Conference item
CloudFlow: a flow matching model to generate high-resolution cloud structures
- Abstract:
-
Our limited understanding of clouds is the dominant source of uncertainty in future climate predictions. Understanding how changing atmospheric environmental conditions constrain cloud organisational patterns and their radiative effects is key to understanding their impact on future climate change. We present CloudFlow, a flow matching model that is able to generate high-resolution cloud structures conditioned on coarse-scale atmospheric conditions. Our model generates realistic cloud structures that match the spectra and distributions of the original high-resolution scenes. CloudFlow introduces a new modeling regime to study how atmospheric environmental conditions impact cloud morphologies which will contribute to an improved understanding of cloud feedbacks, the cloud response to a changing climate and its effect on climate itself.
- Publication status:
- Accepted
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Preview, Accepted manuscript, pdf, 1.6MB, Terms of use)
-
- Publication website:
- https://openreview.net/forum?id=meHQFrgQqw#discussion
Authors
- Funder identifier:
- https://ror.org/001aqnf71
- Grant:
- 10113603
- Publisher:
- OpenReview
- Article number:
- 53
- Publication date:
- 2026-05-30
- Acceptance date:
- 2026-06-05
- Event title:
- 43rd International Conference on Machine Learning (ICML 2026)
- Event location:
- Seoul, South Korea
- Event website:
- https://icml.cc/Conferences/2026
- Event start date:
- 2026-07-06
- Event end date:
- 2026-07-11
- Language:
-
English
- Pubs id:
-
2442400
- Local pid:
-
pubs:2442400
- Deposit date:
-
2026-07-07
- ARK identifier:
Terms of use
- Copyright holder:
- Reichelt and Stier
- Copyright date:
- 2026
- Rights statement:
- Copyright 2026 by the author(s).
- Licence:
- CC Attribution (CC BY)
If you are the owner of this record, you can report an update to it here: Report update to this record