Published April 26, 2024
| Version v1
Poster
Open
Using expired weather forecasts to supply up to 10000 years of data
Description
This work presents a method for improving climate-related planning by utilizing ensemble weather forecasts previously computed for short-term weather predictions. By re-analyzing these forecasts, which reflect the atmospheric conditions of the last twenty years, but contain more than a hundred times more information, we can significantly enhance the accuracy of near-future climate estimates. This approach bridges the gap between the detailed weather records traditionally used to define climate, but now describing an atmosphere of the past, and the coarse GCM methods, offering insights applicable to the new climate conditions, allowing us to take the correct actions.
Files
CI_poster_compressed.pdf
Files
(23.9 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:498436415c8cf5f7ac1d17a6829d8b49
|
23.9 MB | Preview Download |
Additional details
Related works
- Is continued by
- Conference paper: https://www.climatechange.ai/papers/iclr2024/14 (URL)
Funding
- UK Research and Innovation
- UKRI Centre for Doctoral Training in Application of Artificial Intelligence to the study of Environmental Risks (AI4ER) EP/S022961/1
Dates
- Available
-
2024-04-23presented