Medium energy electron fluxes in Earth's outer radiation belt: a machine learning model
Abstract
The radiation belts of the Earth, which are the zones of charged energetic particles trapped by the geomagnetic field, comprise enormous and dynamic systems posing significant threat to satellite communication. While the inner belt is relatively stable, the outer belt is highly variable and depends substantially on solar activity; therefore, accurate and improved models of electron fluxes in the outer radiation belts are essential for understanding of the underlying physical processes. Albeit many models have been developed for the Geostationary orbit and relativistic energies, the prediction of electron flux in the 100-600 keV energy range still remains challenging. We present a data-driven model of the medium energies (100-600 keV) differential electron fluxes in the outer radiation belt based on machine learning algorithms. We use 16 years of electron observations by the CXD particle detector onboard each of the 23 GPS satellites. We set up a 3D model for prediction in terms of L-values, MLT and satellite latitude. As input, we use 28 OMNI solar wind and geomagnetic parameters. We discuss the importance of individual input variables and show that the most significant parameters are the solar wind velocity, SYM-H index and IMF-Bx. We present two modifications of the model, one based solely on solar wind data and another one only on geomagnetic indices and evaluate their performance.
- Publication:
-
AGU Fall Meeting Abstracts
- Pub Date:
- December 2019
- Bibcode:
- 2019AGUFMNG21A..05S
- Keywords:
-
- 1914 Data mining;
- INFORMATICS;
- 1942 Machine learning;
- INFORMATICS;
- 7599 General or miscellaneous;
- SOLAR PHYSICS;
- ASTROPHYSICS;
- AND ASTRONOMY;
- 7999 General or miscellaneous;
- SPACE WEATHER