The authors developed HClimRep-Ocean, a graph neural network-based emulator that directly processes the native unstructured mesh of the Finite-volumE Sea ice-Ocean Model (FESOM2), avoiding the interpolation and resolution loss inherent in standard latitude-longitude grids.
Ocean emulator runs on unstructured mesh, beating baselines for currents
HClimRep-Ocean forecasts ocean currents more accurately than existing methods at 30-day lead times, while temperature and salinity skill remains limited.
Research Lab
Kacper Nowak · Aleksei Koldunov · Nikolay Koldunov · Savvas Melidonis · Ankit Patnala · Simon Grasse · +4 more
Alfred Wegener Institute, Helmholtz Centre for Polar and Marine Research · Forschungszentrum Jülich GmbH, Jülich Supercomputing Center · Karlsruhe Institute of Technology · European Center for Medium-Range Weather Forecasts · University of Cologne
Research Digest··3 min read
The authors present HClimRep-Ocean, a machine-learning emulator that operates directly on the unstructured computational mesh of the FESOM2 ocean model.
Why this paper
From Alfred Wegener Institute, Helmholtz Centre for Polar and Marine Research and 5 others
In one line
HClimRep-Ocean beats all baselines for 30-day current forecasts but not for temperature and salinity.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§