Groundwater Level Fluctuations in Coastal Aquifer: Using Artificial Neural Networks to Predict the Impacts of Climatical CMIP6 Scenarios

Groundwater resources play a crucial role in supplying water for domestic, industrial, and agricultural use. In this study ACCESS-CM2, HadGEM3-GC31-LL, NESM3 were selected validation from Coupled Model Intercomparison Project Phase 6 (CMIP6). the following, feedforward neural network was employed to predict monthly groundwater level (GWL) based on emission scenarios of sixth IPCC report (SSP2-4.5 SSp5-8.5) next two decades (2021–2040) Sari-Neka coastal aquifer near Caspian Sea, Iran. regard, maximum minimum temperature, precipitation, table previous month four piezometers 2000 2019 used as input variables forecast GWL. The evaluation three GCM models demonstrated that ACCESS-CM2 provided best values R2 RMSE with observation parameters. results r, R2, RMSE, MAE evaluated model indicated good performance model. also illustrated under such mentioned scenarios, mean temperature would rise approximately 0.1–1.2 °C. addition, precipitation is likely witness changes -10% 78% decades. As result, seems lead improvement recharge future. can help managers policymakers identify adaptation strategies more precisely basins similar climates.