Agriculture has significantly aided in meeting the food needs of growing population. In addition, it has boosted economic development in irrigated regions. In this study, an assessment of the groundwater (GW) quality for agricultural land was carried out in El Kharga Oasis, Western Desert of Egypt. Several irrigation water quality indices (IWQIs) and geographic information systems (GIS) were used for the modeling development. Two machine learning (ML) models (i.e., adaptive neuro-fuzzy inference system (ANFIS) and support vector machine (SVM)) were developed for the prediction of eight IWQIs, including the irrigation water quality index (IWQI), sodium adsorption ratio (SAR), soluble sodium percentage (SSP), potential salinity (PS), residual sodium carbonate index (RSC), and Kelley index (KI). The physicochemical parameters included T°, pH, EC, TDS, K⁺, Na⁺, Mg²⁺, Ca²⁺, Cl⁻, SO₄²⁻, HCO₃⁻, CO₃²⁻, and NO₃⁻, and they were measured in 140 GW wells. The hydrochemical facies of the GW resources were of Ca-Mg-SO₄, mixed Ca-Mg-Cl-SO₄, Na-Cl, Ca-Mg-HCO₃, and mixed Na-Ca-HCO₃ types, which revealed silicate weathering, dissolution of gypsum/calcite/dolomite/ halite, rock–water interactions, and reverse ion exchange processes. The IWQI, SAR, KI, and PS showed that the majority of the GW samples were categorized for irrigation purposes into no restriction (67.85%), excellent (100%), good (57.85%), and excellent to good (65.71%), respectively. Moreover, the majority of the selected samples were categorized as excellent to good and safe for irrigation according to the SSP and RSC. The performance of the simulation models was evaluated based on several prediction skills criteria, which revealed that the ANFIS model and SVM model were capable of simulating the IWQIs with reasonable accuracy for both training “determination coefficient (R²)” (R² = 0.99 and 0.97) and testing (R² = 0.97 and 0.76). The presented models’ promising accuracy illustrates their potential for use in IWQI prediction. The findings indicate the potential for ML methods of geographically dispersed hydrogeochemical data, such as ANFIS and SVM, to be used for assessing the GW quality for irrigation. The proposed methodological approach offers a useful tool for identifying the crucial hydrogeochemical components for GW evolution assessment and mitigation measures related to GW management in arid and semi-arid environments.

In order to evaluate and project the quality of groundwater utilized for irrigation in the Sahara aquifer in Algeria, this research employed irrigation water quality indices (IWQIs), artificial neural network (ANN) models, and Gradient Boosting Regression (GBR), alongside multivariate statistical analysis and a geographic information system (GIS), to assess and forecast the quality of groundwater used for irrigation in the Sahara aquifer in Algeria. Twenty-seven groundwater samples were examined using conventional analytical methods. The obtained physicochemical parameters for the collected groundwater samples showed that Ca²⁺ > Mg²⁺ > Na⁺ > K⁺, and Cl⁻ > SO₄²⁻ > HCO₃⁻ > NO₃⁻, owing to the predominance of limestone, sandstone, and clay minerals under the effects of human activity, ion dissolution, rock weathering, and exchange processes, which indicate a Ca-Cl water type. For evaluating the quality of irrigation water, the IWQIs values such as irrigation water quality index (IWQI), sodium adsorption ratio (SAR), Kelly index (KI), sodium percentage (Na%), permeability index (PI), and magnesium hazard (MH) showed mean values of 47.17, 1.88, 0.25, 19.96, 41.18, and 27.87, respectively. For instance, the IWQI values revealed that 33% of samples were severely restricted for irrigation, while 67% of samples varied from moderate to high restriction for irrigation, indicating that crops that are moderately to highly hypersensitive to salt should be watered in soft soils without any compressed layers. Two-machine learning models were applied, i.e., the ANN and GBR for IWQI, and the ANN model, which surpassed the GBR model. The findings showed that ANN-2F had the highest correlation between IWQI and exceptional features, making it the most accurate prediction model. For example, this model has two qualities that are critical for the IWQI prediction. The outputs’ R² values for the training and validation sets are 0.973 (RMSE = 2.492) and 0.958 (RMSE = 2.175), respectively. Finally, the application of physicochemical parameters and water quality indices supported by GIS methods, machine learning, and multivariate modeling is a useful and practical strategy for evaluating the quality and development of groundwater.

This study assessed the environmental and health risks associated with heavy metals in the water resources of Egypt's northwestern desert. The current approaches included the Spearman correlation matrix, principal component analysis, and cluster analysis to identify pollution sources and quality-controlling factors. Various indices (HPI, MI, HQ, HI, and CR) were applied to evaluate environmental and human health risks. Additionally, the Monte Carlo method was employed for probabilistic carcinogenic and non-carcinogenic risk assessment via oral and dermal exposure routes in adults and children. Notably, all water resources exhibited high pollution risks with HPI and MI values exceeding permissible limits (HPI > 100 and MI > 6), respectively. Furthermore, HI oral values indicated significant non-carcinogenic risks to both adults and children, while dermal contact posed a high risk to 19.4% of samples for adults and 77.6% of samples for children (HI > 1). Most water samples exhibited CR values exceeding 1 × 10^–4 for Cd, Cr, and Pb, suggesting vulnerability to carcinogenic effects in both age groups. Monte Carlo simulations reinforced these findings, indicating a significant carcinogenic impact on children and adults. Consequently, comprehensive water treatment measures are urgently needed to mitigate carcinogenic and non-carcinogenic health risks in Siwa Oasis.

Irrigation has made a significant contribution to supporting the population’s expanding food demands, as well as promoting economic growth in irrigated regions. The current investigation was carried out in order to estimate the quality of the groundwater for agricultural viability in the Algerian Desert using various water quality indices and geographic information systems (GIS). In addition, support vector machine regression (SVMR) was applied to forecast eight irrigation water quality indices (IWQIs), such as the irrigation water quality index (IWQI), sodium adsorption ratio (SAR), sodium percentage (Na%), soluble sodium percentage (SSP), potential salinity (PS), Kelly index (KI), permeability index (PI), potential salinity (PS), permeability index (PI), and residual sodium carbonate (RSC). Several physicochemical variables, such as temperature (T°), hydrogen ion concentration (pH), total dissolved solids (TDS), electrical conductivity (EC), K⁺, Na²⁺, Mg²⁺, Ca²⁺, Cl⁻, SO₄²⁻, HCO₃⁻, CO₃²⁻, and NO₃⁻, were measured from 45 deep groundwater wells. The hydrochemical facies of the groundwater resources were Ca–Mg–Cl/SO₄ and Na–Cl⁻, which revealed evaporation, reverse ion exchange, and rock–water interaction processes. The IWQI, Na%, SAR, SSP, KI, PS, PI, and RSC showed mean values of 50.78, 43.07, 4.85, 41.78, 0.74, 29.60, 45.65, and −20.44, respectively. For instance, the IWQI for the obtained results indicated that the groundwater samples were categorized into high restriction to moderate restriction for irrigation purposes, which can only be used for plants that are highly salt tolerant. The SVMR model produced robust estimates for eight IWQIs in calibration (Cal.), with R² values varying between 0.90 and 0.97. Furthermore, in validation (Val.), R² values between 0.88 and 0.95 were achieved using the SVMR model, which produced reliable estimates for eight IWQIs. These findings support the feasibility of using IWQIs and SVMR models for the evaluation and management of the groundwater of complex terminal aquifers for irrigation. Finally, the combination of IWQIs, SVMR, and GIS was effective and an applicable technique for interpreting and forecasting the irrigation water quality used in both arid and semi-arid regions.

The assessment and prediction of water quality are important aspects of water resource management. Therefore, the groundwater (GW) quality of the Nubian Sandstone Aquifer (NSSA) in El Kharga Oasis was evaluated using indexing approaches, such as the drinking water quality index (DWQI) and health index (HI), supported with multivariate analysis, artificial neural network (ANN) models, and geographic information system (GIS) techniques. For this, physical and chemical parameters were measured for 140 GW wells, which indicated Ca–Mg–SO₄, mixed Ca–Mg–Cl–SO₄, Na–Cl, Ca–Mg–HCO₃, and mixed Na–Ca–HCO₃ water facies under the influence of silicate weathering, rock–water interactions, and ion exchange processes. The GW in El Kharga Oasis had high levels of heavy metals, particularly iron (Fe) and manganese (Mn), with average concentrations above the limits recommended by the World Health Organization (WHO) for drinking water. The DWQI categorized most of the samples as not suitable for drinking (poor to very poor class), while some samples fell in the good water class. The results of the HI indicated a potential health risk due to the ingestion of water, with the risk being higher for children in only one location. However, for both children and adults, there was a low risk of dermal and ingestion exposure to the water in all locations. The contaminants could be from natural sources, such as minerals leaching from rocks and soil, or from human activities. Based on the results of ANN modeling, ANN-SC-13 was the most accurate prediction model, since it demonstrated the strongest correlation between the best characteristics and the DWQI. For example, this model’s thirteen characteristics were extremely important for predicting DWQI. The R² value for the training, cross-validation (CV), and test data was 0.99. The ANN-SC-2 model was the best in measuring HI ingestion in adults. The R² value for the training, CV, and test data was 1.00 for all models. The ANN-SC-2 model was the most accurate at detecting HI dermal in adults (R² = 0.99, 0.99, and 0.99 for the training, CV, and test data sets, respectively). Finally, the integration of physicochemical parameters, water quality indices (WQIs), and ANN models can help us to understand the quality of GW and its controlling factors, and to implement the necessary measures that prevent outbreaks of various water-borne diseases that are detrimental to human health.

Assessing and predicting quality of groundwater is crucial in managing groundwater availability effectively. In the current study, groundwater quality was thoroughly appraised using various indexing methods, including the drinking water quality index (DWQI), pollution index of heavy metals (HPI), pollution index (PI), metal index (MI), degree of contamination (C_d), and risk indicators, like hazard quotient (HQ) and total hazard indicator (HI). The assessments were augmented through multivariate analytical techniques, models based on recurrent neural networks (RNNs), and integration of geographic information system (GIS) technology. The analysis measured physicochemical parameters across 48 groundwater wells from El-Menoufia region, revealing distinct water types influenced by ion exchange, rock-water interactions, and silicate weathering. Notably, the groundwater showed elevated levels of certain metals, particularly manganese (Mn) and lead (Pb), exceeding the drinking water limits. The DWQI deemed the bulk of the tested samples suitable for consumption, assigning them to the "good" category, whereas a small number were considered inferior quality. The HPI, MI, and C_d indices indicated significant pollution in the central study region. The PI revealed that Pb, Mn, and Fe were significant contributors to water pollution, falling between classes IV (strongly affected) and V (seriously affected). HQ and HI analyses identified the central area of the study as particularly prone to metal contamination, signifying a high risk to children via oral and dermal routes and to adults through oral exposure alone (non-carcinogenic risk). The adults had no health risks due to dermal contact. Finally, the RNN simulation model effectively predicted the health and water quality indices in training and testing series. For instance, the RNN model excelled in predicting the DWQI, with three key parameters being crucial. The model demonstrated an excellent fit on the training set, achieving an R² of 1.00 with a very low root mean of squared error (RMSE) of 0.01. However, on the testing set, the model's performance slightly decreased, showing an R² of 0.96 and an RMSE of 2.73. Regarding HPI, the RNN model performed exceptionally well as the primary predictor, with R² values of 1.00 (RMSE = 0.01) and 0.93 (RMSE = 27.35) for the training and testing sets, respectively. This study provides a unique perspective for improving the integration of various techniques to gain a more comprehensive understanding of groundwater quality and its associated health risks, with a strong focus on feature selection strategies to enhance model accuracy and interpretability.