paper
2023
Post-processing & calibration
New model or method
CNN / U-Net6 h–3 daysUniversity of California, Berkeley Journal
2023-02-08
026
Feb 2023
Anirudhan Badrinath, Luca Delle Monache, Negin Hayatbini et al.
Weather and Forecasting
University of California, Berkeley
U-Net CNN post-processes West-WRF precipitation over the US West Coast, cutting RMSE 12.9–15.9% versus raw model at 1–4 day leads.
Improving Precipitation Forecasts with Convolutional Neural Networks
In one sentence. U-Net CNN post-processes West-WRF precipitation over the US West Coast, cutting RMSE 12.9–15.9% versus raw model at 1–4 day leads.
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, ...)
- Status
- Research
- Identifiers
- DOI:10.1175/waf-d-22-0002.1 OpenAlex:W4319591303
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.