EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hybrid Physics-Informed Residual Learning for Robust BDS-3 Satellite Clock Bias Prediction

Lingfeng Cheng iD, Keyu Li, Wenhui Guan, Zexian Li, Qin Liang iD, Chenglin Cai

Sensors · 31.05.2026 · 26 (11) · 3475

DOI: 10.3390/s26113475 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 31.05.2026. Verfasst von Lingfeng Cheng und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Mathematical and Computational Sciences, Xiangtan University, Xiangtan 411105, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science and Technology of the People's Republic of China, Education Department of Hunan Province, University of South China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Real-time precise point positioning (RT-PPP) has enabled a wide range of high-precision positioning and navigation applications, while its reliability strongly depends on the availability and continuity of precise satellite clock products. In the third-generation BeiDou Navigation Satellite System (BDS-3), interruptions or gaps in real-time precise clock products can significantly degrade the continuity and performance of precise positioning services. Therefore, accurate and robust satellite clock bias (SCB) prediction is essential for supporting reliable RT-PPP applications under product outage conditions. To address this problem, this study proposes a hybrid physics-informed and data-driven framework for BDS-3 SCB prediction. The proposed method sequentially integrates a physics-informed neural network (PINN) and a long short-term memory (LSTM) network. Specifically, the PINN is used to model and extrapolate the physically consistent trend component of SCB increments by embedding clock dynamical constraints through automatic differentiation, while the LSTM is employed to learn and predict the residual sequence containing short-term stochastic variations that cannot be fully captured by the physical model. The final SCB prediction is obtained by reconstructing the trend and residual components and recovering the original clock bias series. The proposed framework is evaluated using BDS-3 precise clock products and compared with conventional models, including quadratic polynomial (QP), autoregressive integrated moving average (ARIMA), convolutional neural network–long short-term memory (CNN-LSTM), and attention-enhanced long short-term memory (LSTM-Attention). Experimental results show that the proposed PINN-LSTM framework consistently achieves superior prediction accuracy and stability at both 12 h and 24 h forecasting horizons. Specifically, compared with QP, ARIMA, CNN-LSTM, and LSTM-Attention, the proposed method improves prediction accuracy by 18.4%, 52.8%, 32.3%, and 33.8%, respectively, for the 12 h forecasting task, and by 34.8%, 58.5%, 41.8%, and 43.8%, respectively, for the 24 h forecasting task. The results further demonstrate reduced long-horizon error accumulation, improved robustness across satellites equipped with different atomic clock types, and stronger generalization across observation days. These findings indicate that the proposed framework can provide effective support for maintaining the continuity and reliability of BDS-3 precise clock products and has strong potential for improving real-time precise positioning applications.

Schlagwörter

Stichwörter der Autor:innen

BDS-3LSTMPINNPPPsatellite clock bias

Autor:innen und Institutionen

  • School of Mathematical and Computational Sciences, Xiangtan University, Xiangtan 411105, China.
  • National Center for Applied Mathematics in Hunan, Xiangtan University, Xiangtan 411105, China.
  • School of Automation and Electronic Information, Xiangtan University, Xiangtan 411105, China.
  • Solux College of Architecture and Design, University of South China, Hengyang 421099, China.

ORCID-Profile: Lingfeng Cheng, Qin Liang

Förderung

  • Ministry of Science and Technology of the People's Republic of China
  • Education Department of Hunan Province
  • University of South China
  • Xiangtan University
  • National Key Research and Development Program of China
  • Scientific Research Fund of Hunan Provincial Education Department
  • Doctoral Research Start-up Fund of University of South China
  • Xiangtan University Innovation Foundation for Postgraduate

Zitieren

APA

Cheng, L., Li, K., Guan, W., Li, Z., Liang, Q., & Cai, C. (2026). Hybrid Physics-Informed Residual Learning for Robust BDS-3 Satellite Clock Bias Prediction. Sensors, 26(11), 3475. https://doi.org/10.3390/s26113475

Vancouver

Cheng L, Li K, Guan W, Li Z, Liang Q, Cai C. Hybrid Physics-Informed Residual Learning for Robust BDS-3 Satellite Clock Bias Prediction. Sensors. 2026;26(11):3475. doi:10.3390/s26113475

BibTeX
@article{Cheng2026,
  author = {Cheng, Lingfeng and Li, Keyu and Guan, Wenhui and Li, Zexian and Liang, Qin and Cai, Chenglin},
  title = {Hybrid Physics-Informed Residual Learning for Robust BDS-3 Satellite Clock Bias Prediction},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {11},
  pages = {3475},
  doi = {10.3390/s26113475}
}
Kostenlos starten →