IPSL-AID: Generative Diffusion Models for Climate Downscaling from Global to Regional Scales
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910102602121216 |
|---|---|
| author | Kingston, Kishanthan Boucher, Olivier Bouchet, Freddy Chapel, Pierre Eade, Rosemary Lamarque, Jean-Francois Lguensat, Redouane Ardaneh, Kazem |
| author_facet | Kingston, Kishanthan Boucher, Olivier Bouchet, Freddy Chapel, Pierre Eade, Rosemary Lamarque, Jean-Francois Lguensat, Redouane Ardaneh, Kazem |
| contents | Effective adaptation and mitigation strategies for climate change require high-resolution projections to inform strategic decision-making. Conventional global climate models, which typically operate at resolutions of 150 to 200 kilometers, lack the capacity to represent essential regional processes. IPSL-AID is a global to regional downscaling tool based on a denoising diffusion probabilistic model designed to address this limitation. Trained on ERA5 reanalysis data, it generates 0.25 degree resolution fields for temperature, wind, and precipitation using coarse inputs and their spatiotemporal context. It also models probability distributions of fine-scale features to produce plausible scenarios for uncertainty quantification. The model accurately reconstructs statistical distributions, including extreme events, power spectra, and spatial structures. This work highlights the potential of generative diffusion models for efficient climate downscaling with uncertainty |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_03275 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | IPSL-AID: Generative Diffusion Models for Climate Downscaling from Global to Regional Scales Kingston, Kishanthan Boucher, Olivier Bouchet, Freddy Chapel, Pierre Eade, Rosemary Lamarque, Jean-Francois Lguensat, Redouane Ardaneh, Kazem Atmospheric and Oceanic Physics Artificial Intelligence Machine Learning Effective adaptation and mitigation strategies for climate change require high-resolution projections to inform strategic decision-making. Conventional global climate models, which typically operate at resolutions of 150 to 200 kilometers, lack the capacity to represent essential regional processes. IPSL-AID is a global to regional downscaling tool based on a denoising diffusion probabilistic model designed to address this limitation. Trained on ERA5 reanalysis data, it generates 0.25 degree resolution fields for temperature, wind, and precipitation using coarse inputs and their spatiotemporal context. It also models probability distributions of fine-scale features to produce plausible scenarios for uncertainty quantification. The model accurately reconstructs statistical distributions, including extreme events, power spectra, and spatial structures. This work highlights the potential of generative diffusion models for efficient climate downscaling with uncertainty |
| title | IPSL-AID: Generative Diffusion Models for Climate Downscaling from Global to Regional Scales |
| topic | Atmospheric and Oceanic Physics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2604.03275 |