Assessing the Risk of Groundwater Pollution in Northern Algeria through the Evaluation of Influencing Parameters and Ensemble Methods

Developing an accurate map to control groundwater pollution is becoming increasingly important to fulfill requirements of the Algerian water directives. Evaluating groundwater vulnerability to nitrate contamination in the eastern Mitidja aquifer has become crucial for water resource control and preservation. In this research, some of the commonly used ensemble methods namely Categorical Boosting, Adaptive Boosting and Random Forest were employed to model the spatial groundwater vulnerability to nitrate concentration based on the maximum acceptable concentration in drinking water according to the Algerian directives (50 mg/L). The study were carried out on the evaluation of different possible influencing parameters including depth to groundwater, permeability, rainfall, vadose zone, distance to river, drainage density, land use land cover, Normalized Difference Vegetation Index, slope, topographic wetness index and elevation. The proposed approach aims to understand and control the vulnerability and pollution process of the groundwater aquifers with the smallest available dataset to assess vulnerability predictive mapping. The best results based on the receiver operating characteristic and area under the curve (ROC-AUC) showed that the Categorical boosting indicated the highest accuracy of 94% then the adaptive boosting algorithm with 92%, and the Random forest algorithm with 89%. It revealed that climatic and hydrogeological factors are the key factors determining groundwater vulnerability to NO 3 concentration in the eastern Mitidja. It is concluded that the risk of groundwater pollution covers a large area of the groundwater resources in the city of Algiers, Blida, and Boumerdas in northern Algeria.