Assessment of groundwater quality in arid regions utilizing principal component analysis, GIS, and machine learning techniques

Assessing water quality in arid regions is vital due to scarce resources, impacting health and sustainable management.This study examines groundwater quality in Assuit Governorate, Egypt, using Principal Component Analysis, GIS, and Machine Learning Techniques. Data from 217 wells across 12 parameters were analyzed, including TDS, EC, Cl−, Fe++, Ca++, Mg++, Na+, SO4−−, Mn++, HCO3−, K+, and pH. The Water Quality Index (WQI) was calculated, and ArcGIS mapped its spatial distribution. Machine learning algorithms, including Ridge Regression, XGBoost, Decision Tree, Random Forest, and K-Nearest Neighbors, were used for predictive analysis. Higher concentrations of Na, K, Ca, Mg, Mn, and Fe were correlated with industrial and densely populated areas. Most samples exhibited excellent or good quality, with a small percentage unsuitable for consumption. Ridge Regression showed the lowest MAPE rates (0.22 % training, 0.26 % in testing). This research highlights the importance of advanced machine learning for sustainable groundwater management in arid regions. Thus, our results could provide valuable assistance to both national and local authorities involved in water management decisions, particularly for water resource managers and decision-makers. This information can aid in the development of regulations aimed at safeguarding and sustainably managing groundwater resources, which are essential for the overall prosperity of the country. [Display omitted] •Utilized PCA, GIS, and ML to assess groundwater quality across 217 wells, considering 12 parameters•Five ML algorithms (Ridge Regression, XGBoost, Decision Tree, Random Forest, KNN) used for WQI prediction.•Ridge regression outperformed other ML algorithms, offering a robust WQI estimation formula.•Subset regression identified nine high R2 input combinations, optimizing WQI prediction.•Diverse ML approaches offer comprehensive insights, enhancing prediction accuracy.