Hydrologic Time Series Prediction Model Based On Wavelet De-noising And Rank Set-Pair Analysis

The wavelet analysis is used to the field of water science widely, and the aspect of set pair analysis was a method of uncertainty analysis, which now is preliminary apply to water resource research. In this paper, the advantages of wavelet analysis and set pair analysis were united to set a hydrologic time series prediction model named WD-RSPA model.Hydrological series were affected by astronomy, geography, climate, human and so on, therefore, they have the non-linear, variability, randomness and cyclical. Especially under large-scale conditions, there are many problems in the hydrologic series prediction, such as single construction method and without consideration of the noise.Therefore, a hydrologic series prediction model(WD-RSPA model) is developed on the combination of wavelet de-noise (WD) method and rank and set-pair analysis(RSPA), which takes advantage of multi-scale analysis and noise reduction in wavelet analysis and clear concept, simple calculation, and overcomes the subjectivity to certain the standard of set elements in RSPA.The WD-RSPA model is applied to predict the annual runoff and the annual precipitation. The annual runoff series of Hua Yuankou station and San Menxia station, the annual precipitation series of Bejing station and Zheng Zhou station were used in this paper. The prediction results by WD-RSPA model are compared with results of traditional RSPA model, AR(p) model and neural network model. It indicates that:(1) the concept to establish WD-RSPA model is clear, the computation is simper and the accuracy of prediction results is higher;(2)WD-RSPA model can get more accurate results on extremum prediction than AR(p) model and RSPA model;(3) the choice of wavelet function will vary the de-noising series, and the difference of sets dimension(T) will change the rank of set pairs, so appropriate wavelet function and sets dimension(T) will lead to higher precision.