Regional ionized layer TEC forecasting method based on LSTM and GCN

Abstract

The invention discloses a regional ionized layer TEC forecasting method based on LSTM and GCN, and relates to the technical field of space environment forecasting. The forecasting method comprises the following steps: firstly, obtaining an ionized layer TEC data set, a solar activity index F10.7 and a geomagnetic index Dst, performing data cleaning, filling and other processing on the data sets, then dividing the data sets into a training set and a test set, and performing zero-mean standardization processing on the training set and the test set; determining a topological structure and network parameters of a regional ionosphere TEC forecasting model, and training a regional ionosphere TEC short-term forecasting model based on an LSTM-GCN network; and finally, inputting the test set data to run the forecasting model, carrying out anti-standardization on an output sequence to restore data, and carrying out error analysis and model performance evaluation. According to the method, the network advantages of the LSTM and the GCN are integrated, the spatial-temporal characteristics of the ionized layer TEC sequence are effectively extracted, and the forecasting precision of the regional ionized layer TEC can be improved.

Description

technical field [0001] The invention relates to a regional ionospheric TEC prediction method based on LSTM and GCN, and belongs to the technical field of space environment prediction. Background technique [0002] The ionosphere is an important component of the earth's atmosphere. It is located in the atmospheric part within the range of 60-1000 km from the ground. Due to the combined action of solar rays, cosmic rays and other falling ions, the atmospheric molecules in the ionosphere are ionized, so the ionosphere contains a large amount of These ions and free electrons will have a great impact on the propagation of radio waves. For example, the ionosphere will cause working errors in wireless communication, navigation and positioning, over-the-horizon radar and other systems. The total electric content of the ionosphere (Total Electric Contents, TEC) is the total electron content of the ionosphere per unit area, and is an important parameter used to characterize the ionosp...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem that the existing ionospheric TEC prediction model based on deep learning method cannot be well applied to regional or global ionospheric TEC prediction, the present invention proposes a regional ionospheric TEC prediction method based on LSTM and GCN, It can better improve the prediction accuracy of regional ionospheric TEC, not only guarantee the stable operation of communication, navigation and satellite positioning systems, but also provide reference value for the analysis and research of ionospheric space environment

Images