paper
2026
Downscaling & super-resolution
Extremes & hazards New model or method
GAN or VAECNN / U-NetPrinceton University Other
2026-10-10
022
Oct 2026
Rosa Vellosa Lyngwa, Akshaya C. Nikumbh, Subimal Ghosh
preprint
Princeton University
A Wasserstein GAN emulates 10 km Himalayan extreme precipitation from ERA5, reducing relative bias by about 35% versus a CNN baseline.
Downscaling & super-resolution
Emulator for Regional Modeling of Extreme Precipitation in the Himalayas using Wasserstein Generative Adversarial Network
In one sentence. A Wasserstein GAN emulates 10 km Himalayan extreme precipitation from ERA5, reducing relative bias by about 35% versus a CNN baseline.
Labels
- Topic
- Downscaling & super-resolution, Extremes & hazards
- Type
- New model or method
- Method
- GAN or VAE, CNN / U-Net
- Domain
- Regional
- Data
- ERA5 / reanalysis, Other
- Status
- Research
- Identifiers
- DOI:10.22541/essoar.15010207/v1 OpenAlex:W7221342729
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.