paper
2024
Extremes & hazards
Nowcasting New model or method
CNN / U-Net0–6 hColorado State University (incl. CIRA)NOAA (incl. GFDL, PSL, GSL, NCEP/EMC)University of Oklahoma (AI2ES) Journal
2024-10-01
051
Oct 2024
Tobias G. Schmidt, Amy McGovern, John T. Allen et al.
Artificial Intelligence for the Earth Systems
Colorado State University (incl. CIRA), NOAA (incl. GFDL, PSL, GSL, NCEP/EMC), University of Oklahoma (AI2ES)
A 3D U-Net nowcasts gridded severe hail up to 40 minutes ahead using Warn-on-Forecast and lightning data, beating HAILCAST baselines with max CSI near 0.48 at 20 minutes.
Gridded Severe Hail Nowcasting Using 3D U-Nets, Lightning Observations, and the Warn-on-Forecast System
In one sentence. A 3D U-Net nowcasts gridded severe hail up to 40 minutes ahead using Warn-on-Forecast and lightning data, beating HAILCAST baselines with max CSI near 0.48 at 20 minutes.
Labels
- Topic
- Extremes & hazards, Nowcasting
- Type
- New model or method
- Method
- CNN / U-Net
- Time scale
- 0–6 h
- Domain
- Regional
- Data
- NWP analysis or forecasts (IFS, GFS, ...), Radar, Other
- Status
- Research
- Identifiers
- DOI:10.1175/aies-d-24-0026.1 OpenAlex:W4404322442
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.