Publications related to the GRACE Missions (no abstracts)

• Sorted by Date • Sorted by Last Name of First Author •

Machine learning algorithms for transplanting accelerometer observations in future satellite gravimetry missions

Romeshkani, Mohsen, Müller, Jürgen, Ebadi, Sahar, Kupriyanov, Alexey, Knabe, Annike, Fletling, Nina, and Schilling, Manuel, 2026. Machine learning algorithms for transplanting accelerometer observations in future satellite gravimetry missions. Journal of Geodesy, 100(10):83, doi:10.1007/s00190-026-02108-y.

Downloads

• from the NASA Astrophysics Data System  • by the DOI System  •

@ARTICLE{2026JGeod.100...83R,
       author = {{Romeshkani}, Mohsen and {M{\"u}ller}, J{\"u}rgen and {Ebadi}, Sahar and {Kupriyanov}, Alexey and {Knabe}, Annike and {Fletling}, Nina and {Schilling}, Manuel},
        title = "{Machine learning algorithms for transplanting accelerometer observations in future satellite gravimetry missions}",
      journal = {Journal of Geodesy},
     keywords = {Satellite gravimetry, Quantum sensors, Machine learning, Instrument noise modeling, Hybrid data transplantation, Future gravity missions, Information and Computing Sciences, Artificial Intelligence and Image Processing, Engineering, Geomatic Engineering},
         year = 2026,
        month = sep,
       volume = {100},
       number = {10},
          eid = {83},
        pages = {83},
     abstract = "{Accurate and continuous monitoring of Earth's gravity field is essential
        for tracking mass redistribution processes linked to climate
        variability, hydrological cycles, and geodynamic phenomena.
        While the GRACE and GRACE Follow-On (GRACE-FO) missions have set
        the benchmark for satellite gravimetry using low--low satellite-
        to-satellite tracking (LL-SST), the precision of gravity field
        recovery still strongly depends on the quality of accelerometer
        (ACC) performance. Traditional electrostatic accelerometers (EA)
        face limitations that can hinder mission outcomes, prompting
        exploration of advanced sensor technologies and data recovery
        techniques. This study presents a systematic evaluation of
        accelerometer data transplantation (i.e., the reconstruction and
        transfer of non-gravitational acceleration measurements between
        satellites) using novel accelerometer configurations, including
        Cold Atom Interferometry (CAI) accelerometers and hybrid EA-CAI
        setups, and applying both analytical and machine learning-based
        methods. Using comprehensive closed-loop LL-SST simulations, we
        compare four scenarios ranging from the conventional EA-only
        setup to ideal dual hybrid configurations, with a particular
        focus on the performance of transplant-based approaches using
        different neural network approaches. Our results show that the
        dual hybrid configuration provides the most accurate gravity
        field retrieval. However, the transplant-based hybrid setup,
        particularly when supported by machine learning (ML), emerges as
        a robust and cost-effective alternative, achieving comparable
        performance while significantly reducing the need for high-
        precision accelerometers across the constellation, thereby
        lowering mission costs and system complexity. These findings
        highlight the promise of combining quantum sensor technology and
        data-driven transplantation for future satellite gravimetry
        missions, paving the way for improved global monitoring of
        Earth's dynamic gravity field.}",
          doi = {10.1007/s00190-026-02108-y},
       adsurl = {https://ui.adsabs.harvard.edu/abs/2026JGeod.100...83R},
      adsnote = {Provided by the SAO/NASA Astrophysics Data System}
}

Generated by bib2html_grace.pl (written by Patrick Riley modified for this page by Volker Klemann) on Thu Oct 08, 2026 16:44:00

---

Thu Oct 08, F. Flechtner