Mapping groundwater recharge zones (GWRZs) is essential for planning artificial recharge programs to mitigate groundwater decline and saltwater intrusion into coastal aquifers. We applied two multi-criteria decision-making approaches, namely the analytical hierarchy process (AHP) and the multi-influencing factors (MIF), to map GWRZs in the Korba aquifer in northeastern Tunisia. GWRZ results from the AHP indicate that the majority (69%) of the area can be classified as very good and good for groundwater recharge. The MIF results suggest larger (80.7%) very good and good GWRZs. The GWRZ maps improve groundwater balance calculations by providing estimates of recharge-precipitation ratios to quantify percolation. Lithology, land use/cover and slope were the most sensitive parameters followed by geomorphology, lineament density, rainfall, drainage density and soil type. The AHP approach produced relatively more accurate results than the MIF technique based on correlation of the obtained GWRZs with groundwater well discharge data from 20 wells across the study area. The accuracy of the approaches ultimately depends on the classification criteria, mean rating score and weights assigned to the thematic layers. Nonetheless, the GWRZ maps suggest that there is ample opportunity to implement aquifer recharge programs to reduce groundwater stress in the Korba aquifer.

In this work, a new parameter of fracture media is introduced to the conventional DRASTIC model to establish a new model for the fractured aquifer vulnerability mapping. Therefore, Artificial Intelligence technique (AI) is employed to reduce potential uncertainties using unsupervised Multi-Frameworks Technique (MFT) (Standard DRASTIC-Fr Framework (SDF) and Fuzzy Membership Framework (FMF)) and supervised learning based on Multi-Models Approach (MMA) (Genetic Algorithm (GA) and Genetic Expression Programming (GEP)). This novel framework comprises two stages; Stage 1 building of two frameworks MFT and models MMA; Stage 2 developing four frameworks including MFT/MMA combination based on Support Vector Machine algorithm. The proposed framework is tested with the fractured aquifer of the Meknassy area (central Tunisia), where the rapid expansive agricultural habits have been converted into excessive usage of fertilizers. Outputs demonstrate that the vulnerability in the study area is very low VL =31%, low L = 21.5%, moderate M = 22.9%, high H = 15% and very high VH =9.6%.

The primary aims of this research paper involve the creation and verification of machine learning-based quality models that utilize Integrated Irrigation Water Quality Indices (IIGWQIs) through an integrated GIS approach. We utilize the Least-Squares Support Vector Machines (LS-SVM) and the Pearson Correlation Fuzzy Inference-based System (PC-FIS) to establish forecasts for groundwater quality in the Meknassy basin. This basin serves as a representative case of an irrigated region in a mining environment under arid climatic conditions in central Tunisia. The evaluated factors for groundwater quality encompass the Irrigation Water Quality Index (IWQIndex), Sodium Adsorption Ratio Index (SARIndex), Soluble Sodium Percentage Index (SSPIndex), Potential Salinity Index (PSIndex), Kelley Index (KIndex), and Residual Sodium Carbonate Index (RSCIndex). These factors were determined based on measurements from 53 groundwater wells, which included various physico-chemical parameters. The hydrogeochemical facies identified included Ca-Mg-SO₄, mixed Ca-Mg-Cl-SO₄, and Na-Cl facies, revealing processes such as carbonate weathering, carbonate dissolution, interactions between rocks and groundwater, and mixing ionic substitution. In terms of the irrigation suitability categories, the IWQIndex, SSPIndex, PSIndex, Kindex, and RSCIndex indicated no limitation or minimal limitation (77.36%), secure (92.45%), favorable to excellent (66.04%), favorable (81.13%), and average to secure (88.68%), respectively. However, only 15.09% were considered favorable, according to SARIndex. The evaluation of the predictive models revealed the effectiveness of both the PC-FIS model and the LS-SVM model in accurately forecasting the IIGWQIs.

A logistic regression model and a bivariate statistical analysis were used in this paper to evaluate the groundwater recharge susceptibility. The approach is based on the assessment of the relationship involving groundwater recharge and parameters that influence this hydrological process. Surface parameters and aquifer-related parameters were evaluated as thematic map layers using ArcGIS. Then, a weighted-rating method was adopted to categorize each parameter's map. To assess the role of each parameter in the aquifer recharge, a logistic regression model and a bivariate statistical analysis were applied to the Guenniche phreatic aquifer (Tunisia). Models are explored to establish a map showing the aquifer recharge susceptibility. The code Modflow was used to simulate the consequence of the recharge. The recharge amount was introduced in the model and was tested to verify the recharge effect on the hydraulic head for the two models. The obtained results reveal that the recharge as mapped in the bivariate statistical model has a minor impact on the hydraulic head. Results of the logistic regression model are more significant as the hydraulic head is widely affected. This model provides good results in mapping the spatial distribution of the aquifer recharge susceptibility.