paper
2025
Downscaling & super-resolution
Benchmarks, datasets & evaluation Benchmark or dataset
CNN / U-NetMétéo-France (incl. CNRM) Other
2025-10-06
051
Oct 2025
Rachid El Montassir, Luciano Drozda, Olivier Pannekoucke et al.
preprint
Météo-France (incl. CNRM)
Benchmarks wavelet, gradient and other training losses and their combinations for deep statistical downscaling of wind speed and precipitation; no single loss dominates.
Downscaling & super-resolution
Training loss matters: exploring new fit-for-purpose loss combinations for statistical downscaling
In one sentence. Benchmarks wavelet, gradient and other training losses and their combinations for deep statistical downscaling of wind speed and precipitation; no single loss dominates.
Labels
- Topic
- Downscaling & super-resolution, Benchmarks, datasets & evaluation
- Type
- Benchmark or dataset
- Method
- CNN / U-Net
- Domain
- Regional
- Data
- ERA5 / reanalysis, Other
- Status
- Research
- Identifiers
- DOI:10.22541/essoar.175977614.45331660/v1 OpenAlex:W4414870727
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.