paper
2020
Downscaling & super-resolution
New model or method
CNN / U-NetNSF NCAR / UCAR Journal
2020-11-16
061
Nov 2020
Yingkai Sha, David John Gagne, Gregory West et al.
Journal of Applied Meteorology and Climatology
NSF NCAR / UCAR
UNet-AE adds an elevation autoencoder branch to downscale daily TMAX/TMIN from 0.25° to 4 km, cutting MAE by over 10% in unseen regions.
Downscaling & super-resolution
Deep-Learning-Based Gridded Downscaling of Surface Meteorological Variables in Complex Terrain. Part I: Daily Maximum and Minimum 2-m Temperature
In one sentence. UNet-AE adds an elevation autoencoder branch to downscale daily TMAX/TMIN from 0.25° to 4 km, cutting MAE by over 10% in unseen regions.
Labels
- Topic
- Downscaling & super-resolution
- Type
- New model or method
- Method
- CNN / U-Net
- Domain
- Regional
- Data
- Other
- Status
- Research
- Identifiers
- DOI:10.1175/jamc-d-20-0057.1 OpenAlex:W3105660549
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.