Abstract
Ocean general circulation models (OGCMs) are essential to climate science but computationally expensive, limiting ensemble size and forcing scenarios. Neural emulators promise orders-of-magnitude speedups, yet existing ocean emulators have not combined fine spatial resolution with multi-year autoregressive rollouts. Samudra, the first autoregressive neural ocean emulator to produce multi-decade global rollouts, is limited to 1∘ resolution and exhibits two long-horizon failure modes: mph{variance collapse}, the loss of temporal variability, and mph{imprinting artifacts}, in which velocity patterns leak into deep-ocean fields. We present Samudra 2, which introduces a wider U-Net backbone with modified ConvNeXt-style blocks and a reduced block-internal expansion factor, together with a dynamic loss that reweights output channels according to their prediction errors, strengthening gradients for slow-evolving deep-ocean fields. At 1∘, Samudra 2 increases upper-ocean global-mean temperature R2 from 0.56 to 0.87 and reduces deep-ocean temperature error by roughly sevenfold. The same architecture scales to 1/2∘ and 1/4∘ over approximately 8-year autoregressive rollouts, recovering mesoscale eddies and sharp western boundary currents. Running on a single GPU, Samudra 2 enables larger ensembles for sea-level projections, ocean heat uptake, and climate variability studies.
Yuan Yuan
Postdoctoral researcher
Adam Subel
PhD Student
My research interests include distributed robotics, mobile computing and programmable matter.
Pavel Perezhogin
Postdoctoral researcher
Laure Zanna
Joseph B. Keller and Herbert B. Keller Professor in Applied Mathematics; Professor of Mathematics and Data Science
My research interests include Climate Dynamics, Physical Oceanography, Applied Math, Numerical Methods, and Data Science.