paper
2021
Hybrid physics-ML & parameterization
New model or method
CNN / U-NetNOAA (incl. GFDL, PSL, GSL, NCEP/EMC)Colorado State University (incl. CIRA) Journal
2021-07-28
051
Jul 2021
Ryan Lagerquist, David D. Turner, Imme Ebert‐Uphoff et al.
Journal of Atmospheric and Oceanic Technology
NOAA (incl. GFDL, PSL, GSL, NCEP/EMC), Colorado State University (incl. CIRA)
Knowledge-guided U-Net++ emulates the RRTM shortwave radiation scheme for NWP, running about 10^4 times faster with good tropical generalization.
Hybrid physics-ML & parameterization
Using deep learning to emulate and accelerate a radiative-transfer model
In one sentence. Knowledge-guided U-Net++ emulates the RRTM shortwave radiation scheme for NWP, running about 10^4 times faster with good tropical generalization.
Labels
- Topic
- Hybrid physics-ML & parameterization
- Type
- New model or method
- Method
- CNN / U-Net
- Domain
- Global
- Data
- Other
- Status
- Pre-operational / experimental
- Identifiers
- DOI:10.1175/jtech-d-21-0007.1 OpenAlex:W3186737891
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.