The time domain electromagnetic method (TDEM) is applied to monitor, to delineate and to map the saltwater intrusion zones in the Mediterranean Plio‐Quaternary aquifer. Forty‐two TDEM soundings were carried out in the coastal plain of Nabeul–Hammamet region (NE Tunisia). TDEM resistivity data were correlated with the existing borehole logging data to assign them to a particular lithology and to provide information about the position of the freshwater–seawater transition zone. The geoelectric sections showing the vertical configuration of seawater intrusion, with the brackish‐salty‐saturated zones, have a resistivity ranging from ~0.1 to 5 Ω⋅m and are detected at a depth lower than 1.5 m. The salinized zones are located at Nabeul (Sidi Moussa, Sidi El Mahrsi, Al Gasba and Mrazgua) and at Hammamet (Touristic zone of Hammamet north and south, Baraket Essahel) and reached a distance of 4 km from the coastline, indicating a severe state for the aquifer in these zones. These TDEM results are confirmed by the increase of chloride concentration content in the analysed water samples of monitoring wells. Moreover, in the northeastern part, the presence of a saltwater front located far from the coast and along the NW–SE major surface fault can be explained by two hypothesis: (i) this fault seems to provide a conduit for seawater to move readily towards the water wells and (ii) the clay and gypsum infiltration of marine Messinian deposits through the fault plane leads to low resistivities. Finally, it comes out from this study that TDEM survey has successfully depicted salinized zones of this coastal aquifer. Copyright © 2012 John Wiley & Sons, Ltd.

No abstract

No abstract

No abstract

Over the last years, the global application of machine learning (ML) models in groundwater quality studies has proved to be a robust alternative tool to produce highly accurate results at a low cost. This research aims to evaluate the ability of machine learning (ML) models to predict the quality of groundwater for irrigation purposes in the downstream Medjerda river basin (DMB) in Tunisia. The random forest (RF), support vector regression (SVR), artificial neural networks (ANN), and adaptive boosting (AdaBoost) models were tested to predict the irrigation quality water parameters (IWQ): total dissolved solids (TDS), potential salinity (PS), sodium adsorption ratio (SAR), exchangeable sodium percentage (ESP), and magnesium adsorption ratio (MAR) through low-cost, in situ physicochemical parameters (T, pH, EC) as input variables. In view of this, seventy-two (72) representative groundwater samples have been collected and analysed for major cations and anions during pre-and post-monsoon seasons of 3 years (2019–2021) to compute IWQ parameters. The performance of the ML models was evaluated according to Pearson’s correlation coefficient (r), the root means square error (RMSE), and the relative bias (RBIAS). The model sensitivity analysis was evaluated to identify input parameters that considerably impact the model predictions using the one-factor-at-time (OFAT) method of the Monte Carlo (MC) approach. The results show that the AdaBoost model is the most appropriate model for predicting all parameters (r was ranged between 0.88 and 0.89), while the random forest model is suitable for predicting only four parameters: TDS, PS, SAR, and ESP (r was with 0.65 to 0.87). Added to that, this study found out that the ANN and SVR models perform well in predicting three parameters (TDS, PS, SAR) and two parameters (PS, SAR), respectively, with the most optimal value of generalization ability (GA) close to unity (between 1 and 0.98). Moreover, the results of the uncertainty analysis confirmed the prominent superiority and robustness of the ML models to produce excellent predictions with only a few physicochemical parameters as inputs. The developed ML models are relevant for predicting cost-effective irrigation water quality indices and can be applied as a DSS tool to improve water management in the Medjerda basin.