Journal of Hydroinformatics In Press, Uncorrected Proof © IWA Publishing 2012  |  doi:10.2166/hydro.2012.143

Improving prediction accuracy of river discharge time series using a Wavelet-NAR artificial neural network

Shouke Wei, Depeng Zuo and Jinxi Song

Department System Analysis, Integrated Assessment and Modelling, The Swiss Federal Institute of Aquatic Science and Technology (EAWAG), 8600 Dübendorf, Switzerland. E-mail: shouke.wei@gmail.com
College of Water Sciences, Beijing Normal University, 100875 Beijing, China
College of Urban and Environmental Sciences, Northwest University, 710069 Xi'an, China
Apmosian SciTech International Inc., BC V5P 3R1, Vancouver, Canada

First received 20 October 2011; accepted in revised form 5 March 2012. Available online 13 June 2012

This study developed a wavelet transformation and nonlinear autoregressive (NAR) artificial neural network (ANN) hybrid modelling approach to improve the prediction accuracy of river discharge time series. Daubechies 5 discrete wavelet was employed to decompose the time series data into sub-series with low and high frequency, and these subseries were then used instead of the original data series as the input vectors for the designed NAR network (NARN) with the Bayesian regularization (BR) optimization algorithm. The proposed hybrid approach was applied to make multi-step-ahead predictions of monthly river discharge series in the Weihe River in China. The prediction results of this hybrid model were compared with those of signal NARNs and the traditional Wavelet-Artificial Neural Network hybrid approach (WNN). The comparison results revealed that the proposed hybrid model could significantly increase the prediction accuracy and prediction period of the river discharge time series in the current case study.

Keywords: bayesian regularization; NAR network; river discharge; wavelet transformation; weihe river

Full Text PDF