Annual Rainfall-Runoff Modeling of Harnav Watershed of a Sabarmati River basin, India using Artificial Neural Network
| Author(s) | : | Ajay B. Patel, Dr. Geeta S. Joshi |
| Institution | : | PG Student, Civil Engineering Department, Faculty of Technology and Engineering, The Maharaja Sayajirao University of Baroda, Gujarat, India |
| Published In | : | Vol. 4, Issue 14 — January 2017 |
| Page No. | : | - |
| Domain | : | Engineering |
| Type | : | Research Paper |
| ISSN (Online) | : | 2348-4470 |
| ISSN (Print) | : | 2348-6406 |
The use of an Artificial Neural Network (ANN) is becoming common due to its ability to analyze complexnonlinear events. An ANN has a flexible, convenient and easy mathematical structure to identify the nonlinearrelationships between input and output data sets. This capability could efficiently be employed for the differenthydrological 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 ANNmodel 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 hydrologicdata were available for thirty years at Khedbrahma station on Harnav river at the location where Harnav river ismeeting to kosambi river. With the developed ANN model runoff values were predicted and they compared well with theobserved values. The whole computation was performed by using MATLAB capability of develop ANN network by usingnntoolbox. 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 with2-hidden layer node performed best with Lavenberg Marquardt training algorithm in the estimation of Runoff. The modelresults 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 obtainedresults can help the water resource managers to operate the reservoir properly in the case of extreme events such asflooding and drought.
Ajay B. Patel, Dr. Geeta S. Joshi, “Annual Rainfall-Runoff Modeling of Harnav Watershed of a Sabarmati River basin, India using Artificial Neural Network”, International Journal of Advance Engineering and Research Development (IJAERD), Vol. 4, Issue 14, pp. -, January 2017.
