paper
2025
Extremes & hazards
Explainability, uncertainty & physics New model or method
CNN / U-Net6 h–3 daysColorado State University (incl. CIRA)NOAA (incl. GFDL, PSL, GSL, NCEP/EMC) Journal
2025-05-15
051
May 2025
Ryan Lagerquist, John A. Knaff, Christopher J. Slocum et al.
Weather and Forecasting
Colorado State University (incl. CIRA), NOAA (incl. GFDL, PSL, GSL, NCEP/EMC)
CNNs on satellite imagery add little skill over SHIPS scalars for 24-h tropical cyclone rapid intensification; XAI shows they rely on known features, with well-calibrated uncertainty.
Identifying Data Sources and Physical Strategies Used by Neural Networks to Predict TC Rapid Intensification
In one sentence. CNNs on satellite imagery add little skill over SHIPS scalars for 24-h tropical cyclone rapid intensification; XAI shows they rely on known features, with well-calibrated uncertainty.
Labels
- Topic
- Extremes & hazards, Explainability, uncertainty & physics
- Type
- New model or method
- Method
- CNN / U-Net
- Time scale
- 6 h–3 days
- Domain
- Global
- Data
- Satellite, Other
- Status
- Research
- Identifiers
- DOI:10.1175/waf-d-24-0166.1 OpenAlex:W4410397028
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.