The Short‐Time Prediction of Thermospheric Mass Density Based on Ensemble‐Transfer Learning
Abstract Reliable short‐time prediction of thermospheric mass density along the satellite orbit is always essential but challenging for the operation of Low‐Earth orbit satellites. In this paper, three machine‐learning prediction algorithms are investigated, including the Bidirectional Long Short‐Te...
Saved in:
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2023-10-01
|
Series: | Space Weather |
Subjects: | |
Online Access: | https://doi.org/10.1029/2023SW003576 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
_version_ | 1841536336091152384 |
---|---|
author | Peian Wang Zhou Chen Xiaohua Deng Jing‐Song Wang Rongxing Tang Haimeng Li Sheng Hong Zhiping Wu |
author_facet | Peian Wang Zhou Chen Xiaohua Deng Jing‐Song Wang Rongxing Tang Haimeng Li Sheng Hong Zhiping Wu |
author_sort | Peian Wang |
collection | DOAJ |
description | Abstract Reliable short‐time prediction of thermospheric mass density along the satellite orbit is always essential but challenging for the operation of Low‐Earth orbit satellites. In this paper, three machine‐learning prediction algorithms are investigated, including the Bidirectional Long Short‐Term Memory, the Transformer, and the Light Gradient Boosting Machine (LightGBM) ensemble model of the above models. We use satellite data from CHAMP, GOCE, and SWARM‐C to evaluate the robustness and accuracy of different density variations. The comparison demonstrates that all models achieve compelling predictions and are much better than NRLMSISE‐00. The LightGBM ensemble model (LE‐model) consistently outperforms others in accuracy and stability. Furthermore, when the obtained density data from the newly launched satellites are limited, the trained LE‐model can provide a valid prediction for the new satellite orbit by transfer learning. This study offers a promising insight into the short‐time prediction of thermospheric mass density using ensemble‐transfer learning and may be advantageous to future research on space whether. |
format | Article |
id | doaj-art-75dc8419c5da43fdaf8bbd473798e96e |
institution | Kabale University |
issn | 1542-7390 |
language | English |
publishDate | 2023-10-01 |
publisher | Wiley |
record_format | Article |
series | Space Weather |
spelling | doaj-art-75dc8419c5da43fdaf8bbd473798e96e2025-01-14T16:31:16ZengWileySpace Weather1542-73902023-10-012110n/an/a10.1029/2023SW003576The Short‐Time Prediction of Thermospheric Mass Density Based on Ensemble‐Transfer LearningPeian Wang0Zhou Chen1Xiaohua Deng2Jing‐Song Wang3Rongxing Tang4Haimeng Li5Sheng Hong6Zhiping Wu7School of Resources & Environmental Nanchang University Nanchang ChinaInstitute of Space Science and Technology Nanchang University Nanchang ChinaSchool of Resources & Environmental Nanchang University Nanchang ChinaKey Laboratory of Space Weather National Satellite Meteorological Center (National Center for Space Weather) China Meteorological Administration Beijing 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 ChinaComputing Institute of Jiangxi Province Nanchang ChinaAbstract Reliable short‐time prediction of thermospheric mass density along the satellite orbit is always essential but challenging for the operation of Low‐Earth orbit satellites. In this paper, three machine‐learning prediction algorithms are investigated, including the Bidirectional Long Short‐Term Memory, the Transformer, and the Light Gradient Boosting Machine (LightGBM) ensemble model of the above models. We use satellite data from CHAMP, GOCE, and SWARM‐C to evaluate the robustness and accuracy of different density variations. The comparison demonstrates that all models achieve compelling predictions and are much better than NRLMSISE‐00. The LightGBM ensemble model (LE‐model) consistently outperforms others in accuracy and stability. Furthermore, when the obtained density data from the newly launched satellites are limited, the trained LE‐model can provide a valid prediction for the new satellite orbit by transfer learning. This study offers a promising insight into the short‐time prediction of thermospheric mass density using ensemble‐transfer learning and may be advantageous to future research on space whether.https://doi.org/10.1029/2023SW003576thermospheric mass densityshort‐time predictionensemble learningtransfer learningNRLMSISE‐00 |
spellingShingle | Peian Wang Zhou Chen Xiaohua Deng Jing‐Song Wang Rongxing Tang Haimeng Li Sheng Hong Zhiping Wu The Short‐Time Prediction of Thermospheric Mass Density Based on Ensemble‐Transfer Learning Space Weather thermospheric mass density short‐time prediction ensemble learning transfer learning NRLMSISE‐00 |
title | The Short‐Time Prediction of Thermospheric Mass Density Based on Ensemble‐Transfer Learning |
title_full | The Short‐Time Prediction of Thermospheric Mass Density Based on Ensemble‐Transfer Learning |
title_fullStr | The Short‐Time Prediction of Thermospheric Mass Density Based on Ensemble‐Transfer Learning |
title_full_unstemmed | The Short‐Time Prediction of Thermospheric Mass Density Based on Ensemble‐Transfer Learning |
title_short | The Short‐Time Prediction of Thermospheric Mass Density Based on Ensemble‐Transfer Learning |
title_sort | short time prediction of thermospheric mass density based on ensemble transfer learning |
topic | thermospheric mass density short‐time prediction ensemble learning transfer learning NRLMSISE‐00 |
url | https://doi.org/10.1029/2023SW003576 |
work_keys_str_mv | AT peianwang theshorttimepredictionofthermosphericmassdensitybasedonensembletransferlearning AT zhouchen theshorttimepredictionofthermosphericmassdensitybasedonensembletransferlearning AT xiaohuadeng theshorttimepredictionofthermosphericmassdensitybasedonensembletransferlearning AT jingsongwang theshorttimepredictionofthermosphericmassdensitybasedonensembletransferlearning AT rongxingtang theshorttimepredictionofthermosphericmassdensitybasedonensembletransferlearning AT haimengli theshorttimepredictionofthermosphericmassdensitybasedonensembletransferlearning AT shenghong theshorttimepredictionofthermosphericmassdensitybasedonensembletransferlearning AT zhipingwu theshorttimepredictionofthermosphericmassdensitybasedonensembletransferlearning AT peianwang shorttimepredictionofthermosphericmassdensitybasedonensembletransferlearning AT zhouchen shorttimepredictionofthermosphericmassdensitybasedonensembletransferlearning AT xiaohuadeng shorttimepredictionofthermosphericmassdensitybasedonensembletransferlearning AT jingsongwang shorttimepredictionofthermosphericmassdensitybasedonensembletransferlearning AT rongxingtang shorttimepredictionofthermosphericmassdensitybasedonensembletransferlearning AT haimengli shorttimepredictionofthermosphericmassdensitybasedonensembletransferlearning AT shenghong shorttimepredictionofthermosphericmassdensitybasedonensembletransferlearning AT zhipingwu shorttimepredictionofthermosphericmassdensitybasedonensembletransferlearning |