Projection of Groundwater Level Fluctuations Using Different Machine Learning Algorithms under Climate Change in the Mashhad Aquifer, Iran

Abstract

Abstract Due to population growth in recent years and climate change in arid and semi-arid regions, the lack of rainfall and the reduction of surface water flows required in various sectors, monitoring and projection of the climate change impact on the Groundwater Level (GWL) in the future is vital in the management and control of these resources. The purpose of this study is the projection of climate change impact on the GWL fluctuations in the Mashhad aquifer during the future period (2022-2064). In the first step, the climatic variables using ACCESS-CM2 under the Shared Socio-economic Pathways (SSPs) 5-8.5 scenario from the CMIP6 model were extracted. We used the CMhyd model to downscale the climatic data from the GCMs model. In the second step, different machine learning algorithms, including Multilayer Perceptron Neural Network (MLP), Adaptive Neuro-fuzzy Inference System Neutral Network (ANFIS), Radial Basis Function Neural Network (RBF), and Support Vector Machine (SVM) were used to predict the GWL fluctuations under climate change in the future period. Our results point out that temperatures and evaporation will increase in the autumn season, and precipitation will decrease by 26% in the future in the Mashhad aquifer. The results showed that the RBF model was an excellent performance in predicting GWL compared to other models. Based on the result of the RBF model, the GWL will decrease by 6.60 meters under the SSP5-8.5 scenario in the future. The findings of this research have a practical role in making helpful groundwater resources management decisions.