{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T04:30:02Z","timestamp":1772253002642,"version":"3.50.1"},"reference-count":60,"publisher":"MDPI AG","issue":"23","license":[{"start":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T00:00:00Z","timestamp":1701302400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>The International GNSS Service analysis centers provide orbit products of GPS satellites with weekly, daily, and sub-daily latency. The most frequent ultra-rapid products, which include 24 h of orbits derived from observations and 24 h of orbit predictions, are vital for real-time applications. However, the predicted part of the ultra-rapid orbits is less accurate than the estimated part and has deviations of several decimeters with respect to the final products. In this study, we investigate the potential of applying machine-learning (ML) and deep-learning (DL) algorithms to further enhance physics-based orbit predictions. We employed multiple ML\/DL algorithms and comprehensively compared the performances of different models. Since the prediction errors of the physics-based propagators accumulate with time and have sequential characteristics, specific sequential modeling algorithms, such as Long Short-Term Memory (LSTM), show superiority. Our approach shows promising results with average improvements of 47% in 3D RMS within the 24-hour prediction interval of the ultra-rapid products. In the end, we applied the orbit predictions improved by LSTM to kinematic precise point positioning and demonstrated the benefits of LSTM-improved orbit predictions for positioning applications. The accuracy of the station coordinates estimated based on these products is improved by 16% on average compared to those using ultra-rapid orbit predictions.<\/jats:p>","DOI":"10.3390\/rs15235585","type":"journal-article","created":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T04:12:56Z","timestamp":1701403976000},"page":"5585","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Modeling the Differences between Ultra-Rapid and Final Orbit Products of GPS Satellites Using Machine-Learning Approaches"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7599-0577","authenticated-orcid":false,"given":"Junyang","family":"Gou","sequence":"first","affiliation":[{"name":"Institute of Geodesy and Photogrammetry, ETH Zurich, 8093 Zurich, Switzerland"}]},{"given":"Christine","family":"R\u00f6sch","sequence":"additional","affiliation":[{"name":"Institute of Geodesy and Photogrammetry, ETH Zurich, 8093 Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6415-1498","authenticated-orcid":false,"given":"Endrit","family":"Shehaj","sequence":"additional","affiliation":[{"name":"Institute of Geodesy and Photogrammetry, ETH Zurich, 8093 Zurich, Switzerland"}]},{"given":"Kangkang","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Geodesy and Photogrammetry, ETH Zurich, 8093 Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5705-7014","authenticated-orcid":false,"given":"Mostafa","family":"Kiani Shahvandi","sequence":"additional","affiliation":[{"name":"Institute of Geodesy and Photogrammetry, ETH Zurich, 8093 Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7010-2147","authenticated-orcid":false,"given":"Benedikt","family":"Soja","sequence":"additional","affiliation":[{"name":"Institute of Geodesy and Photogrammetry, ETH Zurich, 8093 Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7993-8573","authenticated-orcid":false,"given":"Markus","family":"Rothacher","sequence":"additional","affiliation":[{"name":"Institute of Geodesy and Photogrammetry, ETH Zurich, 8093 Zurich, Switzerland"}]}],"member":"1968","published-online":{"date-parts":[[2023,11,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Shi, J., Wang, G., Han, X., and Guo, J. (2017). Impacts of satellite orbit and clock on real-time GPS point and relative positioning. Sensors, 17.","DOI":"10.3390\/s17061363"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"845","DOI":"10.1016\/j.asr.2018.05.025","article-title":"Modeling of the GPS satellite clock error and its performance evaluation in precise point positioning","volume":"62","author":"Li","year":"2018","journal-title":"Adv. Space Res."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1007\/s10291-022-01327-y","article-title":"Improved method for the GPS high-precision real-time satellite clock error service","volume":"26","author":"Li","year":"2022","journal-title":"GPS Solut."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1007\/s10291-023-01558-7","article-title":"Estimating GNSS satellite clock error to provide a new final product and real-time services","volume":"28","author":"Li","year":"2024","journal-title":"GPS Solut."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1002\/navi.416","article-title":"Precise real-time navigation of LEO satellites using GNSS broadcast ephemerides","volume":"68","author":"Hauschild","year":"2021","journal-title":"Navig. J. Inst. Navig."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1007\/s10291-021-01198-9","article-title":"Performance assessment of GNSS-based real-time navigation for the Sentinel-6 spacecraft","volume":"26","author":"Montenbruck","year":"2022","journal-title":"GPS Solut."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"M\u00fcller, L., Chen, K., M\u00f6ller, G., Rothacher, M., Soja, B., and Lopez, L. (2023). Real-time navigation solutions of low-cost off-the-shelf GNSS receivers on board the Astrocast constellation satellites. Adv. Space Res.","DOI":"10.1016\/j.asr.2023.10.001"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"eaau0323","DOI":"10.1126\/science.aau0323","article-title":"Machine learning for data-driven discovery in solid Earth geoscience","volume":"363","author":"Bergen","year":"2019","journal-title":"Science"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1038\/s41586-019-0912-1","article-title":"Deep learning and process understanding for data-driven Earth system science","volume":"566","author":"Reichstein","year":"2019","journal-title":"Nature"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"e2021RG000742","DOI":"10.1029\/2021RG000742","article-title":"Deep learning for geophysics: Current and future trends","volume":"59","author":"Yu","year":"2021","journal-title":"Rev. Geophys."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1515\/jag-2020-0043","article-title":"Machine learning and geodesy: A survey","volume":"15","author":"Butt","year":"2021","journal-title":"J. Appl. Geod."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Pihlajasalo, J., Lepp\u00e4koski, H., Ali-L\u00f6ytty, S., and Pich\u00e9, R. (2018, January 14\u201317). Improvement of GPS and BeiDou extended orbit predictions with CNNs. Proceedings of the 2018 European Navigation Conference (ENC), Gothenburg, Sweden.","DOI":"10.1109\/EURONAV.2018.8433244"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Chen, H., Niu, F., Su, X., Geng, T., Liu, Z., and Li, Q. (2021). Initial results of modeling and improvement of BDS-2\/GPS broadcast ephemeris satellite orbit based on BP and PSO-BP neural networks. Remote. Sens., 13.","DOI":"10.3390\/rs13234801"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"376","DOI":"10.1016\/j.geog.2020.06.002","article-title":"Simultaneous approximation of a function and its derivatives by Sobolev polynomials: Applications in satellite geodesy and precise orbit determination for LEO CubeSats","volume":"11","author":"Kiani","year":"2020","journal-title":"Geod. Geodyn."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2628","DOI":"10.1016\/j.asr.2018.03.001","article-title":"Improving orbit prediction accuracy through supervised machine learning","volume":"61","author":"Peng","year":"2018","journal-title":"Adv. Space Res."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1007\/s40295-019-00158-3","article-title":"Machine learning approach to improve satellite orbit prediction accuracy using publicly available data","volume":"67","author":"Peng","year":"2020","journal-title":"J. Astronaut. Sci."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Mortlock, T., and Kassas, Z.M. (2021, January 6\u201313). Assessing machine learning for LEO satellite orbit determination in simultaneous tracking and navigation. Proceedings of the 2021 IEEE Aerospace Conference (50100), Big Sky, MT, USA.","DOI":"10.1109\/AERO50100.2021.9438144"},{"key":"ref_18","unstructured":"Johnston, G., Riddell, A., and Hausler, G. (2017). Springer Handbook of Global Navigation Satellite Systems, Springer International Publishing."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10291-019-0834-2","article-title":"Prediction versus real-time orbit determination for GNSS satellites","volume":"23","author":"Duan","year":"2019","journal-title":"GPS Solut."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2855","DOI":"10.1016\/j.asr.2017.09.022","article-title":"Impacts of Earth rotation parameters on GNSS ultra-rapid orbit prediction: Derivation and real-time correction","volume":"60","author":"Wang","year":"2017","journal-title":"Adv. Space Res."},{"key":"ref_21","unstructured":"(2012, November 24). IGS Products. Available online: https:\/\/igs.org\/products\/#orbits_clocks."},{"key":"ref_22","unstructured":"M\u00e4nnel, B., Brandt, A., Nischan, T., Brack, A., Sakic, P., and Bradke, M. (2020). GFZ Ultra-Rapid Product Series for the International GNSS Service (IGS), GFZ Data Services."},{"key":"ref_23","unstructured":"M\u00e4nnel, B., Brandt, A., Nischan, T., Brack, A., Sakic, P., and Bradke, M. (2020). GFZ Final Product Series for the International GNSS Service (IGS), GFZ Data Services."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1007\/s00190-018-1149-8","article-title":"Combined orbits and clocks from IGS second reprocessing","volume":"93","author":"Griffiths","year":"2019","journal-title":"J. Geod."},{"key":"ref_25","unstructured":"Rothacher, M. (1992). Orbits of Satellite Systems in Space Geodesy, lnstitut ftlr Geodlsie mid Photogrammetrie."},{"key":"ref_26","unstructured":"Petit, G., and Luzum, B. (2010). IERS Conventions (2010), Verlag des Bundesamts f\u00fcr Kartographie und Geod\u00e4sie."},{"key":"ref_27","unstructured":"Montenbruck, O., and Gill, E. (2012). Satellite Orbits: Models, Methods and Applications, Springer Science & Business Media."},{"key":"ref_28","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press."},{"key":"ref_29","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Crocetti, L., Schartner, M., and Soja, B. (2021). Discontinuity Detection in GNSS Station Coordinate Time Series Using Machine Learning. Remote. Sens., 13.","DOI":"10.5194\/egusphere-egu21-1975"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"e2019EA000959","DOI":"10.1029\/2019EA000959","article-title":"Can terrestrial water storage dynamics be estimated from climate anomalies?","volume":"7","author":"Jing","year":"2020","journal-title":"Earth Space Sci."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Kiani Shahvandi, M., Gou, J., Schartner, M., and Soja, B. (2022, January 17\u201322). Data Driven Approaches for the Prediction of Earth\u2019s Effective Angular Momentum Functions. Proceedings of the IGARSS 2022\u20142022 IEEE International Geoscience and Remote Sensing Symposium, Kuala Lumpur, Malaysia.","DOI":"10.1109\/IGARSS46834.2022.9883545"},{"key":"ref_33","unstructured":"Breiman, L. (2011). Classification and Regression Trees, Routledge. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_35","unstructured":"Marchuk, G.I. (1974, January 1\u20137). On bayesian methods for seeking the extremum. Proceedings of the Optimization Techniques IFIP Technical Conference, Novosibirsk, Russia."},{"key":"ref_36","unstructured":"Pereira, F., Burges, C., Bottou, L., and Weinberger, K. (2012, January 3\u20138). Practical Bayesian Optimization of Machine Learning Algorithms. Proceedings of the Advances in Neural Information Processing Systems, Lake Tahoe, NV, USA."},{"key":"ref_37","unstructured":"Haykin, S. (1994). Neural Networks: A Comprehensive Foundation, Prentice Hall PTR."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1007\/s00190-001-0242-5","article-title":"Prediction of Earth orientation parameters by artificial neural networks","volume":"76","author":"Schuh","year":"2002","journal-title":"J. Geod."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"e2019WR026551","DOI":"10.1029\/2019WR026551","article-title":"Comparison of data-driven techniques to reconstruct (1992\u20132002) and predict (2017\u20132018) GRACE-like gridded total water storage changes using climate inputs","volume":"56","author":"Li","year":"2020","journal-title":"Water Resour. Res."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"key":"ref_41","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., and Devin, M. (2021, March 01). TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. Available online: tensorflow.org."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1109\/72.279181","article-title":"Learning long-term dependencies with gradient descent is difficult","volume":"5","author":"Bengio","year":"1994","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_44","unstructured":"Pascanu, R., Mikolov, T., and Bengio, Y. (2013, January 16\u201321). On the difficulty of training recurrent neural networks. Proceedings of the International Conference on Machine Learning, PMLR, Atlanta, GA, USA."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-Term Memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1007\/s00190-023-01745-x","article-title":"Ultra-short-term prediction of LOD using LSTM neural networks","volume":"97","author":"Gou","year":"2023","journal-title":"J. Geod."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Kiani Shahvandi, M., and Soja, B. (2021, January 4\u20138). Small geodetic datasets and deep networks: Attention-based residual LSTM Autoencoder stacking for geodetic time series. Proceedings of the 7th International Conference on Machine Learning, Optimization, and Data Science, Grasmere, UK.","DOI":"10.1007\/978-3-030-95467-3_22"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1016\/j.asr.2022.05.042","article-title":"Inclusion of data uncertainty in machine learning and its application in geodetic data science, with case studies for the prediction of Earth orientation parameters and GNSS station coordinate time series","volume":"70","author":"Soja","year":"2022","journal-title":"Adv. Space Res."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Tang, J., Li, Y., Ding, M., Liu, H., Yang, D., and Wu, X. (2022). An ionospheric TEC forecasting model based on a CNN-LSTM-attention mechanism neural network. Remote. Sens., 14.","DOI":"10.3390\/rs14102433"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., and Bengio, Y. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv.","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref_51","unstructured":"Sutskever, I., Vinyals, O., and Le, Q.V. Sequence to sequence learning with neural networks. In Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada, 8\u201313 October 2014."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Donahue, J., Anne Hendricks, L., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., and Darrell, T. (2015, January 7\u201312). Long-term recurrent convolutional networks for visual recognition and description. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref_53","unstructured":"Dach, R., Lutz, S., Walser, P., and Fridez, P. Bernese GNSS Software, version 5.2."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1007\/s00190-007-0135-3","article-title":"Short note: A global model of pressure and temperature for geodetic applications","volume":"81","author":"Heinkelmann","year":"2007","journal-title":"J. Geod."},{"key":"ref_55","unstructured":"Dach, R., Schaer, S., Arnold, D., Kalarus, M.S., Prange, L., Stebler, P., Villiger, A., and J\u00e4ggi, A. (2020). CODE Final Product Series for the IGS, Astronomical Institute, University of Bern."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"1251","DOI":"10.1007\/s10291-017-0610-0","article-title":"Robust combination of IGS analysis center GLONASS clocks","volume":"21","author":"Chen","year":"2017","journal-title":"GPS Solut."},{"key":"ref_57","unstructured":"IGS (2022, May 16). International GNSS Service, GNSS Final Cumulative Combined Set of Station Coordinates Product, Greenbelt, MD, USA: NASA Crustal Dynamics Data Information System (CDDIS), Available online: https:\/\/cddis.nasa.gov\/Data_and_Derived_Products\/GNSS\/gnss_igssnx.html."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"1421","DOI":"10.1016\/j.asr.2010.01.018","article-title":"The crustal dynamics data information system: A resource to support scientific analysis using space geodesy","volume":"45","author":"Noll","year":"2010","journal-title":"Adv. Space Res."},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1007\/BF03655285","article-title":"Impact of GPS satellite sky distribution","volume":"16","author":"Santerre","year":"1991","journal-title":"Manuscripta Geod."},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1007\/s10291-014-0432-2","article-title":"CODE\u2019s new ultra-rapid orbit and ERP products for the IGS","volume":"20","author":"Lutz","year":"2016","journal-title":"GPS Solut."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/23\/5585\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:35:16Z","timestamp":1760132116000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/23\/5585"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,30]]},"references-count":60,"journal-issue":{"issue":"23","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["rs15235585"],"URL":"https:\/\/doi.org\/10.3390\/rs15235585","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-3015887\/v1","asserted-by":"object"}]},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,30]]}}}