer geology and to the water scarcity caused by climate change.

In this study, a new approach integrating a groundwater vulnerability method and a numerical model for predicting groundwater resource sustainability under actual and future conditions of exploitation (2010–2030) is proposed in the semi-arid region of the Tebessa-Morsott alluvial aquifer (northeastern Algeria). The groundwater vulnerability method-based DRASTIC model was used to evaluate and delineate the vulnerable areas using a GIS technique. The MODFLOW code, on the other hand, was used to calculate the dynamics of groundwater level under actual and future conditions of exploitation considering two scenarios. The results of the application of the DRASTIC method to the reference year conditions (year 2010) showed that the high and average vulnerability classes covered a wide zone of the study area, about 97%. These results were validated based on the nitrate concentration values (R² = 0.955). However, the results for predicting future groundwater vulnerability showed that groundwater vulnerability variation over time (period 2010–2030) was closely related to groundwater depth variation caused by the pumping rate, since the decreases in the piezometric level produce a worsening of groundwater vulnerability. To achieve better groundwater management, an experimental site for artificial recharge supplemented by hydro-chemical monitoring of the groundwater could be an effective remediation strategy.

The region of Chelghoum Laid - Tadjenanet is located in the east of Algeria in the high southern plains of Setif, characterized by a highly vulnerable shallow alluvial aquifer. The vulnerability of groundwater to pollutants is a relative concept, not measurable or dimensional. The nature, quality, and reliability of used data used have a major impact on the correctness of its assessment. Its classification is usually based on the estimation of many more or less essential factors, such as the characteristics of soil and unsaturated zone, the saturated zone, the recharge , the topography and the hydraulic conductivity. The vulnerability of the aquifer to pollution was investigated using two intrinsic vulnerability methods: DRASTIC and susceptibility index (SI). SI method is an adaptation of the DRASTIC specifically design for nitrate-based pollution. The parameters used as input data are, among others, the depth of the groundwater, the soil type, the topographic slope and the groundwater recharge. The validity of the two methods for assessing the vulnerability to nitrates was established by comparing the distribution of these elements in groundwater with the distribution of the various vulnerability classes. GIS techniques were used to implement these methods. Vulnerability maps created using the DRASTIC and SI method’s depict the potential for pollutants to penetrate and spread in these locations depending on the terrain encountered on the surface and the depth of the aquifer. The comparison revealed that the SI technique is the most accurate in the studied alluvial aquifer. The establishment of the pollution vulnerability map highlighted an area of great vulnerability in the center of the plain, reflected by the fragility of the soil and the shallow depth of the water. While the average vulnerability areas are in the center, and east at the periphery of Wadi Rhumel, the rest of the field is slightly vulnerable. The vulnerability and contamination risk maps created for this study are valuable tools for environmental planning and can be used for predictive management of groundwater resources. This case study suggests that the approach may be applicable to other areas as part of efforts to target groundwater management efforts.