Hydrological time series prediction method based on combination model

Abstract

The invention discloses a hydrological time series prediction method based on a wavelet neural network and a difference autoregression moving average model. The method comprises: obtaining hydrological time series data and performing normalization processing; performing discrete wavelet decomposition on the normalized hydrological time series, to obtain a scale changing series and a plurality of wavelet transforming serieses; using an ARIMA model to perform fitting prediction on the scale changing series, to obtain a prediction value series, and performing wavelet reconstruction to obtain a normalized water level prediction series; using a WNN model to perform training fitting on the wavelet transforming serieses, to obtain prediction value serieses; performing reverse normalization on a normalized water level time series, to obtain a prediction value of an original series. The invention provides a new combination prediction model for water level and flow prediction of rivers and lakesfor water conservancy and hydropower industries. Prediction precision of the model is better than that of a conventional single neural network model and existing combination prediction methods. The method has high application value for flood control and drought relief, and irrigation and power generation.

Description

technical field [0001] The present invention relates to a model construction method for water level prediction one day in advance based on data mining and neural network field hydrological time series. Technologies such as wavelet neural networks are used to predict future water levels. Background technique [0002] The water level prediction of river runoff is an important part of hydrological forecasting. The change of water level has trend and seasonal characteristics, and it also contains noise factors. The prediction ability of a single model is limited. The traditional ARIMA (differential autoregressive moving average model) The accuracy of the model prediction nonlinear time series is not high enough, and the structure of WNN (wavelet neural network) neural network is complex, which is prone to the problem of "curse of dimensionality". Individual optimization of these methods does not overcome the limitations of individual methods. Contents of the invention [000...

AI Technical Summary

Problems solved by technology

[0003] Purpose of the invention: In view of the shortcomings of the existing time series forecasting methods that are not targeted and the prediction accuracy is relatively low, according to the fluctuation characteristics of the hydrological time series, the method of combining the wavelet neural network and the ARIMA model is used to simulate the hydrological time series Forecasting, Improving the Accuracy of Hydrological Time Series Forecasting

Images