An end-to-end machine-learning system for global eddy-resolving ocean forecast.

WenHai-E2E, an end-to-end eddy-resolving global ocean forecast system, outperforms a state-of-the-art numerical GOFS in forecast accuracy.

• Why it matters: ML ocean models typically depend on initial conditions from numerical GOFSs, limiting standalone deployment. This work targets that operational bottleneck.
• What they did: The study builds WenHai-E2E to generate forecasts directly from multisource heterogeneous ocean observations, replacing the numerical GOFS pipeline at deployment time. It then compares forecast accuracy against a state-of-the-art numerical GOFS.
• The result: The improved accuracy indicates ML GOFSs can surpass numerical GOFSs and suggests a pathway toward next-generation GOFS development.

AI summary of the abstract · may contain errors · not medical advice · read the paper.