Modeling of Rainfall-Runoff Correlations Using Artificial Neural Network-A Case Study of Dharoi Watershed of a Sabarmati River Basin, India

Abstract

The use of an Artificial Neural Network (ANN) is becoming common due to its ability to analyse 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 for establishing monthly and annual rainfall runoff correlations. The hydrologic variables used were monthly and annual rainfall and runoff for monthly and annual time period of monsoon season. The ANN model developed in this study is applied to Dharoi reservoir watersheds of Sabarmati river basin of India. The hydrologic data were available for twenty-nine years at Dharoi station at Dharoi dam project. The model results yielding into the least error is recommended for simulating the rainfall-runoff characteristics of the watersheds. 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.

River Flood Modelling For Flooding Risk Mitigation in Iraq

“…Urban floods in developing countries are mainly characterized by fundamental factors, which seem to present limitations and knowledge gaps towards their analyses in the context of developing countries. First, the means of representing the hydrological, climatic, and human factors that drive urban flooding in these regions are complex, particularly in the formulation and solution of shallow water equations that underlies flood modeling [17]. Secondly, the urban geomorphology, flood hydrodynamics, and detailed topographic data are still completely inaccessible to many urban watersheds in developing countries.…”

“…Although Iraq is a developing country, where statistics and data are rarely available, there are some convenient flood models which can solve these constraints [18]. For instance, Gharib et al (2017) [15] and Patel & Joshi (2017) [17] showed in their studies that the lack of availability of data can be avoided by adopting computer software for flooding simulation. For examples, GIS, Global Mapper, Artificial Neural Network (ANN), and rainfall-runoff modelling that can be used in specifically in developing countries, due to its simplicity and efficiency.…”

A Multi-Layer Perceptron (MLP)-Fire Fly Algorithm (FFA)-based model for sediment prediction

“…The rainfall-runoff correlation is positively modeled using ANNs (Raid and Mania 2004;Maier et al 2010;Patel and Joshi 2017). ANNs were also measured as a dominant instrument to use in monthly river flow prediction and various groundwater problems (Coulibaly et al 2001;Singh et al 2013).…”

Developing a Discharge Estimation Model for Ungauged Watershed Using CNN and Hydrological Image

“…Expressing the relationship between precipitation and discharge in a specific watershed is not numerically easy, even if a constitutive model is used, owing to the condition that complex natural phenomena must be expressed with numerous formulae [14]. As an alternative, an empirical model explained by the stable relationship between the independent variable and the dependent variable can be proposed [15]. The empirical model is relatively simple to construct compared to the constitutive model, and the frequency of using the empirical model has increased in several previous studies.…”