paper
2025
Sub-seasonal to seasonal
Explainability, uncertainty & physics New model or method
CNN / U-Net2 weeks–2 monthsColorado State University (incl. CIRA) Journal
2025-10-01
026
Oct 2025
Nicolas J. Gordillo, Elizabeth A. Barnes
Artificial Intelligence for the Earth Systems
Colorado State University (incl. CIRA)
ProtoLNet, an interpretable prototype network, forecasts North American subseasonal temperature from CESM2 and transfers prototypes to ERA5 with useful skill.
Application of an Interpretable Prototypical-Part Network to Subseasonal to Seasonal Climate Prediction over North America
In one sentence. ProtoLNet, an interpretable prototype network, forecasts North American subseasonal temperature from CESM2 and transfers prototypes to ERA5 with useful skill.
Labels
- Topic
- Sub-seasonal to seasonal, Explainability, uncertainty & physics
- Type
- New model or method
- Method
- CNN / U-Net
- Time scale
- 2 weeks–2 months
- Domain
- Regional
- Data
- CMIP / climate model output, NWP analysis or forecasts (IFS, GFS, ...)
- Status
- Research
- Identifiers
- DOI:10.1175/aies-d-24-0021.1 OpenAlex:W4415517652
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.