Metraipolis › archive › dc_e5e975cedf8f

Just Weather Scoring: Efficient End-to-end Nowcasting with Distributional Diffusion — arXiv:2610.12189

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.12189
License (as archived)
CC0-1.0
Archived
2026-10-09T06:23:40.913Z
SHA-256 of the archived text
82aa82046baf59e510a317d6aab9bf2d57d6dae13bf4ce8a89022117d78d7f55
Stable URL of this page
https://metraipolis.com/documento/dc_e5e975cedf8f

How to cite

Just Weather Scoring: Efficient End-to-end Nowcasting with Distributional Diffusion — arXiv:2610.12189 — arXiv (en), https://arxiv.org/abs/2610.12189 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e5e975cedf8f (Metraipolis archive dc_e5e975cedf8f, sha256 82aa82046baf59e510a317d6aab9bf2d57d6dae13bf4ce8a89022117d78d7f55)
BibTeX
@misc{dce5e975cedf8f,
  title = {Just Weather Scoring: Efficient End-to-end Nowcasting with Distributional Diffusion — arXiv:2610.12189},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.12189},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e5e975cedf8f; sha256 82aa82046baf59e510a317d6aab9bf2d57d6dae13bf4ce8a89022117d78d7f55},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12189. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generative diffusion models are well-suited for probabilistic precipitation nowcasting, but existing approaches often rely on separately trained compression or deterministic forecasting components and remain costly at inference due to iterative denoising. We introduce Just Weather Scoring (JWS), a single-stage, end-to-end diffusion model which addresses both issues by forecasting directly in radar space and enabling few-step generation. Radar-space modeling greatly simplifies training and inference and eliminates uncertainty arising from lossy compression. JWS combines Masked Asynchronous Diffusion, a timestep-sampling scheme that preserves clean context while adapting diffusion training to high-dimensional spatio-temporal data, with a simple scoring-rule objective that aligns training with probabilistic forecasting and unlocks few-step generation. On the SEVIR and MeteoNet benchmarks, JWS achieves state-of-the-art probabilistic forecasting performance at reduced training and inference cost. Even our smallest model remains competitive using substantially fewer parameters and more than 17x faster inference.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.12189 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T05:50:31.715Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).