The Short‐Time Prediction of Thermospheric Mass Density Based on Ensemble‐Transfer Learning

• Published in: Space Weather Vol. 21; no. 10
• Main Authors: Wang, Peian, Chen, Zhou, Deng, Xiaohua, Wang, Jing‐Song, Tang, Rongxing, Li, Haimeng, Hong, Sheng, Wu, Zhiping
• Format: Journal Article
• Language: English
• Published: Washington John Wiley & Sons, Inc 01.10.2023; Wiley
• Subjects: Accuracy; Aerospace industry; Algorithms; Atmospheric drag; Atmospheric models; Density; Earth orbits; ensemble learning; Low earth orbits; Machine learning; Modelling; NRLMSISE‐00; Satellite data; Satellite orbits; Satellites; short‐time prediction; Space research; thermospheric mass density; transfer learning
• ISSN: 1542-7390; 1539-4964; 1542-7390
• DOI: 10.1029/2023SW003576

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. Low‐Earth orbit (LEO) satellites play an important role in many aspects, such as navigation, aerospace, military industry, and so on. The LEO satellites suffer atmospheric drag caused by thermospheric mass density. Therefore, we present three different machine‐learning algorithms to achieve a robust short‐time prediction for thermospheric mass density. All models can provide effective results from testing with three satellite data, and the ensemble model always outperforms others. Then, when the obtained density data from the newly launched satellites are very limited, the pre‐trained ensemble model is also useful for the new satellite orbit by transfer learning. We offer a good insight into the short‐time prediction of thermospheric mass density and assistance for aerospace digitization and intellectualization. Based on three different machine‐learning algorithms, we present a robust short‐time prediction for thermospheric mass density We evaluate the model performances using data from CHAMP, GOCE, and SWARM‐C with NRLMSISE‐00 as the reference The LightGBM ensemble model of Bidirectional Long Short‐Term Memory and Transformer outperforms others and can provide reliable transfer predictions for new satellites