Annual Rainfall-Runoff Modeling of Harnav Watershed of a Sabarmati River basin, India using Artificial Neural Network

Abstract

The use of an Artificial Neural Network (ANN) is becoming common due to its ability to analyze complex
nonlinear events. An ANN has a flexible, convenient and easy mathematical structure to identify the nonlinear
relationships between input and output data sets. This capability could efficiently be employed for the different
hydrological models such as rainfall-runoff models, which are inherently nonlinear in nature. Artificial Neural Networks
(ANN) can be used in cases where the available data is limited. The present work involves the development of an ANN
model using Feed-Forward Back Propagation algorithm. The hydrologic variables used were annual rainfall and runoff.
The ANN model developed in this study is applied to Harnav watershed of Sabarmati river basin of India. The hydrologic
data were available for thirty years at Khedbrahma station on Harnav river at the location where Harnav river is
meeting to kosambi river. With the developed ANN model runoff values were predicted and they compared well with the
observed values. The whole computation was performed by using MATLAB capability of develop ANN network by using
nntoolbox. In this study, from the total number of input data set, 70% have been used as training data set, while 15%
have been used as testing data set and 15% have been used as validation dataset. It was observed that only input set with
2-hidden layer node performed best with Lavenberg Marquardt training algorithm in the estimation of Runoff. The model
results yielding into the least error is recommended for simulating the rainfall-runoff characteristics of the watershed.
The results indicate that the Artificial Neural Network is a powerful tool in modelling rainfall-runoff. The obtained
results can help the water resource managers to operate the reservoir properly in the case of extreme events such as
flooding and drought.