paper
2019
Extremes & hazards
Explainability, uncertainty & physics New model or method
CNN / U-Net6 h–3 daysNSF NCAR / UCAR Journal
2019-07-17
061
Jul 2019
David John Gagne II, Sue Ellen Haupt, Douglas W. Nychka et al.
Monthly Weather Review
NSF NCAR / UCAR
A CNN outperforms logistic regression at predicting severe hail from convection-allowing NWP fields, and interpretation reveals learned storm and environment features consistent with hail physics.
Interpretable Deep Learning for Spatial Analysis of Severe Hailstorms
In one sentence. A CNN outperforms logistic regression at predicting severe hail from convection-allowing NWP fields, and interpretation reveals learned storm and environment features consistent with hail physics.
Labels
- Topic
- Extremes & hazards, Explainability, uncertainty & physics
- Type
- New model or method
- Method
- CNN / U-Net
- Time scale
- 6 h–3 days
- Domain
- Regional
- Data
- NWP analysis or forecasts (IFS, GFS, ...)
- Status
- Research
- Identifiers
- DOI:10.1175/mwr-d-18-0316.1 OpenAlex:W2947707259
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.