Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918207697190912 |
|---|---|
| author | Andry, Gérôme Lewin, Sacha Rozet, François Rochman, Omer Mangeleer, Victor Pirlet, Matthias Faulx, Elise Grégoire, Marilaure Louppe, Gilles |
| author_facet | Andry, Gérôme Lewin, Sacha Rozet, François Rochman, Omer Mangeleer, Victor Pirlet, Matthias Faulx, Elise Grégoire, Marilaure Louppe, Gilles |
| contents | Deep learning has advanced weather forecasting, but accurate predictions first require identifying the current state of the atmosphere from observational data. In this work, we introduce Appa, a score-based data assimilation model generating global atmospheric trajectories at 0.25\si{\degree} resolution and 1-hour intervals. Powered by a 565M-parameter latent diffusion model trained on ERA5, Appa can be conditioned on arbitrary observations to infer plausible trajectories, without retraining. Our probabilistic framework handles reanalysis, filtering, and forecasting, within a single model, producing physically consistent reconstructions from various inputs. Results establish latent score-based data assimilation as a promising foundation for future global atmospheric modeling systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_18720 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilation Andry, Gérôme Lewin, Sacha Rozet, François Rochman, Omer Mangeleer, Victor Pirlet, Matthias Faulx, Elise Grégoire, Marilaure Louppe, Gilles Machine Learning Atmospheric and Oceanic Physics Deep learning has advanced weather forecasting, but accurate predictions first require identifying the current state of the atmosphere from observational data. In this work, we introduce Appa, a score-based data assimilation model generating global atmospheric trajectories at 0.25\si{\degree} resolution and 1-hour intervals. Powered by a 565M-parameter latent diffusion model trained on ERA5, Appa can be conditioned on arbitrary observations to infer plausible trajectories, without retraining. Our probabilistic framework handles reanalysis, filtering, and forecasting, within a single model, producing physically consistent reconstructions from various inputs. Results establish latent score-based data assimilation as a promising foundation for future global atmospheric modeling systems. |
| title | Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilation |
| topic | Machine Learning Atmospheric and Oceanic Physics |
| url | https://arxiv.org/abs/2504.18720 |