Climate in a Bottle: Towards a Generative Foundation Model for the Kilometer-Scale Global Atmosphere
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_ | 1866916871928807424 |
|---|---|
| author | Brenowitz, Noah D. Ge, Tao Subramaniam, Akshay Manshausen, Peter Gupta, Aayush Hall, David M. Mardani, Morteza Vahdat, Arash Kashinath, Karthik Pritchard, Michael S. |
| author_facet | Brenowitz, Noah D. Ge, Tao Subramaniam, Akshay Manshausen, Peter Gupta, Aayush Hall, David M. Mardani, Morteza Vahdat, Arash Kashinath, Karthik Pritchard, Michael S. |
| contents | Climate modeling is reaching unprecedented resolution, producing petabytes of data. AI climate model emulators offer a path to computationally cheap analysis, enabling new scientific insight and scenario planning. Recent advances show promise in faithfully emulating climate data. However, prevailing auto-regressive paradigms are difficult to train on climate time horizons due to drifts, instabilities, and component-coupling challenges. They are hard to scale to high resolution and require sifting through troves of output to identify rare extremes of interest. We present Climate in a Bottle (cBottle), a generative diffusion-based framework emulating global 5 km climate simulations and reanalysis on the HEALPix grid. cBottle samples directly from the full distribution of atmospheric states, avoiding auto-regressive rollout, and is the first to reach this 12.5M-pixel global resolution. It consists of two stages: a coarse-resolution generator conditioned on sea surface temperatures and solar position, followed by a patch-based 16x super-resolution stage. cBottle passes a battery of tests, including diurnal-to-seasonal variability, large-scale modes of variability, tropical cyclone statistics, and trends of climate change and weather extremes. It is a step toward a foundation model: bridging data modalities (reanalysis and simulation), enabling zero-shot bias correction, downscaling, and data infilling. It also enables new interactivity via guided diffusion. For example, we train a tropical cyclone (TC) classifier alongside the generator, guide towards TC states, and obtain physically credible samples. This opens the door to guidance methods for a wide array of user queries and new ways of interacting with climate data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_06474 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Climate in a Bottle: Towards a Generative Foundation Model for the Kilometer-Scale Global Atmosphere Brenowitz, Noah D. Ge, Tao Subramaniam, Akshay Manshausen, Peter Gupta, Aayush Hall, David M. Mardani, Morteza Vahdat, Arash Kashinath, Karthik Pritchard, Michael S. Atmospheric and Oceanic Physics Climate modeling is reaching unprecedented resolution, producing petabytes of data. AI climate model emulators offer a path to computationally cheap analysis, enabling new scientific insight and scenario planning. Recent advances show promise in faithfully emulating climate data. However, prevailing auto-regressive paradigms are difficult to train on climate time horizons due to drifts, instabilities, and component-coupling challenges. They are hard to scale to high resolution and require sifting through troves of output to identify rare extremes of interest. We present Climate in a Bottle (cBottle), a generative diffusion-based framework emulating global 5 km climate simulations and reanalysis on the HEALPix grid. cBottle samples directly from the full distribution of atmospheric states, avoiding auto-regressive rollout, and is the first to reach this 12.5M-pixel global resolution. It consists of two stages: a coarse-resolution generator conditioned on sea surface temperatures and solar position, followed by a patch-based 16x super-resolution stage. cBottle passes a battery of tests, including diurnal-to-seasonal variability, large-scale modes of variability, tropical cyclone statistics, and trends of climate change and weather extremes. It is a step toward a foundation model: bridging data modalities (reanalysis and simulation), enabling zero-shot bias correction, downscaling, and data infilling. It also enables new interactivity via guided diffusion. For example, we train a tropical cyclone (TC) classifier alongside the generator, guide towards TC states, and obtain physically credible samples. This opens the door to guidance methods for a wide array of user queries and new ways of interacting with climate data. |
| title | Climate in a Bottle: Towards a Generative Foundation Model for the Kilometer-Scale Global Atmosphere |
| topic | Atmospheric and Oceanic Physics |
| url | https://arxiv.org/abs/2505.06474 |