Water quality index (WQI) is the primary method applied to characterize water quality in the world. The current study employed the statistical analysis and multilayer perceptron (MLP) approaches for predicting groundwater quality in the Ghiss-Nekkor aquifer, northeast of Al Hoceima, Morocco. Fifty sampled groundwater were identified and analyzed for major anions and cations throughout May 2019. Several physicochemical parameters of all the samples were identified in this investigation, such as TDS, pH, EC, Na, K, Ca, Mg, HCO₃, NO₃, Br, SO₄, and Cl. The entropy-weighted groundwater quality index (EWQI) was calculated from these parameters. The WQI procedure determined the suitability of groundwater for consumption. The WQI value varied from 90.98 to 337.28. The EC, TDS, WQI, and Cl⁻ spatial distribution showed that EC and Cl⁻ are associated with poor groundwater quality. A single sample (W16) represented unsuitable water for drinking purposes and offered a WQI value of 337.28, indicating poor drinking quality due to seawater intrusion, overexploitation, and harsh weather conditions. The majority of the values obtained for the parameters exceeded the recommended limit of the World Health Organization (WHO)’s guidelines for consumption. The findings show that using parameters is a straightforward method for predicting water quality indexes with sufficient and suitable precision. The MLP model shows good predictive performances in terms of the coefficient of determination R², mean absolute error (MAE), and root-mean-square error (RMSE) with values of 0.9885, 5.8031, and 4.7211, respectively. The ANN approach was applied to develop a model that can accurately predict WQI utilizing mineralization, TH, NO3, and NO2 as inputs. The MAE for the model’s performance was calculated to be 4.72. A Bland–Altman test was used to validate that the model is suitable. Following the test, it was determined that the model is appropriate for predicting WQI, with an error of just 0.1%.

Groundwater is a valuable shared resource in the Moulouya Basin, but it has been in decline due to recent years of low rainfall and rapid population growth. To support socio-economic development, there is increased demand for this precious resource. This paper presents a standard methodology for delimiting potential groundwater zones using geographic information systems (GIS), an integrated analytical hierarchy process (AHP), and remote sensing techniques. Seven parameters that monitor the presence and mobility of groundwater, including drainage density, lithology, slope, precipitation, land use/land cover, distance to river, and lineament density, were incorporated into a raster data model using ArcGIS software. AHP-based expert knowledge was used to prepare a groundwater potential index and assign weights to the thematic layers. The study classified the area into five zones of varying groundwater potential: very high (26%), high (51%), moderate (13%), poor (9%), and very poor (1%). The accuracy of the model was validated by comparing the Groundwater Potential Zones map with data from 96 wells and boreholes across the basin. The validity of the results was confirmed by comparing them with the specific yield of the aquifer in the study area, yielding a high correlation coefficient (R²) of 0.79. The analysis revealed that 89.5% of the boreholes were situated in the high and very high potential zones, demonstrating the reliability and robustness of the employed approach. These findings can aid decision-making and planning for sustainable groundwater use in the water-stressed region.

This research evaluates the applicability of different types of hydrological models to simulate discharge behavior scenarios in a northern Moroccan watershed, Oued Laou Watershed (OLW). In this context, an improved understanding of the runoff mechanisms through hydrological modeling of the OLW can assist in the hazard risk management and facilitate the effective planning of water resources. For that end, a multitude of hydrological models were used to perform a very efficient modelling, and a comparative approach was adopted. Comparison of the models allowed the determination of potential sources of uncertainty in hydrological modelling of a subhumid watershed. Three models (ATelier Hydrologique Spatialisé (ATHYS), Hydrologic Modeling System (HEC-HMS), and Soil and Water Assessment Tool (SWAT)) with different characteristics were employed for a continuous modelling approach. The models were calibrated and validated using observed daily rainfall and streamflow data for 4 years (2004–2008) and 3 years (2009–2011), respectively. The multi-criteria model comparison (R², NSE, RSR, and PBIAS) showed that all three models are capable of reproducing the observed flows. The SWAT model performed well over both periods (NSE = 0.76 for calibration), with an improvement in validation (NSE = 0.84). A good agreement was also observed in the HEC-HMS model outputs, with an approximately stable NSE of 0.77 and 0.78 for calibration and validation phases, respectively. The ATHYS model showed a NSE value of 0.67 during the calibration, with a decrease of 0.06 towards the validation period. The other performance criteria confirmed these findings. Additionally, results suggest that semi-distributed and conceptual hydrological models are particularly suitable for the OLW given their physical heterogeneity. Generally, the integration of these models may be suitable for water resources assessment in OLW.