water Article Distribution of Groundwater Arsenic in Uruguay Using Hybrid Machine Learning and Expert System Approaches Ruohan Wu 1, Elena M. Alvareda 2,* , David A. Polya 1,* , Gonzalo Blanco 3 and Pablo Gamazo 2,* 1 Department of Earth and Environmental Sciences, School of Natural Sciences and Williamson Research Centre for Molecular Environmental Sciences, University of Manchester, Manchester M13 9PL, UK;
[email protected] 2 Departamento del Agua, Centro Universitario Regional Litoral Norte, Universidad de la República, Gral. Rivera 1350, Salto 50000, Uruguay 3 PDU Geología y Recursos Minerales, Centro Universitario Regional Este, Universidad de la República, Ruta 8 km 282, Treinta y Tres 33000, Uruguay;
[email protected] * Correspondence:
[email protected] (E.M.A.);
[email protected] (D.A.P.);
[email protected] (P.G.) Abstract: Groundwater arsenic in Uruguay is an important environmental hazard, hence, predicting its distribution is important to inform stakeholders. Furthermore, occurrences in Uruguay are known to variably show dependence on depth and geology, arguably reflecting different processes controlling groundwater arsenic concentrations. Here, we present the distribution of groundwater arsenic in Uruguay modelled by a variety of machine learning, basic expert systems, and hybrid approaches. A pure random forest approach, using 26 potential predictor variables, gave rise to a groundwater arsenic distribution model with a very high degree of accuracy (AUC = 0.92), which is consistent with known high groundwater arsenic hazard areas. These areas are mainly in southwest Uruguay, including the Paysandú,Río Negro, Soriano, Colonia, Flores, San José, Florida, Montevideo, and Canelones departments, where the Mercedes, Cuaternario Oeste, Raigón, and Cretácico main aquifers occur.