Medium-and-long-term forecasting method for screening factors based on mutual information and principal component analysis

Abstract

The invention discloses a medium and long term forecasting method based on mutual information and principal component analysis screening factors, and relates to the field of hydrological forecasting.The method comprises the following steps of: firstly, analyzing a forecasting factor which greatly affects the predicted runoff based on a mutual information-based factor screening method; extractingmain components of the factors by using a main component analysis method; the optimization of forecasting factors of the forecasting model is realized; according to the method, the linear and nonlinear relationship between two variables is fully considered, the information of the overlapped part is removed, the number of original variables is reduced, and the characteristics of a research object are typically shown, so that the obtained medium and long term runoff forecasting model is better in forecasting effect and higher in model stability compared with a traditional method.

Description

technical field [0001] The invention relates to the field of hydrological forecasting, in particular to a medium and long-term forecasting method based on mutual information and principal component analysis screening factors. Background technique [0002] Scientifically and rationally carrying out medium- and long-term hydrological forecasting is the basis for the management and development of water resources in the basin, and it is of great significance to promote social and economic development. [0003] At present, medium and long-term hydrological forecast methods mainly include time series method, fuzzy mathematics method, artificial neural network method, gray system method, wavelet analysis method, chaos theory method, support vector machine method, optimal combination prediction method, etc. Among them, artificial neural network, as a highly parallel radial basis network, has strong nonlinear mapping ability, is suitable for solving various nonlinear, fuzzy, uncertai...

AI Technical Summary

Problems solved by technology

However, it is difficult to avoid too many input variables by using mutual information screening factors, which will increase the sample observation error and increase the complexity of the network structure, which is not conducive to the improvement of the stability of the neural network model. Although the principal component analysis can extract the prediction factors The main information part, but most of them stay on the linear correlation analysis, which is not enough to reveal the complex change mechanism of runoff formation

Images