A Conjunction Method of Wavelet Transform-Particle Swarm Optimization-Support Vector Machine for Streamflow Forecasting

• Published in: Journal of Applied Mathematics Vol. 2014; no. 2014; pp. 132 - 141-910
• Main Authors: Zhang, Fanping, Dai, Huichao, Tang, Deshan
• Format: Journal Article
• Language: English
• Published: Cairo, Egypt Hindawi Limiteds 01.01.2014; Hindawi Puplishing Corporation; Hindawi Publishing Corporation; John Wiley & Sons, Inc; Wiley
• Subjects: Correlation coefficients; Forecasting; Machine learning; Mathematical analysis; Mathematical models; Mathematical optimization; Neural networks; Regression analysis; Streamflow; Support vector machines; Swarm intelligence; Time series; Wavelet; Wavelet transforms; China, People's Rep., Huang He R
• ISSN: 1110-757X; 1687-0042
• DOI: 10.1155/2014/910196

Streamflow forecasting has an important role in water resource management and reservoir operation. Support vector machine (SVM) is an appropriate and suitable method for streamflow prediction due to its best versatility, robustness, and effectiveness. In this study, a wavelet transform particle swarm optimization support vector machine (WT-PSO-SVM) model is proposed and applied for streamflow time series prediction. Firstly, the streamflow time series were decomposed into various details (Ds) and an approximation (A3) at three resolution levels (21-22-23) using Daubechies (db3) discrete wavelet. Correlation coefficients between each D subtime series and original monthly streamflow time series are calculated. Ds components with high correlation coefficients (D3) are added to the approximation (A3) as the input values of the SVM model. Secondly, the PSO is employed to select the optimal parameters, C, ε, and σ, of the SVM model. Finally, the WT-PSO-SVM models are trained and tested by the monthly streamflow time series of Tangnaihai Station located in Yellow River upper stream from January 1956 to December 2008. The test results indicate that the WT-PSO-SVM approach provide a superior alternative to the single SVM model for forecasting monthly streamflow in situations without formulating models for internal structure of the watershed.