paper
2021
Post-processing & calibration
New model or method
CNN / U-Net6 h–3 daysKNMI (Royal Netherlands Meteorological Institute) Journal
2021-04-01
047
Apr 2021
Simon Veldkamp, Kirien Whan, Sjoerd Dirksen et al.
Monthly Weather Review
KNMI (Royal Netherlands Meteorological Institute)
CNNs postprocess HARMONIE-AROME wind speed forecasts over the Netherlands using full spatial patterns, improving CRPS and Brier skill over fully connected networks and quantile regression forests at 48 h.
Statistical Postprocessing of Wind Speed Forecasts Using Convolutional Neural Networks
In one sentence. CNNs postprocess HARMONIE-AROME wind speed forecasts over the Netherlands using full spatial patterns, improving CRPS and Brier skill over fully connected networks and quantile regression forests at 48 h.
Labels
- Topic
- Post-processing & calibration
- Type
- New model or method
- Method
- CNN / U-Net
- Time scale
- 6 h–3 days
- Domain
- Regional
- Data
- NWP analysis or forecasts (IFS, GFS, ...), Station / in-situ
- Status
- Research
- Identifiers
- arXiv:2007.04005 DOI:10.1175/mwr-d-20-0219.1 OpenAlex:W3042212860
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.