WD-RBF (wavelet denoising-radial basis function)-based analogue prediction method of hydrological time sequence

Abstract

The invention discloses a WD-RBF (wavelet denoising-radial basis function)-based analogue prediction method of a hydrological time sequence. The method comprises the following steps of: obtaining a wavelet coefficient under each dimension by wavelet transform according to the selected hydrological time sequence; removing sequence noise by using a soft threshold denoising technology, and obtaining a denoised hydrological time sequence by wavelet reconstruction; carrying out modified RBF network modeling on the denoised sequence, and carrying out analogue prediction on the sequence by utilizing the built network. The method disclosed by the invention is applied to prediction of four groups of hydrological time sequences, and compared with an ARIMA (autoregressive integrated moving average) model and an RBF method. The result shows that the nonlinear relationship in the hydrological time sequences can be excavated by the RBF; and noise ingredients in the hydrological time sequences can be effectively identified and eliminated by wavelet denoising, so as to achieve the target of restoring a true sequence. The experiment validates that the WD-RBF method can display the performance superior to the ARIMA model and the RBF not only on sequence simulation but also on numerical prediction, and has higher accuracy.

Description

technical field [0001] The invention relates to a simulation prediction method of hydrological time series, in particular to a WD-RBF simulation prediction method based on wavelet denoising and RBF neural network coupling. Background technique [0002] With the rapid development of society, the excessive exploitation and utilization of water resources put forward higher requirements for the rational allocation of water resources. Accurate prediction of hydrological time series is the premise of scientific allocation of water resources, which is of great significance to the scientific formulation of water resources planning and the sustainable development of river basins and regions. [0003] Previous hydrological time series simulation and prediction models, such as AR, MA, ARMA and other models are all linear mapping models, and the few nonlinear models, such as bilinear models, have a very limited degree of nonlinearity, and are used in hydrological simulation and predicti...

AI Technical Summary

Problems solved by technology

[0036] Purpose of the invention: the purpose of the present invention is to overcome the non-linear identification and noise pollution problems in hydrological time series simulation prediction, provide a kind of hydrological time series simulation prediction method based on WD-RBF, coupling wavelet denoising technology and RBF neural network, through Wavelet denoising can effectively identify and eliminate the noise components in the hydrological time series, construct RBF network to effectively mine the nonlinear correlation in the time series, and achieve the purpose of effective simulation and prediction of the series

Images