paper
2026
Extremes & hazards
Probabilistic & ensemble forecasting Evaluation or intercomparison of existing models
Transformer / ViT3–15 daysFudan University (FuXi) Journal
2026-07-06
055
Jul 2026
Jun Liu, Tao Zhou, Jia-Rui Li et al.
Journal of Geophysical Research: Atmospheres
Fudan University (FuXi)
FuXi-ENS gives smaller TC track errors than ECMWF-ENS for 90 storms in 2018 via better steering flow, but remains underdispersive.
Exploring Physical Mechanisms for Superior Tropical Cyclone Track Forecasting in AI‐Based Ensemble Weather Prediction Models
In one sentence. FuXi-ENS gives smaller TC track errors than ECMWF-ENS for 90 storms in 2018 via better steering flow, but remains underdispersive.
Labels
- Topic
- Extremes & hazards, Probabilistic & ensemble forecasting
- Type
- Evaluation or intercomparison of existing models
- Method
- Transformer / ViT
- Time scale
- 3–15 days
- Domain
- Global
- Data
- NWP analysis or forecasts (IFS, GFS, ...), ERA5 / reanalysis
- Status
- Research
- Identifiers
- DOI:10.1029/2025jd046208 OpenAlex:W7167493354
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.