paper
2022
Downscaling & super-resolution
New model or method
CNN / U-NetMétéo-France (incl. CNRM) Journal
2022-12-27
047
Dec 2022
Louis Le Toumelin, Isabelle Gouttevin, Nora Helbig et al.
Artificial Intelligence for the Earth Systems
Météo-France (incl. CNRM)
DEVINE, a CNN trained on ARPS simulations, downscales AROME winds to 30 m over the Alps and cuts the mean wind-speed bias by 27% at 61 stations.
Downscaling & super-resolution
Emulating the Adaptation of Wind Fields to Complex Terrain with Deep Learning
In one sentence. DEVINE, a CNN trained on ARPS simulations, downscales AROME winds to 30 m over the Alps and cuts the mean wind-speed bias by 27% at 61 stations.
Labels
- Topic
- Downscaling & super-resolution
- Type
- New model or method
- Method
- CNN / U-Net
- Domain
- Regional
- Data
- NWP analysis or forecasts (IFS, GFS, ...), km-scale or high-res simulation, Station / in-situ
- Status
- Research
- Identifiers
- DOI:10.1175/aies-d-22-0034.1 OpenAlex:W4312213174
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.