Groundwater Level Predictions Using Artificial Neural Networks

IntroductionThe prediction of groundwater level fluctuation fordifferent natural conditions and usage rates is ofgreat importance for the use and management ofgroundwater resources.However,groundwaterlevel fluctuations are influenced by many factors,such as precipitation,infiltration,usage and thehydro- geological properties of the aquifer.Therefore,the groundwater level fluctuations arecomplicated and difficult to predict,especially indeep areas.Wells are commonly drilled tounderstand aquifer…

Groundwater Level Predictions Using Artificial Neural Networks

The prediction of groundwater level is important for the use and management of groundwater resources. In this paper, the artificial neural networks (ANN) were used to predict groundwater level in the Dawu Aquifer of Zibo in Eastern China. The first step was an auto-correlation analysis of the groundwater level which showed that the monthly groundwater level was time dependent. An auto-regression type ANN (ARANN) model and a regression-auto-regression type ANN (RARANN) model using back-propagation algorithm were then used to predict the groundwater level. Monthly data from June 1988 to May 1998 was used for the network training and testing. The results show that the RARANN model is more reliable than the ARANN model, especially in the testing period, which indicates that the RARANN model can describe the relationship between the groundwater fluctuation and main factors that currently influence the groundwater level. The results suggest that the model is suitable for predicting groundwater level fluctuations in this area for similar conditions in the future.