Rainfall-runoff modeling for the Hoshangabad Basin of Narmada River using artificial neural network
- PDF / 1,733,976 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 3 Downloads / 250 Views
ORIGINAL PAPER
Rainfall-runoff modeling for the Hoshangabad Basin of Narmada River using artificial neural network Vikas Poonia 1
&
Hari Lal Tiwari 2
Received: 20 May 2020 / Accepted: 2 September 2020 # Saudi Society for Geosciences 2020
Abstract Accurate modeling of the rainfall-runoff process is still a challenging job despite the availability of various modeling methods, such as data-driven or knowledge-driven, developed by various researchers in their previous studies. Among these models, artificial neural network (ANN)-based rainfall-runoff models play an important role in the hydrology due to their capability of reproducing the highly nonlinear nature between the various factors involved in the hydrology of the watershed. In this paper, an attempt has been made to develop an ANN-based rainfall-runoff model for the Hoshangabad catchment of the Narmada River in Madhya Pradesh. Two different models, feed-forward back propagation (FFBP) and radial basis function (RBF) network models, were developed using several arrangements of input dataset then relate their capability of flow estimation for the period 2004– 2013. The best model performance was selected based on various performance evaluation criteria, i.e., R2, MSE, and AARE. Based on this study, it is observed that the ANN model provides better outcomes for the dataset scaled between zero and one. For the Hoshangabad catchment, an input arrangement of present-day rainfall with antecedent rainfall up to 4 days and a 1-day antecedent runoff value provide the best outcomes for both models (FFBP and RBF). Out of this, the RBF network performs better as compared with the FFBP network with R2 value of 0.9964. The result of the present study suggests that ANN network models an essential tool for predicting the hydrological responses in agricultural watersheds and thus helps to provide sustainable measures for a watershed. Keywords Antecedent . Artificial neural network . Back propagation . RBF . Streamflow
Introduction The rainfall-runoff relationship is complicated to understand due to its complex hydrological nature (Wang et al. 2013). It may be due to the large spatio-temporal unpredictability of basin and rainfall patterns. The R-R model calculates the conversion of rainfall into runoff. Mulvany (1850) develops the
Responsible Editor: Broder J. Merkel Electronic supplementary material The online version of this article (https://doi.org/10.1007/s12517-020-05930-6) contains supplementary material, which is available to authorized users. * Vikas Poonia [email protected] 1
Discipline of Civil Engineering, Indian Institute of Technology Indore, Indore, India
2
Department of Civil Engineering, MANIT, Bhopal, India
rational method to calculate peak discharge, and various other models have also been presented. Based on the governing processes, the rainfall-runoff models may be classified into two types, i.e., data-driven (system theoretic) and knowledge-driven (physically based) (Jain et al. 2004; Srinivasulu and Jain 2006; Devia et al. 2015). These p
Data Loading...
