Open Access iconOpen Access

ARTICLE

BDS-3 Satellite Orbit Prediction Method Based on Ensemble Learning and Neural Networks

Ruibo Wei1,2, Yao Kong3, Mengzhao Li1,2, Feng Liu1,2,*, Fang Cheng4,*

1 School of Computer Science, Xi’an Polytechnic University, Xi’an, 710600, China
2 Shaanxi Key Laboratory of Clothing Intelligence, Xi’an, 710600, China
3 School of Electronics and Information, Xi’an Polytechnic University, Xi’an, 710600, China
4 National Time Service Center, Chinese Academy of Sciences, Xi’an, 710600, China

* Corresponding Authors: Feng Liu. Email: email; Fang Cheng. Email: email

Computers, Materials & Continua 2025, 84(1), 1507-1528. https://doi.org/10.32604/cmc.2025.063722

Abstract

To address uncertainties in satellite orbit error prediction, this study proposes a novel ensemble learning-based orbit prediction method specifically designed for the BeiDou navigation satellite system (BDS). Building on ephemeris data and perturbation corrections, two new models are proposed: attention-enhanced BPNN (AEBP) and Transformer-ResNet-BiLSTM (TR-BiLSTM). These models effectively capture both local and global dependencies in satellite orbit data. To further enhance prediction accuracy and stability, the outputs of these two models were integrated using the gradient boosting decision tree (GBDT) ensemble learning method, which was optimized through a grid search. The main contribution of this approach is the synergistic combination of deep learning models and GBDT, which significantly improves both the accuracy and robustness of satellite orbit predictions. This model was validated using broadcast ephemeris data from the BDS-3 MEO and inclined geosynchronous orbit (IGSO) satellites. The results show that the proposed method achieves an error correction rate of 65.4%. This ensemble learning-based approach offers a highly effective solution for high-precision and stable satellite orbit predictions.

Keywords

BDS satellite orbit; ensemble learning; neural networks; orbit error

Cite This Article

APA Style
Wei, R., Kong, Y., Li, M., Liu, F., Cheng, F. (2025). BDS-3 Satellite Orbit Prediction Method Based on Ensemble Learning and Neural Networks. Computers, Materials & Continua, 84(1), 1507–1528. https://doi.org/10.32604/cmc.2025.063722
Vancouver Style
Wei R, Kong Y, Li M, Liu F, Cheng F. BDS-3 Satellite Orbit Prediction Method Based on Ensemble Learning and Neural Networks. Comput Mater Contin. 2025;84(1):1507–1528. https://doi.org/10.32604/cmc.2025.063722
IEEE Style
R. Wei, Y. Kong, M. Li, F. Liu, and F. Cheng, “BDS-3 Satellite Orbit Prediction Method Based on Ensemble Learning and Neural Networks,” Comput. Mater. Contin., vol. 84, no. 1, pp. 1507–1528, 2025. https://doi.org/10.32604/cmc.2025.063722



cc Copyright © 2025 The Author(s). Published by Tech Science Press.
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 563

    View

  • 240

    Download

  • 0

    Like

Share Link