Global ionospheric electron total content prediction method based on semantic segmentation

Abstract

The invention discloses a global ionospheric electron total content prediction method based on semantic segmentation. The method comprises a training stage and a prediction stage. The training stage comprises: 1, collecting a global ionospheric electron total content thermodynamic diagram, and forming an original image sequence after adjusting a horizontal position; 2, constructing a training sample set; and 3, constructing a global ionospheric electron total content prediction model based on semantic segmentation, and performing training by utilizing the training sample set. The prediction stage comprises: 4, collecting K global ionospheric electron total content thermodynamic diagrams every day, and continuously collecting the thermodynamic diagrams for t days; adjusting the horizontal position of a pixel of the acquired image, establishing a prediction sample, and taking the prediction sample as the input of a global ionospheric electron total content prediction model to obtain a prediction thermodynamic diagram; and 5, carrying out longitude sorting on the predicted thermodynamic diagram to obtain a predicted global ionospheric electron total content thermodynamic diagram. According to the method, the change of the ionized layer in space and time is combined, the existing observation data is fully and effectively utilized, and the prediction precision is improved.

Description

technical field [0001] The invention belongs to the field of ionospheric detection, in particular to a method for predicting the total electron content of the global ionosphere based on semantic segmentation. Background technique [0002] The ionosphere is an important part of the earth's space environment, and the electron content of the ionosphere is an important physical characteristic parameter. It is not only necessary to study the temporal and spatial variation of the ionosphere electron content, but also to predict it. At present, the forecast of ionospheric electron content can be divided into long-period forecast and short-period forecast according to the different forecast duration. These forecasting methods use the electronic content time series data observed in a certain geographical location to establish mathematical models for forecasting. The ionospheric electron content changes continuously not only in the time dimension but also in the space. The traditiona...

AI Technical Summary

Problems solved by technology

The ionospheric electron content changes continuously not only in the time dimension but also in the space. The traditional method only considers the time change of the ionospheric electron content and ignores the spatial correlation. Therefore, it is necessary to make full use of the ionospheric electron content. Content observation data, analysis of its temporal and spatial changes and forecasting, high-precision ionospheric electron content prediction model will be of great significance to ionospheric related research

Images