@COMMENT This file was generated by bib2html_grace.pl <https://sourceforge.net/projects/bib2html/> version 0.94
@COMMENT written by Patrick Riley <https://sourceforge.net/users/patstg/>
@COMMENT This file was prepared using the NASA Astrophysics Data System (ADS)
@COMMENT https://ui.adsabs.harvard.edu/
@ARTICLE{2026SatNa...7...28W,
       author = {{Wu}, Tianhao and {Li}, Bofeng and {Ge}, Haibo},
        title = "{Neural network-based clock bias prediction for low earth orbit satellites with a reconstruction fine-tuning mechanism}",
      journal = {Satellite Navigation},
     keywords = {Low Earth Orbit (LEO), Satellite Clock Bias (SCB) prediction, Neural network, Informer, Information and Computing Sciences, Artificial Intelligence and Image Processing},
         year = 2026,
        month = sep,
       volume = {7},
       number = {1},
          eid = {28},
        pages = {28},
     abstract = "{Accurate prediction of Satellite Clock Bias (SCB) for Low Earth Orbit
        (LEO) satellites is critical for real-time LEO-enhanced Global
        Navigation Satellite System (LeGNSS) applications. However, the
        inherent instability of LEO onboard oscillators results in
        complex SCB variations that are difficult for conventional
        prediction models to capture. While deep learning methods offer
        a promising alternative, their effectiveness can be limited by
        two key issues: the pronounced high-order trends in LEO SCB,
        which are not completely removed by the conventional single
        differencing; and the potential biased error accumulation that
        occurs when reconstructing predictions from the differenced
        domain. To address these challenges, we propose a novel neural
        network-based framework featuring two key innovations: (1)
        advanced differencing strategies---single-differencing with
        segment-wise standardization and direct double-differencing---to
        suppress high-order trends without performing external fitting,
        thereby preserving prediction independence; and (2) a
        reconstruction fine-tuning mechanism to explicitly mitigate
        directional error accumulation. Validated with Gravity Recovery
        and Climate Experiment Follow-On (GRACE-FO) data, the fine-
        tuning mechanism reduces overall prediction errors by 6\%--16\%
        with reconstruction biases mitigated. Compared to the
        conventional spectrum analysis model, the proposed framework
        improves overall prediction accuracy by approximately 90\% and
        94\% for the 60 min and the 10 min prediction horizons,
        respectively. Specifically, for the prediction length of 60 min,
        the prediction errors for the GRACE-FO C and D satellites
        decrease to 0.84 ns and 1.42 ns, respectively; for the
        prediction length of 10 min, they decrease to 0.10 ns and 0.15
        ns, respectively. These results indicate the framework's
        potential for high-precision real-time applications from the
        inference-efficiency perspective.}",
          doi = {10.1186/s43020-026-00215-x},
       adsurl = {https://ui.adsabs.harvard.edu/abs/2026SatNa...7...28W},
      adsnote = {Provided by the SAO/NASA Astrophysics Data System}
}