Simulation of spring flows from a karst aquifer with an artificial neural network.

This article discusses a simulation model for the spring discharges of karst aquifers in semiarid regions in China using an artificial neural network. According to the authors, spring discharges reflect the variability of ground water storage and the fluctuation of ground water levels in the basins. They treated the karst spring aquifer as a non-linear input and output system and simulated the effects of precipitation on karst spring flow at the Niangziguan Springs in east Shanxi Province. They concluded that the artificial neural network model performed better than the time-lag linear model.