Groundwater Level Simulation Using Artificial Neural Network in Southeast, Punjab, India

Abstract

This paper presents an efficient and stable artificial neural network (ANN) model for predicting groundwater level in south-east Punjab, India. After improving the model accuracy using different types of network architectures and training algorithms, it has been observed that best results can be achieved with a standard feed forward neural network trained with the Levenberg–Marquardt algorithm. Good estimation of groundwater level can be achieved by designing distinct networks for different sites and ANN method has been found to forecast groundwater level in Faridkot, Ferozepur, Ludhiana and Patiala districts of Punjab, India with reasonable accuracy