Pierre Gentine

Neural operators can now stably emulate full 3D global ocean and sea-ice dynamics out to 60 days at 0.25° resolution, breaking the compute bottleneck of numerical ocean circulation models.

ML weather models may excel in accuracy, but without physical consistency, their forecasts could mislead operational decisions.

Achieve the accuracy of complex 4D data assimilation with the speed of end-to-end inference by operating in a learned latent space.