Investigation of quantitative and qualitative changes in groundwater of Ardebil plain using ensemble artificial intelligence-based modeling

Abstract Groundwater is an essential source to supply water for various sectors. This paper aimed predict the quantitative and qualitative changes in groundwater over time evaluate efficiency of different modeling methods. study based on three steps. In first step, piezometers were clustered by Growing Neural Gas Network (GNG) method, central piezometer each cluster was used behalf cluster. second four Artificial Intelligence (AI) models applied, namely (ANN), Adaptive Neuro-Fuzzy Inference System (ANFIS), Support Vector Machine (SVM), Emotional (EANN). As a post-processing approach ensemble methods used: simple average (SAE), weighted (WAE), nonlinear neural network (NNE). third outputs single AI enhance evaluation results. Therefore, results demonstrate that NNE led reach better performance GWL, TDS, TH parameters up 37, 29, 23% average, respectively. Study will lead improvement applications research benefit development plans.