Abstract: There are many environmental concerns to the quantity of surface water and groundwater in the hydrological system. It is very important to estimate the groundwater levels by using readily available data for managing the water resources. Worldwide concern for the sustainability of groundwater resources, basin-wise modeling of groundwater flow is essential for the efficient planning and management of groundwater resources in a groundwater basin. This study aims to evaluate the performance of finite difference-based numerical model MODFLOW and an artificial neural network model, applied to simulate groundwater levels in Sindapalli Uppodai sub basin of Vaippar River basin, Tamilnadu, southern India. Among the different robust tools available, the Back-Propagation Neural Network (BPNN) model is commonly used to empirically forecast hydrological variables. Calibration of the MODFLOW was done by using monthly groundwater level data of 4 years from June 2006 to May 2010 and validation of the model was done using six month from June 2010 to December 2010 groundwater level data. Groundwater levels at 25 observation wells were simulated for the validation period. The inputs to the Artificial Neural Networks (ANN) model consisted of monthly rainfall, evaporation, water level in the small storage structures and groundwater levels in these wells at the previous time step. The time periods used in the MODFLOW were also considered for the training and testing of the developed ANN model. The simulated groundwater level by MODFLOW and ANN model were compared with the observed groundwater levels. The average regression coefficient for MODFLOW is 0.967 and back propagation neural network is 0.99 during fitting and 0.88 during forecasting respectively. It was found that the ANN model predicting the groundwater levels in the study area similar to the numerical model for short-horizon predictions.
Keywords: Groundwater flow modeling – MODFLOW Numerical - Artificial neural network – BPNN - Sindapalli Uppodai sub basin.
Title: SIMULATING GROUNDWATER FLOW USING NUMERICAL MODEL AND ARTIFICIAL NEURAL NETWORK - A CASE STUDY
Author: VENKATESAN V, RAJESH PRASANNA P
International Journal of Civil and Structural Engineering Research
ISSN 2348-7607 (Online)
Research Publish Journals
