Groundwater represents the main water resource for irrigation in the Ouled Djellal region (southeast of Algeria). Despite the importance of groundwater in this area, its quality and sustainability remain insufficiently studied. Therefore, this study aimed to introduce an integrated analytical framework by combining multivariate statistical techniques i.e., Principal Component Analysis (PCA) and Hierarchical Ascending Classification (HAC), irrigation indices (IWQI, SAR, Na%, SSP, PS, and RSC), and machine learning (ML) models such as Artificial Neural Network (ANN), Support Vector Machine (SVM), and Multiple Linear Regression (MLR) to assess and predict groundwater quality for irrigation. The main difference with previous studies is the fact that this work applied Empirical Bayesian Kriging Regression Prediction (EBKRP) to spatialize irrigation indices derived from ML with higher precision. The approach enables cross-validation of model performance and captures complex nonlinear interactions among hydrochemical parameters. The attained results revealed that groundwater quality was varied from moderate to poor for irrigation, driven mainly by salinity and sodicity effects. In addition, the ANN model achieved the highest predictive accuracy (R² = 0.97, RMSE = 1.50), confirming its superiority in modelling complex hydrochemical behavior. The proposed modelling framework represents a methodological advancement for data-scarce arid regions, serving as a practical tool adaptable to groundwater monitoring and irrigation planning in similar regions.

A hydrogeological study of the thermal source of Ouled Aïcha in the Aurès Mountains showed that the source emerges in a particular natural context mainly represented by the presence of a vertical fault in the NE-SW direction affecting Cretaceous limestone. This supports the increase on the surface of moderately hot water, whose temperature is approximately 30 °C and an exploited flow of 3 L·s-1. The vertical electric sounding in situ showed the in-depth presence of a saliferous conducting level within a calcareous-resistant mass, which probably settled in the fault's favor. The presence of this saliferous level strongly influences the hydrochemistry of this thermal source. Thus, the water from the source is characterized by high salinity due to its temperature, which favors the dissolution of mineral salts in sufficient quantity throughout its journey (12390 µS/cm). The high concentrations of chlorides, sodium and sulfates indicate a significant contribution of salt from evaporitic formations as for the calcium content indicates that this water is influenced by the dissolution of carbonate formations. These physicochemical characteristics provide this water therapeutic virtue, which can be attributed to its chemical composition, high rock salt content, and low nitrate content. Geothermometry has shown that these thermal waters acquire a high temperature in their original tanks coming from a depth through a fault system that affects the basement.

Evaluating hydrological trends is crucial for the sustainable management of water resources with the escalating impacts of climate change. This study assesses the Wadi Bouhamdane Basin in Northeast Algeria, integrating data from the Gravity Recovery and Climate Experiment (GRACE) and the Follow-On mission (GRACE-FO) with hydrological observations and modeling to provide insights into precipitation and runoff dynamics since 1991. Using techniques such as linear regression, the Mann–Kendall trend test, cumulative departure, mutation analysis, and Morlet wavelet transformations, we identified a declining trend in annual rainfall (− 36.85 mm/decade) and an increase in runoff (20.65 mm/decade). Our rainfall analysis projected droughts from 2018 to 2020 and a water-rich phase in 2024, with predicted fluctuations extending into 2025. GRACE/GFO data from 2002 to 2022 revealed consistent reductions in terrestrial water storage (~ 0.35 cm/year), marked declines during projected drought periods, and insights into post-drought recovery and water accumulation trends. These findings are consistent with the projected wet–dry fluctuations from 2021 to 2023 and suggest the onset of a wetter period around 2024. The runoff sequence is projected to maintain its slight upward trend from 2018 to 2019, with fluctuations from 2018 to 2020, a dry period from 2022 to 2024, and a predicted dry year in 2025. Our combined approach of satellite data with ground-based measurements highlights the complex interactions influencing hydrological responses in semi-arid regions. This study underscores the significance of merging conventional hydrological methods with advanced satellite observations to enhance water management precision and resilience, advocating for a multi-source data framework to inform sustainable water resource policies amid evolving climate conditions.

Groundwater from coastal aquifers plays a significant role in agriculture, but its diminishing of quality often impacts crop production and soil sustainability by leading to soil salinization and the deterioration of irrigation water standards. This study addresses the pressing issue at Mornang Plain in Tunisia utilizing an integrated approach that combines statistical analysis (principal component analysis (PCA) and cluster analysis (CA), geographic information system (GIS), and machine learning (ML) techniques to assess and predict irrigation water quality. Key parameters such as irrigation water quality index (IWQI), potential salinity (PS), sodium percentage (Na%), and sodium adsorption ratio (SAR) were evaluated to assess water quality for agricultural use. The study identified three main groundwater facies (Na-Cl, Ca-Mg-SO₄, Ca-Mg-Cl/SO₄), that displaying distinct chemical signatures shaped by geological, hydrological, and human processes. The analysis showed that over 65% of the groundwater samples fall within the “unsuitable” category for irrigation, with high to severe constraints for soil and crop sustainability. A novel decision tree (DT) based ML model was optimized to predict these irrigation indices, achieving high performance with fewer input parameters. With low RMSE values and R² values ranging from 0.706 to 0.996 across several indices, the DT models showed remarkable predictive accuracy. The models’ efficiency in producing accurate water quality forecasts at lower analytical costs is demonstrated by their R² = 0.992 (RMSE = 1.693) for IWQI and 0.996 (RMSE = 0.822) for PS. This approach provides a cost-effective alternative to traditional methods by reducing the number of chemical parameters required for analysis. The results of this study offer significant insights for water resource management in arid and semi-arid regions, highlighting the potential of ML techniques in predicting irrigation water quality. The findings are valuable not only for Tunisia but also for similar regions worldwide, offering a tool for decision-makers to develop sustainable water management strategies and improve agricultural practices globally.

The deterioration of the physico-chemical quality of surface waters in the Algerian Northeast is caused by several factors. Our study aims to fill the knowledge gap on the control of hydro-chemical evolution of surface waters in wetlands. The main focus is on major elements in surface waters of the Skikda region in northeastern Algeria. To address this issue, we received 45 samples during the 09 campaigns conducted during the period of low and high water of the year 2015-2016, distributed over five points, namely the tributary Oued Khemakhem, Oued Bouadjeb, Oued Safsaf, reservoir of the Zerdazas dam and the downstream of the Zerdazas dam. First, we studied the variation of physical elements such as pH and EC. Then, using PCA and FA, we characterized the physicochemical properties of the water to demonstrate the relationship between the elements and the factors controlling the distribution of the major elements and the heavy metals Pb2+, Fe2+ and Sr2+. The specific formula of the dominance of the different concentrations in the surface waters of the study area followed the sequence: Ca-Mg-Na-K and Cl-SO4-HCO3 from which a predominant specific facies emerges on 67% of the samples, is of the chloride and sulfate-calco Magnesian facies.

Water resources are facing significant challenges in result of rapidly growing demand, deteriorating quality, and the effects of climate change. Today, water quantity and quality issues have become prevalent in various regions across the globe, affecting both northern and southern territories. Among the sectors reliant on this resource, irrigation stands out as the largest consumer of water. When surface water becomes inaccessible due to insufficient precipitation or other factors, the use of groundwater becomes the only viable alternative for irrigation. The Remila Plain (Khenchela) is located in an endorean watershed in northeastern Algeria and extends over 250 km2 in a synclinal basin filled with water from the Mio-Plio Quaternary - the main aquifer of the region, widely used for irrigation. The aim of this work is to study the hydrochemistry of these waters, as well as the evolution of mineralisation, the identification of the origin of the chemistry, and the suitability of these waters for irrigation. Initial results indicate an evolution of mineralisation in the direction of groundwater flow, with electrical conductivity values varying between 1000μS/cm in the recharge zones, and 2700μS/cm at the outlet. This mineralisation is mainly due to the dissolution of evaporitic minerals and the alteration of silicates. In addition, the various water quality indices used indicate that the water can be used for irrigation without major risk to plants and soils.