paper
2023
Post-processing & calibration
Observations & remote sensing New model or method
CNN / U-Net6 h–3 daysColorado State University (incl. CIRA) Journal
2023-10-27
022
Oct 2023
Katherine Haynes, Jason Stock, Jack Dostalek et al.
Artificial Intelligence for the Earth Systems
Colorado State University (incl. CIRA)
A residual U-Net postprocesses RAP forecasts with satellite data, improving dewpoint profiles and CAPE by up to 40% with well-calibrated uncertainty for severe-weather forecasting.
Exploring the Use of Machine Learning to Improve Vertical Profiles of Temperature and Moisture
In one sentence. A residual U-Net postprocesses RAP forecasts with satellite data, improving dewpoint profiles and CAPE by up to 40% with well-calibrated uncertainty for severe-weather forecasting.
Labels
- Topic
- Post-processing & calibration, Observations & remote sensing
- Type
- New model or method
- Method
- CNN / U-Net
- Time scale
- 6 h–3 days
- Domain
- Regional
- Data
- NWP analysis or forecasts (IFS, GFS, ...), Satellite
- Status
- Research
- Identifiers
- DOI:10.1175/aies-d-22-0090.1 OpenAlex:W4387972375
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.