paper
2023
Nowcasting
Extremes & hazards New model or method
GAN or VAECNN / U-Net0–6 hKNMI (Royal Netherlands Meteorological Institute) Journal
2023-09-14
051
Sep 2023
Charlotte Cambier van Nooten, Koert Schreurs, Jasper S. Wijnands et al.
Artificial Intelligence for the Earth Systems
KNMI (Royal Netherlands Meteorological Institute)
A deep generative nowcasting model with a balanced loss and temperature input extends skillful heavy-rain nowcasts over the Netherlands to 60-minute lead times.
Improving Precipitation Nowcasting for High-Intensity Events Using Deep Generative Models with Balanced Loss and Temperature Data: A Case Study in the Netherlands
In one sentence. A deep generative nowcasting model with a balanced loss and temperature input extends skillful heavy-rain nowcasts over the Netherlands to 60-minute lead times.
Labels
- Topic
- Nowcasting, Extremes & hazards
- Type
- New model or method
- Method
- GAN or VAE, CNN / U-Net
- Time scale
- 0–6 h
- Domain
- Regional
- Data
- Radar, Station / in-situ
- Status
- Research
- Identifiers
- DOI:10.1175/aies-d-23-0017.1 OpenAlex:W4386740901
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.