Improving Thermospheric Density Predictions in Low‐Earth Orbit With Machine Learning
Abstract Thermospheric density is one of the main sources of uncertainty in the estimation of satellites' position and velocity in low‐Earth orbit. This has negative consequences in several space domains, including space traffic management, collision avoidance, re‐entry predictions, orbital lif...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-02-01
|
| Series: | Space Weather |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2023SW003652 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536406717988864 |
|---|---|
| author | Giacomo Acciarini Edward Brown Tom Berger Madhulika Guhathakurta James Parr Christopher Bridges Atılım Güneş Baydin |
| author_facet | Giacomo Acciarini Edward Brown Tom Berger Madhulika Guhathakurta James Parr Christopher Bridges Atılım Güneş Baydin |
| author_sort | Giacomo Acciarini |
| collection | DOAJ |
| description | Abstract Thermospheric density is one of the main sources of uncertainty in the estimation of satellites' position and velocity in low‐Earth orbit. This has negative consequences in several space domains, including space traffic management, collision avoidance, re‐entry predictions, orbital lifetime analysis, and space object cataloging. In this paper, we investigate the prediction accuracy of empirical density models (e.g., NRLMSISE‐00 and JB‐08) against black‐box machine learning (ML) models trained on precise orbit determination‐derived thermospheric density data (from CHAMP, GOCE, GRACE, SWARM‐A/B satellites). We show that by using the same inputs, the ML models we designed are capable of consistently improving the predictions with respect to state‐of‐the‐art empirical models by reducing the mean absolute percentage error (MAPE) in the thermospheric density estimation from the range of 40%–60% to approximately 20%. As a result of this work, we introduce Karman: an open‐source Python software package developed during this study. Karman provides functionalities to ingest and preprocess thermospheric density, solar irradiance, and geomagnetic input data for ML readiness. Additionally, it facilitates developing and training ML models on the aforementioned data and benchmarking their performance at different altitudes, geographic locations, times, and solar activity conditions. Through this contribution, we offer the scientific community a comprehensive tool for comparing and enhancing thermospheric density models using ML techniques. |
| format | Article |
| id | doaj-art-6480207316ca48f18856a827358f19cf |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2024-02-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-6480207316ca48f18856a827358f19cf2025-01-14T16:30:41ZengWileySpace Weather1542-73902024-02-01222n/an/a10.1029/2023SW003652Improving Thermospheric Density Predictions in Low‐Earth Orbit With Machine LearningGiacomo Acciarini0Edward Brown1Tom Berger2Madhulika Guhathakurta3James Parr4Christopher Bridges5Atılım Güneş Baydin6Trillium Technologies Inc. London UKTrillium Technologies Inc. London UKSpace Weather Center CU Boulder Boulder CO USANASA Headquarters Washington DC DC USATrillium Technologies Inc. London UKTrillium Technologies Inc. London UKTrillium Technologies Inc. London UKAbstract Thermospheric density is one of the main sources of uncertainty in the estimation of satellites' position and velocity in low‐Earth orbit. This has negative consequences in several space domains, including space traffic management, collision avoidance, re‐entry predictions, orbital lifetime analysis, and space object cataloging. In this paper, we investigate the prediction accuracy of empirical density models (e.g., NRLMSISE‐00 and JB‐08) against black‐box machine learning (ML) models trained on precise orbit determination‐derived thermospheric density data (from CHAMP, GOCE, GRACE, SWARM‐A/B satellites). We show that by using the same inputs, the ML models we designed are capable of consistently improving the predictions with respect to state‐of‐the‐art empirical models by reducing the mean absolute percentage error (MAPE) in the thermospheric density estimation from the range of 40%–60% to approximately 20%. As a result of this work, we introduce Karman: an open‐source Python software package developed during this study. Karman provides functionalities to ingest and preprocess thermospheric density, solar irradiance, and geomagnetic input data for ML readiness. Additionally, it facilitates developing and training ML models on the aforementioned data and benchmarking their performance at different altitudes, geographic locations, times, and solar activity conditions. Through this contribution, we offer the scientific community a comprehensive tool for comparing and enhancing thermospheric density models using ML techniques.https://doi.org/10.1029/2023SW003652thermospheric densitysatellite dragmachine learningspace weatherspace traffic managementspace situational awareness |
| spellingShingle | Giacomo Acciarini Edward Brown Tom Berger Madhulika Guhathakurta James Parr Christopher Bridges Atılım Güneş Baydin Improving Thermospheric Density Predictions in Low‐Earth Orbit With Machine Learning Space Weather thermospheric density satellite drag machine learning space weather space traffic management space situational awareness |
| title | Improving Thermospheric Density Predictions in Low‐Earth Orbit With Machine Learning |
| title_full | Improving Thermospheric Density Predictions in Low‐Earth Orbit With Machine Learning |
| title_fullStr | Improving Thermospheric Density Predictions in Low‐Earth Orbit With Machine Learning |
| title_full_unstemmed | Improving Thermospheric Density Predictions in Low‐Earth Orbit With Machine Learning |
| title_short | Improving Thermospheric Density Predictions in Low‐Earth Orbit With Machine Learning |
| title_sort | improving thermospheric density predictions in low earth orbit with machine learning |
| topic | thermospheric density satellite drag machine learning space weather space traffic management space situational awareness |
| url | https://doi.org/10.1029/2023SW003652 |
| work_keys_str_mv | AT giacomoacciarini improvingthermosphericdensitypredictionsinlowearthorbitwithmachinelearning AT edwardbrown improvingthermosphericdensitypredictionsinlowearthorbitwithmachinelearning AT tomberger improvingthermosphericdensitypredictionsinlowearthorbitwithmachinelearning AT madhulikaguhathakurta improvingthermosphericdensitypredictionsinlowearthorbitwithmachinelearning AT jamesparr improvingthermosphericdensitypredictionsinlowearthorbitwithmachinelearning AT christopherbridges improvingthermosphericdensitypredictionsinlowearthorbitwithmachinelearning AT atılımgunesbaydin improvingthermosphericdensitypredictionsinlowearthorbitwithmachinelearning |