Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilation

Score-based data assimilation models can produce global atmospheric trajectories at 0.25-degree resolution and 1-hour intervals. Using a spatio-temporal latent diffusion model trained on ERA5 reanalysis data, it can be conditioned on any types of observations to infer the posterior distribution of plausible state trajectories, without retraining.