Groundwater Level Simulation Using Soft Computing Methods with Emphasis on Major Meteorological Components

Precise estimation of groundwater level (GWL) might be great importance for attaining sustainable development goals and integrated water resources management. Compared with alternative numerical models, soft computing methods are promising tools GWL prediction, which need more hydrogeological aquifer characteristics. The central aim this research is to explore the performance such well-accepted data-driven models predict monthly emphasis on major meteorological components, including; precipitation (P), temperature (T), evapotranspiration (ET). Artificial neural network (ANN), fuzzy logic (FL), adaptive neuro-fuzzy inference system (ANFIS), group method data handling (GMDH), least-square support vector machine (LSSVM) used one-, two-, three-month ahead in an unconfined aquifer. main components (Tt, ETt, Pt, Pt-1) one, two, three lag-time (GWLt-1, GWLt-2, GWLt-3) as input attain precise prediction. results show that all could have best prediction one month scenario 5, comprising inputs GWLt-1, GWLt-3, Tt, Tt-1, ETt-1, Pt-1. Based different evaluation criteria, employed a desirable accuracy, LSSVM superior one.