Paper · 2025 · Open access

OceanBench: A Benchmark for Data-Driven Global Ocean Forecasting systems

Anass El Aouni, Quentin Gaudel, Regnier, Charly, Julien Le Sommer, Gennip, Simon, Van, Ronan Fablet, Marie Drévillon, Yann Drillet, Le Traon, Pierre-Yves

HAL · Published 30 November 2025

Read the free full textCite this paper

In brief

“OceanBench: A Benchmark for Data-Driven Global Ocean Forecasting systems” is a 2025 paper by Anass El Aouni and 8 co-authors, published in HAL. OpenAlex counts 0 citations as of 15 November 2026. It is open access under a CC BY licence: the full text is free to read at HAL.

Citations
0
Authors
9

Abstract

Data-driven approaches, particularly those based on deep learning, are rapidly advancing Earth system modeling. However, their application to ocean forecasting remains limited despite the ocean's pivotal role in climate regulation and marine ecosystems. To address this gap, we present OceanBench, a benchmark designed to evaluate and accelerate global short-range (1-10 days) data-driven ocean forecasting. OceanBench is constructed from a curated dataset comprising first-guess trajectories, nowcasts, and atmospheric forcings from operational physical ocean models, typically unavailable in public datasets due to assimilation cycles. Matched observational data are also included, enabling realistic evaluation in an operational-like forecasting framework. The benchmark defines three complementary evaluation tracks: (i) Model-to-Reanalysis, where models are compared against the reanalysis dataset commonly used for training; (ii) Model-to-Analysis, assessing generalization to a higher-resolution physical analysis; and (iii) Model-to-Observations, Intercomparison and Validation (IV-TT) CLASS-4 evaluation against independent observational data. The first two tracks are further supported by process-oriented diagnostics to assess the dynamical consistency and physical plausibility of forecasts. OceanBench includes key ocean variables: sea surface height, temperature, salinity, and currents, along with standardized metrics grounded in physical oceanography. Baseline comparisons with operational systems and state-of-the-art deep learning models are provided. All data, code, and evaluation protocols are openly available at https://github.com/mercator-ocean/oceanbench, establishing Ocean-Bench as a foundation for reproducible and rigorous research in data-driven ocean forecasting.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

El Aouni, A., Gaudel, Q., Charly, R., Le Sommer, J., Van, G. S., Fablet, R., Drévillon, M., Drillet, Y., & Pierre-Yves, L. T. (2025). OceanBench: A Benchmark for Data-Driven Global Ocean Forecasting systems. HAL. https://hal.science/hal-05412248

MLA 9

El Aouni, Anass, et al. “OceanBench: A Benchmark for Data-Driven Global Ocean Forecasting systems.” HAL, no. 1-14, 2025. https://hal.science/hal-05412248.

Chicago

El Aouni, Anass, Quentin Gaudel, Regnier, Charly, Julien Le Sommer, Gennip, Simon, Van, Ronan Fablet, Marie Drévillon, Yann Drillet, and Le Traon, Pierre-Yves. 2025. “OceanBench: A Benchmark for Data-Driven Global Ocean Forecasting systems.” HAL (1-14). https://hal.science/hal-05412248.

Harvard

El Aouni, A. et al. (2025) ‘OceanBench: A Benchmark for Data-Driven Global Ocean Forecasting systems’, HAL. Available at: https://hal.science/hal-05412248.

IEEE

A. El Aouni et al., “OceanBench: A Benchmark for Data-Driven Global Ocean Forecasting systems,” HAL, no. 1-14, 2025.

BibTeX

@article{elaouni2025oceanbench,
  title     = {{OceanBench: A Benchmark for Data-Driven Global Ocean Forecasting systems}},
  author    = {El Aouni, Anass and Gaudel, Quentin and Charly, Regnier, and Le Sommer, Julien and Van, Gennip, Simon, and Fablet, Ronan and Drévillon, Marie and Drillet, Yann and Pierre-Yves, Le Traon,},
  journal   = {HAL},
  year      = {2025},
  number    = {1-14},
  url       = {https://hal.science/hal-05412248}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Earth and Planetary Sciences › Oceanography › Oceanographic and Atmospheric Processes

  • benchmark
  • nowcasting
  • reanalysis
  • sea surface height
  • sea surface temperature
  • salinity
  • ocean currents
  • forecast evaluation metrics

Work with this paper

Most-cited papers in Earth and Planetary Sciences

All highly cited Earth and Planetary Sciences papers

Questions about this paper

How do I cite this paper in APA style?

El Aouni, A., Gaudel, Q., Charly, R., Le Sommer, J., Van, G. S., Fablet, R., Drévillon, M., Drillet, Y., & Pierre-Yves, L. T. (2025). OceanBench: A Benchmark for Data-Driven Global Ocean Forecasting systems. HAL. https://hal.science/hal-05412248

How many times has this paper been cited?

0 times, according to OpenAlex on 15 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access: read the free full text at HAL.

Who wrote this paper?

Anass El Aouni, Quentin Gaudel, Regnier, Charly, Julien Le Sommer, Gennip, Simon, Van, Ronan Fablet, Marie Drévillon, Yann Drillet, Le Traon, Pierre-Yves.

Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.