The Application of Wavelet Neural Networks on Rainfall Forecast

Article Preview

Abstract:

We proposed the improved wavelet neural network and applied it to forecast rainfall. Activation function was selected automatically from three wavelet basis functions. The three given wavelet basis functions were Morlet, Mexican-Hat and Different Of Gauss(DOG) wavelet basis functions respectively. We demonstrat its effectiveness by forecasts rainfall of some cities in China. The results show that the improved wavelet networks method is better than BP neural network method in rainfall forecast.

You might also be interested in these eBooks

Info:

Periodical:

Pages:

3370-3373

Citation:

Online since:

December 2012

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2013 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] Q. Zhang, A. Benveniste, Wavelet networks, IEEE Transations on Neural Networks, vol. 3, pp.889-898, 1992.

Google Scholar

[2] Weiwei Xiao, Haiyan Liu, Using Wavelet Networks in Image Compression, Conference proceedings of the 7th International Conference on Natural Computation, 719-723,2011.

Google Scholar

[3] F. Shi, X. Wang, L. Yu and Y. Li, Matlab Neural Network Analysis of Thirty Cases, Beijing, China: Beijing University of Aeronautics and Astronautics Press, pp.208-217, 2010.

Google Scholar