paper
2024
Extremes & hazards
Regional & km-scale models New model or method
CNN / U-Net6 h–3 daysInriaMétéo-France (incl. CNRM) Journal
2024-04-01
051
Apr 2024
Laure Raynaud, Ghislain Faure, M. Puig et al.
Artificial Intelligence for the Earth Systems
Inria, Météo-France (incl. CNRM)
A U-Net detects tropical cyclone wind structure in kilometer-scale AROME forecasts with IoU near 0.8, outperforming an operational heuristic, especially for weak storms.
A Convolutional Neural Network for Tropical Cyclone Wind Structure Identification in Kilometer-Scale Forecasts
In one sentence. A U-Net detects tropical cyclone wind structure in kilometer-scale AROME forecasts with IoU near 0.8, outperforming an operational heuristic, especially for weak storms.
Labels
- Topic
- Extremes & hazards, Regional & km-scale models
- Type
- New model or method
- Method
- CNN / U-Net
- Time scale
- 6 h–3 days
- Domain
- Regional
- Data
- km-scale or high-res simulation, NWP analysis or forecasts (IFS, GFS, ...)
- Status
- Pre-operational / experimental
- Identifiers
- DOI:10.1175/aies-d-23-0059.1 OpenAlex:W4393386500
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.