paper
2022
Post-processing & calibration
Evaluation or intercomparison of existing models
Classical ML (trees, GP, linear, kernels)6 h–3 days Journal
2022-08-29
012
Aug 2022
Christopher C. Hennon, Andrew Coleman, Andrew Hill
Weather and Forecasting
Neural networks trained on MOS, HRRR and NWS guidance cut 1-day temperature error 20–30% versus MOS at 11 US cities, though gains over linear regression were not significant.
Short-Term Weather Forecast Skill of Artificial Neural Networks
In one sentence. Neural networks trained on MOS, HRRR and NWS guidance cut 1-day temperature error 20–30% versus MOS at 11 US cities, though gains over linear regression were not significant.
Labels
- Topic
- Post-processing & calibration
- Type
- Evaluation or intercomparison of existing models
- Method
- Classical ML (trees, GP, linear, kernels)
- Time scale
- 6 h–3 days
- Domain
- Local / station
- Data
- NWP analysis or forecasts (IFS, GFS, ...), Station / in-situ
- Status
- Pre-operational / experimental
- Identifiers
- DOI:10.1175/waf-d-22-0009.1 OpenAlex:W4293731191
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.