Prediction of groundwater level fluctuations under climate change based on machine learning algorithms in the Mashhad aquifer, Iran

Abstract The purpose of this study is the projection climate change's impact on Groundwater Level (GWL) fluctuations in Mashhad aquifer during future period (2022–2064). In first step, climatic variables using ACCESS-CM2 model under Shared Socio-economic Pathways (SSPs) 5–8.5 scenario were extracted. second different machine learning algorithms, including Multilayer Perceptron Neural Network (MLP), Adaptive Neuro-fuzzy Inference System Neutral (ANFIS), Radial Basis Function (RBF), and Support Vector Machine (SVM) employed for GWL time series prediction change future. Our results point out that temperatures evaporation will increase autumn season, precipitation decrease by 26%. amount winter due to an temperature a precipitation. showed RBFNN had excellent performance predicting compared other models highest value R² (R² = 0.99) lowest RMSE, which 0.05 0.06 meters training testing steps, respectively. Based result model, 6.60 SSP5-8.5 scenario.