STUDY OF UKAI DAM RESERVOIR USING ANN TECHNIQUES

Abstract

Hydrologic forecasting plays a increasing role in water resource management, as engineers are required to
make component forecasts of natural inflows to reservoirs for various purposes. Prediction for hydrologic events has
always been an important issue for optimizing and planning the whole system. In this study, two different ANN
(Artificial Neural Networks) techniques (Generalized Feed Forward network and Multilayer Perceptron) were used
for Ukai reservoir project. A total of 21 years of historical data were used to train and test the networks. To evaluate
the accuracy of the proposed model, the Root Mean Squared Error (MSE) and the Correlation Coefficient (CC) were
employed and found the network to be cross validated and trained properly for both models. The developed model
shows good results with actual observation.