Hydrological time series prediction network and method based on feature extraction and guidance

Abstract

The application provides a hydrological time series prediction network and method based on feature extraction and guidance, and belongs to the technical field of hydrological time prediction; solves the problems of insufficient prediction accuracy and rapid error growth of existing methods; adopts an encoder-decoder model structure of Informer, further includes a feature extraction module, and the output of the feature extraction module is used as the input of the encoder; the feature extraction module includes a time domain feature extraction module, a frequency domain feature extraction module and a dynamic feature fusion module; the time domain feature extraction module is used for extracting multi-scale time domain features in the hydrological time series data; the frequency domain feature extraction module extracts global frequency domain features in the hydrological time series data through discrete cosine transformation; the dynamic feature fusion module is used for channel-level and spatial-level fusion of the time domain features and the frequency domain features; the guide attention mechanism is used to replace the sparse attention mechanism in the original encoder; and the application is applied to hydrological time series prediction.

Images