Time Series Modeling of River Flow Using Wavelet Neural Networks

B Krishna,P C Nayak,Y R Satyaji Rao

doi:10.4236/jwarp.2011.31006

Abstract

A new hybrid model which combines wavelets and Artificial Neural Network (ANN) called wavelet neural network (WNN) model was proposed in the current study and applied for time series modeling of river flow. The time series of daily river flow of the Malaprabha River basin (Karnataka state, India) were analyzed by the WNN model. The observed time series are decomposed into sub-series using discrete wavelet transform and then appropriate sub-series is used as inputs to the neural network for forecasting hydrological variables. The hybrid model (WNN) was compared with the standard ANN and AR models. The WNN model was able to provide a good fit with the observed data, especially the peak values during the testing period. The benchmark results from WNN model applications showed that the hybrid model produced better results in estimating the hydrograph properties than the latter models (ANN and AR).

Highlights

Water resources planning and management requires, output from hydrological studies
This paper reports a hybrid model called wavelet based neural network model for time series modeling of river flow
The proposed model is a combination of wavelet analysis and artificial neural network (WNN)

Summary

Introduction

Water resources planning and management requires, output from hydrological studies. These are mainly in the form of estimation or forecasting of the magnitude of hydrological variables like precipitation, stream flow and groundwater levels using historical data. Time series modeling for either data generation or forecasting of hydrological variables is an important step in the planning and management of water resources. ARMA models have been widely used for modeling water resources time-series modeling [2]. The time series models are used to describe the stochastic structure of the time sequence of a hydrological variable measured over time. Time series analysis requires mapping complex relationships between input(s) and output(s), since the forecasted values are mapped as a function of observed patterns in the past. It seems necessary that nonlinear models such as neural networks, which are suited to complex nonlinear problems, be used for the time series modeling of river flow

Methods

Results

Conclusion