paper
2025
Extremes & hazards
Global medium-range NWP Evaluation or intercomparison of existing models
Transformer / ViTPhysics-informed / physics-constrained6 h–3 days3–15 daysChina Meteorological Administration (CMA)Fudan University (FuXi) Journal
2025-12-19
055
Dec 2025
Zeyi Niu, Wei Huang, Yuhua Yang et al.
Quarterly Journal of the Royal Meteorological Society
China Meteorological Administration (CMA), Fudan University (FuXi)
Hybrid SHTM–FuXi typhoon system cuts 72-h track error by 16.5% versus FuXi alone and improves 2024 land precipitation threat scores.
Performance of a machine‐learning‐physics hybrid model on 2024 typhoons and land precipitations
In one sentence. Hybrid SHTM–FuXi typhoon system cuts 72-h track error by 16.5% versus FuXi alone and improves 2024 land precipitation threat scores.
Labels
- Topic
- Extremes & hazards, Global medium-range NWP
- Type
- Evaluation or intercomparison of existing models
- Method
- Transformer / ViT, Physics-informed / physics-constrained
- Time scale
- 6 h–3 days, 3–15 days
- Domain
- Regional
- Data
- ERA5 / reanalysis, NWP analysis or forecasts (IFS, GFS, ...)
- Status
- Pre-operational / experimental
- Identifiers
- DOI:10.1002/qj.70101 OpenAlex:W4417503411
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.