Water Quality Evaluation and Prediction Using Irrigation Indices, Artificial Neural Networks, and Partial Least Square Regression Models for the Nile River, Egypt

Water quality is identically important as quantity in terms of meeting basic human needs. Therefore, evaluating the surface-water and associated hydrochemical characteristics essential for managing water resources arid semi-arid environments. present research was conducted to evaluate predict agricultural purposes across Nile River, Egypt. For that, several irrigation indices (IWQIs) were used, along with an artificial neural network (ANN), partial least square regression (PLSR) models, geographic information system (GIS) tools. The physicochemical parameters, such T °C, pH, EC, TDS, K+, Na+, Mg2+, Ca2+, Cl−, SO42−, HCO3−, CO32−, NO3−, measured at 51 locations. As a result, ions contents following: Ca2+ > Na+ Mg2+ K+ HCO3− Cl− SO42− NO3− reflecting Ca-HCO3 mixed Ca-Mg-Cl-SO4 types. index (IWQI), sodium adsorption ratio (SAR), percentage (Na%), soluble (SSP), permeability (PI), magnesium hazard (MH) had mean values 92.30, 1.01, 35.85, 31.75, 72.30, 43.95, respectively. instance, IWQI readings revealed that approximately 98% samples inside no restriction category, while 2% fell within low area irrigation. ANN-IWQI-6 model’s six indices, R2 0.999 calibration (Cal.) 0.945 validation (Val.) datasets, are crucial predicting IWQI. rest models behaved admirably SAR, Na%, SSP, PI, MR Cal. Val. 0.999. findings ANN PLSR effective methods assist decision plans. To summarize, integrating features, WQIs, ANN, PLSR, GIS tools suitability offers complete image sustainable development.