Modelling rainfall-runoff using various intelligent computing techniques for Haripura and Baur Dams in Uttarakhand
Loading...
Date
2021-07
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand)
Abstract
Water resources are primary aspects of social, cultural and economic growth of a country. Water conservation is a basic idea for sustainable development of agricultural production, industrialization and high living standards of people. In this study, intelligent computing techniques like artificial neural network (ANN), wavelet coupled ANN (WANN), adaptive neuro-fuzzy inference system (ANFIS), support vector machine (SVM), and nonlinear regression (NLR) were used for rainfall-runoff modelling. The rainfall and runoff data of 20 years duration (1996-2015) for Haripura dam and 8 years duration (2006-2013) for Baur dam were used in this study. These dams are located in Uttarakhand. The data were used for prediction of present day runoff for both of the dams. Gamma test was used to select the best input combination for the development of models. Multilayer perceptron and various activation functions were used for ANN, various wavelet functions were used for WANN, various membership functions were used for ANFIS and radial kernel function was used for SVM techniques. The results showed that the Db-2 WANN model and SVM model were found to be the best among all developed models for Haripura and Baur dams. As the study areas are close to each other, their climatic and meteorological conditions and even soil characteristics are same. Hence both dams are comparable and a common model can be suggested for both Haripura and Baur dams.