Technical Report: Towards Unified Diffusion Models for Multi-Model Climate Emulation at Scale
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_ | 1866908679944536064 |
|---|---|
| author | Immorlano, Francesco Tavares, Elijah Draxler, Felix Smyth, Padhraic Gentine, Pierre Mandt, Stephan |
| author_facet | Immorlano, Francesco Tavares, Elijah Draxler, Felix Smyth, Padhraic Gentine, Pierre Mandt, Stephan |
| contents | Large ensembles of climate projections are essential for characterizing uncertainty in future climate and extreme weather events, yet computational constraints of numerical climate models limit ensemble sizes to a small number of realizations per model. We present a unified conditional diffusion model that dramatically reduces this computational barrier by learning shared distributional patterns across multiple Coupled Model Intercomparison Project phase 6 models and emission scenarios. Rather than training separate emulators for each model-scenario combination, our approach captures the common statistical structures underlying nine CMIP6 models, generating daily temperature maps with a global coverage for historical and future periods. This unified framework enables: (i) efficient probabilistic sampling for comprehensive uncertainty quantification across models and scenarios; (ii) rapid generation of large ensembles that would be computationally intractable with traditional climate models; (iii) variance-reduced treatment effect analysis via fixed-seed generation that disentangles forced climate responses from internal variability. Evaluations on held-out models demonstrate reliable generalization to unseen future climates, enabling rapid exploration of different emission pathways. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_22970 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Technical Report: Towards Unified Diffusion Models for Multi-Model Climate Emulation at Scale Immorlano, Francesco Tavares, Elijah Draxler, Felix Smyth, Padhraic Gentine, Pierre Mandt, Stephan Atmospheric and Oceanic Physics Large ensembles of climate projections are essential for characterizing uncertainty in future climate and extreme weather events, yet computational constraints of numerical climate models limit ensemble sizes to a small number of realizations per model. We present a unified conditional diffusion model that dramatically reduces this computational barrier by learning shared distributional patterns across multiple Coupled Model Intercomparison Project phase 6 models and emission scenarios. Rather than training separate emulators for each model-scenario combination, our approach captures the common statistical structures underlying nine CMIP6 models, generating daily temperature maps with a global coverage for historical and future periods. This unified framework enables: (i) efficient probabilistic sampling for comprehensive uncertainty quantification across models and scenarios; (ii) rapid generation of large ensembles that would be computationally intractable with traditional climate models; (iii) variance-reduced treatment effect analysis via fixed-seed generation that disentangles forced climate responses from internal variability. Evaluations on held-out models demonstrate reliable generalization to unseen future climates, enabling rapid exploration of different emission pathways. |
| title | Technical Report: Towards Unified Diffusion Models for Multi-Model Climate Emulation at Scale |
| topic | Atmospheric and Oceanic Physics |
| url | https://arxiv.org/abs/2511.22970 |