paper
2020
Downscaling & super-resolution
Observations & remote sensing New model or method
CNN / U-Net0–6 hUniversity of Washington Journal
2020-10-12
022
Oct 2020
Andrew Geiss, Joseph Clinton Hardin
Journal of Atmospheric and Oceanic Technology
University of Washington
A deep CNN super-resolves NEXRAD radar reflectivity, outperforming interpolation at 4x and 8x resolution increases on objective and perceptual metrics after six months of training data.
Downscaling & super-resolution
Radar Super Resolution Using a Deep Convolutional Neural Network
In one sentence. A deep CNN super-resolves NEXRAD radar reflectivity, outperforming interpolation at 4x and 8x resolution increases on objective and perceptual metrics after six months of training data.
Labels
- Topic
- Downscaling & super-resolution, Observations & remote sensing
- Type
- New model or method
- Method
- CNN / U-Net
- Time scale
- 0–6 h
- Domain
- Local / station
- Data
- Radar
- Status
- Research
- Identifiers
- DOI:10.1175/jtech-d-20-0074.1 OpenAlex:W3110128403
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.