Integrating experimental-based vulnerability mapping with intelligent identification of multi-aquifer groundwater salinization

Abstract

Groundwater salinization is a pressing global issue, threatening water security and sustainable development in many regions. In alignment with Saudi Vision 2030 and the Sustainable Development Goals (SDGs), this study addresses groundwater salinity challenges in the coastal regions of eastern Saudi Arabia through comprehensive experimental analysis and advanced mapping techniques. Groundwater samples were analyzed using ion chromatography (IC) and inductively coupled plasma mass spectrometry (ICP-MS) to determine salinity levels. The data were processed using ArcGIS 10.3 software to create vulnerability maps, supported by five artificial intelligence (AI)-based models for robust predictions and enhanced insights. Model performance was assessed using statistical parameters, including Nash–Sutcliffe efficiency (NSE), root mean square error (RMSE), Pearson correlation coefficient (PCC), and mean square error (MSE). Among the models, interactive learning (ILR-M3) delivered the best results (RMSE=0.0385; MSE=0.0015), while all models were validated as satisfactory. This research highlights the potential of combining experimental data with AI-driven approaches for effective water resource management. The outcomes directly support Saudi Vision 2030 and contribute to achieving the SDGs by advancing sustainable and intelligent solutions for global water security challenges.