The Short‐Time Prediction of the Energetic Electron Flux in the Planetary Radiation Belt Based on Stacking Ensemble‐Learning Algorithm
Abstract High energy electrons in planetary radiation belts are a major threat to satellites and communications in deep space applications. In order to predict the variations of energetic electron fluxes for different energy channels, we proposed a new ensemble machine leaning model for differential...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-02-01
|
| Series: | Space Weather |
| Online Access: | https://doi.org/10.1029/2021SW002969 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536340982759424 |
|---|---|
| author | Rongxin Tang Yuhao Tao Jiahao Li Zhou Chen Xiaohua Deng Haimeng Li |
| author_facet | Rongxin Tang Yuhao Tao Jiahao Li Zhou Chen Xiaohua Deng Haimeng Li |
| author_sort | Rongxin Tang |
| collection | DOAJ |
| description | Abstract High energy electrons in planetary radiation belts are a major threat to satellites and communications in deep space applications. In order to predict the variations of energetic electron fluxes for different energy channels, we proposed a new ensemble machine leaning model for differential electron flux from 30 keV to 4 MeV in the Earth's radiation belts based on the RBSP‐A observation data from March 2013 to December 2017. The deep neural network (DNN), the convolutional neural network (CNN), the combination of CNN and DNN (CNN&DNN), the linear regression (LR), and the light gradient boosting machine (LightGBM) are among the machine learning models chosen. We carefully compared the electron flux predictions for 20 energy levels and all five models can present valid short‐time flux forecasts. The DNN model has the poorest result. The LR model is good for short‐term forecasting but not so good for long‐term forecasting. The LightGBM ensemble model is highly stable, and it has always outperformed other independent models in terms of forecast accuracy. Then the comparison by adding AE and SYM‐H indexes is given and the influence of geomagnetic activity conditions can be negligible for this short‐time prediction. Furthermore, we applied these five models on Saturn and finally got very similar prediction results. Our results will be significantly useful in instrument designs and system control of future scientific satellites in deep space explorations. |
| format | Article |
| id | doaj-art-8f66a27b8ee84edcbb779c56ecfe3eb5 |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2022-02-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-8f66a27b8ee84edcbb779c56ecfe3eb52025-01-14T16:30:59ZengWileySpace Weather1542-73902022-02-01202n/an/a10.1029/2021SW002969The Short‐Time Prediction of the Energetic Electron Flux in the Planetary Radiation Belt Based on Stacking Ensemble‐Learning AlgorithmRongxin Tang0Yuhao Tao1Jiahao Li2Zhou Chen3Xiaohua Deng4Haimeng Li5Institute of Space Science and Technology Nanchang University Nanchang ChinaInstitute of Space Science and Technology Nanchang University Nanchang ChinaSchool of Information and Engineering Nanchang University Nanchang ChinaInstitute of Space Science and Technology Nanchang University Nanchang ChinaInstitute of Space Science and Technology Nanchang University Nanchang ChinaInstitute of Space Science and Technology Nanchang University Nanchang ChinaAbstract High energy electrons in planetary radiation belts are a major threat to satellites and communications in deep space applications. In order to predict the variations of energetic electron fluxes for different energy channels, we proposed a new ensemble machine leaning model for differential electron flux from 30 keV to 4 MeV in the Earth's radiation belts based on the RBSP‐A observation data from March 2013 to December 2017. The deep neural network (DNN), the convolutional neural network (CNN), the combination of CNN and DNN (CNN&DNN), the linear regression (LR), and the light gradient boosting machine (LightGBM) are among the machine learning models chosen. We carefully compared the electron flux predictions for 20 energy levels and all five models can present valid short‐time flux forecasts. The DNN model has the poorest result. The LR model is good for short‐term forecasting but not so good for long‐term forecasting. The LightGBM ensemble model is highly stable, and it has always outperformed other independent models in terms of forecast accuracy. Then the comparison by adding AE and SYM‐H indexes is given and the influence of geomagnetic activity conditions can be negligible for this short‐time prediction. Furthermore, we applied these five models on Saturn and finally got very similar prediction results. Our results will be significantly useful in instrument designs and system control of future scientific satellites in deep space explorations.https://doi.org/10.1029/2021SW002969 |
| spellingShingle | Rongxin Tang Yuhao Tao Jiahao Li Zhou Chen Xiaohua Deng Haimeng Li The Short‐Time Prediction of the Energetic Electron Flux in the Planetary Radiation Belt Based on Stacking Ensemble‐Learning Algorithm Space Weather |
| title | The Short‐Time Prediction of the Energetic Electron Flux in the Planetary Radiation Belt Based on Stacking Ensemble‐Learning Algorithm |
| title_full | The Short‐Time Prediction of the Energetic Electron Flux in the Planetary Radiation Belt Based on Stacking Ensemble‐Learning Algorithm |
| title_fullStr | The Short‐Time Prediction of the Energetic Electron Flux in the Planetary Radiation Belt Based on Stacking Ensemble‐Learning Algorithm |
| title_full_unstemmed | The Short‐Time Prediction of the Energetic Electron Flux in the Planetary Radiation Belt Based on Stacking Ensemble‐Learning Algorithm |
| title_short | The Short‐Time Prediction of the Energetic Electron Flux in the Planetary Radiation Belt Based on Stacking Ensemble‐Learning Algorithm |
| title_sort | short time prediction of the energetic electron flux in the planetary radiation belt based on stacking ensemble learning algorithm |
| url | https://doi.org/10.1029/2021SW002969 |
| work_keys_str_mv | AT rongxintang theshorttimepredictionoftheenergeticelectronfluxintheplanetaryradiationbeltbasedonstackingensemblelearningalgorithm AT yuhaotao theshorttimepredictionoftheenergeticelectronfluxintheplanetaryradiationbeltbasedonstackingensemblelearningalgorithm AT jiahaoli theshorttimepredictionoftheenergeticelectronfluxintheplanetaryradiationbeltbasedonstackingensemblelearningalgorithm AT zhouchen theshorttimepredictionoftheenergeticelectronfluxintheplanetaryradiationbeltbasedonstackingensemblelearningalgorithm AT xiaohuadeng theshorttimepredictionoftheenergeticelectronfluxintheplanetaryradiationbeltbasedonstackingensemblelearningalgorithm AT haimengli theshorttimepredictionoftheenergeticelectronfluxintheplanetaryradiationbeltbasedonstackingensemblelearningalgorithm AT rongxintang shorttimepredictionoftheenergeticelectronfluxintheplanetaryradiationbeltbasedonstackingensemblelearningalgorithm AT yuhaotao shorttimepredictionoftheenergeticelectronfluxintheplanetaryradiationbeltbasedonstackingensemblelearningalgorithm AT jiahaoli shorttimepredictionoftheenergeticelectronfluxintheplanetaryradiationbeltbasedonstackingensemblelearningalgorithm AT zhouchen shorttimepredictionoftheenergeticelectronfluxintheplanetaryradiationbeltbasedonstackingensemblelearningalgorithm AT xiaohuadeng shorttimepredictionoftheenergeticelectronfluxintheplanetaryradiationbeltbasedonstackingensemblelearningalgorithm AT haimengli shorttimepredictionoftheenergeticelectronfluxintheplanetaryradiationbeltbasedonstackingensemblelearningalgorithm |