paper
2020
Post-processing & calibration
Extremes & hazards New model or method
Other3–15 days Other
2020-02-20
012
Feb 2020
Salvatore Candido, Aakanksha Singh, Luca Delle Monache
preprint
Distills the analog ensemble post-processing into a small neural network, enabling fast on-the-fly ECMWF lower-stratosphere wind corrections with a model of only hundreds of kilobytes.
Distilling an Analog Ensemble into a Deep Neural Network
In one sentence. Distills the analog ensemble post-processing into a small neural network, enabling fast on-the-fly ECMWF lower-stratosphere wind corrections with a model of only hundreds of kilobytes.
Labels
- Topic
- Post-processing & calibration, Extremes & hazards
- Type
- New model or method
- Method
- Other
- Time scale
- 3–15 days
- Domain
- Global
- Data
- NWP analysis or forecasts (IFS, GFS, ...), Station / in-situ
- Status
- Pre-operational / experimental
- Identifiers
- DOI:10.1002/essoar.10502348.1 OpenAlex:W3006922662
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.