paper
2025
Sub-seasonal to seasonal
Extremes & hazards New model or method
CNN / U-NetSeasonal to annualNOAA (incl. GFDL, PSL, GSL, NCEP/EMC)Princeton University Journal
2025-12-18
051
Dec 2025
Antonia Comaniciu, Hiroyuki Murakami
Artificial Intelligence for the Earth Systems
NOAA (incl. GFDL, PSL, GSL, NCEP/EMC), Princeton University
CNNs trained on SST and OLR maps predict Atlantic hurricane activity (ACE) categories four months ahead, with higher accuracy than past May and August seasonal forecasts.
A Novel Method for Improving Seasonal Atlantic Hurricane Activity Prediction Based on Convolutional Neural Networks and Visualization Maps
In one sentence. CNNs trained on SST and OLR maps predict Atlantic hurricane activity (ACE) categories four months ahead, with higher accuracy than past May and August seasonal forecasts.
Labels
- Topic
- Sub-seasonal to seasonal, Extremes & hazards
- Type
- New model or method
- Method
- CNN / U-Net
- Time scale
- Seasonal to annual
- Domain
- Regional
- Data
- Other
- Status
- Research
- Identifiers
- DOI:10.1175/aies-d-25-0010.1 OpenAlex:W4417467504
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.