EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Neural ocean forecasting from sparse satellite-derived observations: A case study for SSH dynamics and altimetry data

Daria Botvynko, Pierre Haslée, Lucile Gaultier, Julien Le Sommer, Clément de Boyer Montégut, Anass el Aouni, Betrand Chapron, Ronan Fablet

Environmental Data Science · 2026 · 5

DOI: 10.1017/eds.2026.10063 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Environmental Data Science, online erschienen am 05.11.2026. Verfasst von Daria Botvynko und 7 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present an end-to-end deep learning framework for short-term forecasting of global sea surface dynamics based on sparse satellite altimetry data. Building on two state-of-the-art architectures: U-Net and 4DVarNet, originally developed for image segmentation and spatiotemporal interpolation, respectively, we adapt the models to forecast the sea level anomaly (SLA) and sea surface currents over a seven-day horizon using sequences of sparse nadir altimeters observations. The model is trained on data from the GLORYS12 operational ocean reanalysis, with synthetic nadir sampling patterns applied to simulate realistic observational coverage. The forecasting task is formulated as a sequence-to-sequence mapping, with the input comprising partial SLA snapshots and the target being the corresponding future full-field SLA maps. We evaluate model performance using (i) normalized root mean squared error (nRMSE), (ii) averaged effective resolution, (iii) percentage of correctly predicted velocities, magnitudes and angles, and benchmark results against the operational Mercator Ocean forecast product. Results show that end-to-end neural forecasts outperform the baseline across all lead times, with particularly notable improvements in high variability regions. Our framework is developed within the OceanBench benchmarking initiative, promoting reproducibility and standardized evaluation in ocean machine learning. These results demonstrate the feasibility and potential of end-to-end neural forecasting models for operational oceanography, even in data-sparse conditions.

Zitieren

APA

Botvynko, D., Haslée, P., Gaultier, L., Sommer, J. L., Montégut, C. D. B., Aouni, A. E., Chapron, B., & Fablet, R. (2026). Neural ocean forecasting from sparse satellite-derived observations: A case study for SSH dynamics and altimetry data. Environmental Data Science, 5. https://doi.org/10.1017/eds.2026.10063

Vancouver

Botvynko D, Haslée P, Gaultier L, Sommer JL, Montégut CDB, Aouni AE, et al. Neural ocean forecasting from sparse satellite-derived observations: A case study for SSH dynamics and altimetry data. Environmental Data Science. 2026;5. doi:10.1017/eds.2026.10063

BibTeX
@article{Botvynko2026,
  author = {Botvynko, Daria and Haslée, Pierre and Gaultier, Lucile and Sommer, Julien Le and Montégut, Clément de Boyer and Aouni, Anass el and Chapron, Betrand and Fablet, Ronan},
  title = {Neural ocean forecasting from sparse satellite-derived observations: A case study for SSH dynamics and altimetry data},
  journal = {Environmental Data Science},
  year = {2026},
  volume = {5},
  doi = {10.1017/eds.2026.10063}
}
Kostenlos starten →