Machine Learning Based Modeling of Thermospheric Mass Density
Abstract In this study, we propose a machine learning based approach to construct an empirical model of thermospheric mass densities, based on the MultiLayer Perceptron and bi‐directional Long Short‐Term Memory for ensemble learning model (MBiLE). The MBiLE model was trained by using only the thermo...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-05-01
|
| Series: | Space Weather |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2023SW003844 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536417406124032 |
|---|---|
| author | Qian Pan Chao Xiong Hermann Lühr Artem Smirnov Yuyang Huang Chunyu Xu Xu Yang Yunliang Zhou Yang Hu |
| author_facet | Qian Pan Chao Xiong Hermann Lühr Artem Smirnov Yuyang Huang Chunyu Xu Xu Yang Yunliang Zhou Yang Hu |
| author_sort | Qian Pan |
| collection | DOAJ |
| description | Abstract In this study, we propose a machine learning based approach to construct an empirical model of thermospheric mass densities, based on the MultiLayer Perceptron and bi‐directional Long Short‐Term Memory for ensemble learning model (MBiLE). The MBiLE model was trained by using only the thermospheric mass density from Swarm C satellite at ∼450 km altitude. To assess the performance of the MBiLE model, the model predictions were compared with observations from several satellites, namely, the Swarm C, the Challenging Minisatellite Payload (CHAMP) and the Gravity Field and Steady‐State Ocean Circulation Explorer (GOCE) satellites. The determination coefficients (R2) for the three satellites are 0.98, 0.99, and 0.98, respectively. The MBiLE model predicts the thermospheric mass density well not only at Swarm C altitude but also at lower altitudes. Earlier empirical models based on multivariate least‐square‐fitting approach failed to achieve this good altitude generalization (e.g., Liu et al., 2013, https://doi.org/10.1002/jgra.50144; Xiong et al., 2018a, https://doi.org/10.5194/angeo‐2018‐25). Further tests have been made by checking the MBiLE model prediction deviations in relation to magnetic local time, day of year, solar flux level, and magnetic activities. No obvious dependences are found for these parameters. Comparing with the NRLMSIS‐2.0 model, the MBiLE model improves prediction accuracy by 91%, 66%, and 56% at the three satellites altitudes. The results indicate that the MBiLE model has the ability to predict well the thermospheric mass density over a wide altitude range, for example, from 224 to 528 km, offering potential for atmospheric research applications. |
| format | Article |
| id | doaj-art-8be29dcfa9af46ac81b10659a0836425 |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2024-05-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-8be29dcfa9af46ac81b10659a08364252025-01-14T16:27:31ZengWileySpace Weather1542-73902024-05-01225n/an/a10.1029/2023SW003844Machine Learning Based Modeling of Thermospheric Mass DensityQian Pan0Chao Xiong1Hermann Lühr2Artem Smirnov3Yuyang Huang4Chunyu Xu5Xu Yang6Yunliang Zhou7Yang Hu8Department of Space Physics, Electronic Information School, Hubei Luojia Laboratory Wuhan University Wuhan ChinaDepartment of Space Physics, Electronic Information School, Hubei Luojia Laboratory Wuhan University Wuhan ChinaHelmholtz Centre Potsdam, GFZ German Research Centre for Geosciences Potsdam GermanyHelmholtz Centre Potsdam, GFZ German Research Centre for Geosciences Potsdam GermanyDepartment of Space Physics, Electronic Information School, Hubei Luojia Laboratory Wuhan University Wuhan ChinaDepartment of Space Physics, Electronic Information School, Hubei Luojia Laboratory Wuhan University Wuhan ChinaCollege of Meteorology and Oceanography, National University of Defense Technology Changsha ChinaDepartment of Space Physics, Electronic Information School, Hubei Luojia Laboratory Wuhan University Wuhan ChinaDepartment of Space Physics, Electronic Information School, Hubei Luojia Laboratory Wuhan University Wuhan ChinaAbstract In this study, we propose a machine learning based approach to construct an empirical model of thermospheric mass densities, based on the MultiLayer Perceptron and bi‐directional Long Short‐Term Memory for ensemble learning model (MBiLE). The MBiLE model was trained by using only the thermospheric mass density from Swarm C satellite at ∼450 km altitude. To assess the performance of the MBiLE model, the model predictions were compared with observations from several satellites, namely, the Swarm C, the Challenging Minisatellite Payload (CHAMP) and the Gravity Field and Steady‐State Ocean Circulation Explorer (GOCE) satellites. The determination coefficients (R2) for the three satellites are 0.98, 0.99, and 0.98, respectively. The MBiLE model predicts the thermospheric mass density well not only at Swarm C altitude but also at lower altitudes. Earlier empirical models based on multivariate least‐square‐fitting approach failed to achieve this good altitude generalization (e.g., Liu et al., 2013, https://doi.org/10.1002/jgra.50144; Xiong et al., 2018a, https://doi.org/10.5194/angeo‐2018‐25). Further tests have been made by checking the MBiLE model prediction deviations in relation to magnetic local time, day of year, solar flux level, and magnetic activities. No obvious dependences are found for these parameters. Comparing with the NRLMSIS‐2.0 model, the MBiLE model improves prediction accuracy by 91%, 66%, and 56% at the three satellites altitudes. The results indicate that the MBiLE model has the ability to predict well the thermospheric mass density over a wide altitude range, for example, from 224 to 528 km, offering potential for atmospheric research applications.https://doi.org/10.1029/2023SW003844thermosphere mass densitymachine learningpredict abilitywide altitude range |
| spellingShingle | Qian Pan Chao Xiong Hermann Lühr Artem Smirnov Yuyang Huang Chunyu Xu Xu Yang Yunliang Zhou Yang Hu Machine Learning Based Modeling of Thermospheric Mass Density Space Weather thermosphere mass density machine learning predict ability wide altitude range |
| title | Machine Learning Based Modeling of Thermospheric Mass Density |
| title_full | Machine Learning Based Modeling of Thermospheric Mass Density |
| title_fullStr | Machine Learning Based Modeling of Thermospheric Mass Density |
| title_full_unstemmed | Machine Learning Based Modeling of Thermospheric Mass Density |
| title_short | Machine Learning Based Modeling of Thermospheric Mass Density |
| title_sort | machine learning based modeling of thermospheric mass density |
| topic | thermosphere mass density machine learning predict ability wide altitude range |
| url | https://doi.org/10.1029/2023SW003844 |
| work_keys_str_mv | AT qianpan machinelearningbasedmodelingofthermosphericmassdensity AT chaoxiong machinelearningbasedmodelingofthermosphericmassdensity AT hermannluhr machinelearningbasedmodelingofthermosphericmassdensity AT artemsmirnov machinelearningbasedmodelingofthermosphericmassdensity AT yuyanghuang machinelearningbasedmodelingofthermosphericmassdensity AT chunyuxu machinelearningbasedmodelingofthermosphericmassdensity AT xuyang machinelearningbasedmodelingofthermosphericmassdensity AT yunliangzhou machinelearningbasedmodelingofthermosphericmassdensity AT yanghu machinelearningbasedmodelingofthermosphericmassdensity |