A wavelet-neural network hybrid modelling approach for estimating and predicting river monthly flows |
| |
Authors: | Shouke Wei Hong Yang Jinxi Song Karim Abbaspour Zongxue Xu |
| |
Institution: | 1. Swiss Federal Institute of Aquatic Science and Technology (EAWAG) , CH-8600 , Dübendorf , Switzerland E-mail: shouke.wei@gmail.com;2. Emodlogic Technology Inc , Vancouver , British Columbia , V5P 3R1 , Canada;3. Department of Forest Resources Management , University of British Columbia , Vancouver , British Columbia , V6T 1Z4 , Canada shouke.wei@gmail.com;5. Swiss Federal Institute of Aquatic Science and Technology (EAWAG) , CH-8600 , Dübendorf , Switzerland E-mail: shouke.wei@gmail.com;6. College of Urban and Environmental Sciences, Northwest University , Xi'an , 710069 , China;7. College of Water Sciences, Beijing Normal University , Beijing , 100875 , China |
| |
Abstract: | Abstract A wavelet-neural network (WNN) hybrid modelling approach for monthly river flow estimation and prediction is developed. This approach integrates discrete wavelet multi-resolution decomposition and a back-propagation (BP) feed-forward multilayer perceptron (FFML) artificial neural network (ANN). The Levenberg-Marquardt (LM) algorithm and the Bayesian regularization (BR) algorithm were employed to perform the network modelling. Monthly flow data from three gauges in the Weihe River in China were used for network training and testing for 48-month-ahead prediction. The comparison of results of the WNN hybrid model with those of the single ANN model show that the former is able to significantly increase the prediction accuracy. Editor D. Koutsoyiannis; Associate editor H. Aksoy Citation Wei, S., Yang, H., Song, J.X., Abbaspour, K., and Xu, Z.X., 2013. A wavelet-neural network hybrid modelling approach for estimating and predicting river monthly flows. Hydrological Sciences Journal, 58 (2), 374–389. |
| |
Keywords: | instream flow wavelet-neural network Levenberg-Marquardt Bayesian regularization |
|
|