Groundwater Level Prediction based on Neural Networks: A case study in Linze, Northwestern China

College of Information Science And Engineering, China University of Petroleum-Beijing, Beijing, China

Abstract

Groundwater level is an important factor in evaluating groundwater resources. Due to numerous non-linear factors, establishing theoretical models is difficult.. Therefore, this paper proposesthe BP (Back Propagation) neural network and the Radial Basis Function (RBF) neural network. The study area is divided into two zones. The R² (coefficient of determination) and RMSE (Root Mean Squared Error) are used to evaluate the performance. The BP neural network is used to predict groundwater level in the two zones with the R²of0.57 and 0.54, with the RMSE of 0.0804 meters and 0.1864 meters respectively. The RBF neural network is implemented with R²of 0.65 and 0.61, with RMSE of 0.0720 meters and 0.1519 meters, respectively. The results show the RBF neural network performs better than the BP neural network in the accuracy of predicting groundwater level. This study shows the feasibility and superiority of groundwater simulation using neural network.