Machine Learning Algorithms for Modeling and Mapping of Groundwater Pollution Risk: A Study to Reach Water Security and Sustainable Development (Sdg) Goals in a Mediterranean Aquifer System

Groundwater pollution poses a severe threat and issue to the environment humanity overall. That is why mitigative strategies are urgently needed. Today, studies mapping groundwater risk assessment being developed. In this study, five new hybrid/ensemble machine learning (ML) models developed, named DRASTIC-Random Forest (RF), DRASTIC-Support Vector Machine (SVM), DRASTIC-Multilayer Perceptron (MLP), DRASTIC-RF-SVM, DRASTIC-RF-MLP, for in Saiss basin, Morocco. The performances of these evaluated using Receiver Operating Characteristic curve (ROC curve), precision, accuracy. Based on results ROC method, it indicated that use improves performance individual algorithms. effect, AUC value original DRASTIC 0.51. Furthermore, both models, DRASTIC-RF-MLP (AUC = 0.953) 0.901) achieve best accuracy among other followed by DRASTIC-RF 0.852), DRASTIC-SVM 0.802), DRASTIC-MLP 0.763). delineate areas vulnerable pollution, which require urgent actions improve environmental social qualities local population.