Title: Ground water level prediction using artificial neural network

Authors: Noor-e-ashmaul Husna; Sheikh Hefzul Bari; Md. Manjurul Hussain; Md. Tauhid Ur-rahman; Mashrekur Rahman

Addresses: Institute of Water and Flood Management, Bangladesh University of Engineering and Technology, Dhaka, Bangladesh ' Dept. of Civil Engineering, Leading University, Sylhet, Bangladesh ' Dept. of Civil and Environmental Engineering, Shahjalal University of Science and Technology, Sylhet, Bangladesh ' Department of Civil Engineering, Military Institute of Science and Technology, Dhaka, Bangladesh ' Institute of Water and Flood Management, Bangladesh University of Engineering and Technology, Dhaka

Abstract: In this paper, the feedforward neural network was used to predict the groundwater level at Chandpur District of Bangladesh. Levenberg-Marquardt (LM) algorithm was used as network training algorithm and sigmoid function as the transfer function. Weekly groundwater level data of six measuring wells from 1998 to 2007 were used to train and test the neural network. Prediction accuracy of each network structure was tested using mean square error (MSE), root mean square error (RMSE), and efficiency criterion (R²). Results showed that the artificial neural network (ANN) predicted groundwater level up to ten weeks ahead with reasonable errors. The accuracy of the network decreases rapidly after that limit. The maximum root mean square error was 0.328 metre and 0.193 metre for ten-week and one-week lead prediction respectively. As the one-week lead prediction was found almost similar to the actual field value, this could be useful in missing value analysis.

Keywords: Bangladesh; artificial neural networks; ANNs; groundwater level prediction; Levenberg-Marquardt algorithm; feedforward backpropagation neural networks; FBPNN.

DOI: 10.1504/IJHST.2016.079356

International Journal of Hydrology Science and Technology, 2016 Vol.6 No.4, pp.371 - 381

Received: 10 Dec 2015
Accepted: 09 Jan 2016
Published online: 27 Sep 2016 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article