paper
2021
Nowcasting
Post-processing & calibration New model or method
Classical ML (trees, GP, linear, kernels)0–6 h6 h–3 daysDeutscher Wetterdienst (DWD) Journal
2021-04-22
051
Apr 2021
P. Schaumann, Reinhold Hess, Martin Rempel et al.
Weather and Forecasting
Deutscher Wetterdienst (DWD)
Neural network combines RadVOR radar nowcasts with postprocessed COSMO-DE-EPS ensembles, giving calibrated precipitation threshold probabilities that beat both inputs for 1 to 6 h.
A Calibrated and Consistent Combination of Probabilistic Forecasts for the Exceedance of Several Precipitation Thresholds Using Neural Networks
In one sentence. Neural network combines RadVOR radar nowcasts with postprocessed COSMO-DE-EPS ensembles, giving calibrated precipitation threshold probabilities that beat both inputs for 1 to 6 h.
Labels
- Topic
- Nowcasting, Post-processing & calibration
- Type
- New model or method
- Method
- Classical ML (trees, GP, linear, kernels)
- Time scale
- 0–6 h, 6 h–3 days
- Domain
- Regional
- Data
- Radar, NWP analysis or forecasts (IFS, GFS, ...)
- Status
- Research
- Identifiers
- DOI:10.1175/waf-d-20-0188.1 OpenAlex:W3159768227
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.