Graph Nets + Physics | Visiting PhD Student at Geometric Intelligence Lab, UC Santa Barbara
π https://danielholmberg.fi
Daniel Holmberg
Loading...
The ocean is inherently chaotic, yet existing data-driven ocean models produce deterministic forecasts. In our new preprint, we introduce Njord, a probabilistic graph neural network for ensemble ocean forecasting.
Link: arxiv.org/abs/2605.15470
A couple highlights below π§΅
β’ K-means cluster meshes. Latitude weighted spherical K-means produces a mesh that conforms better to ocean grids by construction compared to previously used quadrilateral or icosahedral meshes.
β’ Sea ice is predicted alongside other physical state variables. Smooth invertible activation functions together with a binary density channel keep ice variables within realistic bounds.