Mercator Ocean International participated in the 2025 Conference on Neural Information Processing Systems (NeurIPS 2025), held from 2 to 7 December 2025 in San Diego, USA, one of the world’s leading conferences on artificial intelligence.
During the conference, Anass El Aouni, Oceanographer and Machine Learning Researcher, and Quentin Gaudel, ML Systems Architect at Mercator Ocean, presented OceanBench, the first open benchmark dedicated to the evaluation of AI-driven global ocean forecasting systems.
OceanBench was unveiled at NeurIPS 2025 as part of Mercator Ocean’s broader efforts to advance trustworthy and operational artificial intelligence for ocean prediction, alongside its global neural-network-based forecasting system GLONET.
Related links:
- Press release: Mercator Ocean International Makes AI Ocean Forecasting Operational with GLONET Validated by OceanBench at NeurIPS 2025 – Mercator Ocean International
- Related article: Mercator launches OceanBench for AI forecasting
- NeurIPS poster: NeurIPS Poster OceanBench: A Benchmark for Data-Driven Global Ocean Forecasting systems
About OceanBench V1.0
OceanBench: A Benchmark for Data-Driven Global Ocean Forecasting Systems was published and presented at NeurIPS 2025, within the Datasets and Benchmarks track, which focuses on high-quality reference frameworks for the evaluation of machine learning systems.
The work was led by Mercator Ocean International, with contributions from Anass El Aouni, Quentin Gaudel, Juan Emmanuel Johnson, Charly Regnier, Julien Le Sommer, Simon van Gennip, Ronan Fablet, Marie Drevillon, Yann Drillet, and Pierre-Yves Le Traon.
OceanBench is implemented by Mercator Ocean International in collaboration with the Programme prioritaire de recherche Océan & Climat, IMT Atlantique, Université Grenoble Alpes, and the IGEO – Instituto de Geociencias.