Groundwater Level Forecasting by Application of Artificial Neural Network Approach: A Case Study in Qom Plain, Iran

Abstract

Groundwater plays an important role in providing water supply especially in arid and semi-arid regions such as Iran. Given globally water crisis, monitoring and analyzing water levels can help water resources managers and planners for sustainable utilization and management of water supplies. On the other hand, groundwater processes exhibit dynamic, temporal and spatial patterns; making groundwater fluctuation modeling a complex and challenging task. Among different modeling methods, artificial neural networks (ANNs) are regularly used for complicated problems due to their distinctive and powerful properties. Qom plain in Iran is an arid region whose groundwater utilization in the last decades has led to downfall in water table. In this study groundwater level fluctuations were investigated in two distinct wells in this region using monthly groundwater level data recorded for 11 years. For modeling, the ground water time series of each studied well were entered as the input and output to the network and Time delay neural networks (TDNN) with various network structures and input delays were used for achieving the best results. The findings of the best modeling structure represented fair fitting for forecasted results in comparison with observed data, hereby underlining the promising application of this method for groundwater level modeling.