paper
2020
Extremes & hazards
New model or method
Classical ML (trees, GP, linear, kernels)Other6 h–3 daysNOAA (incl. GFDL, PSL, GSL, NCEP/EMC) Journal
2020-03-03
051
Mar 2020
S. Neetu, Matthieu Lengaigne, Jérôme Vialard et al.
Weather and Forecasting
NOAA (incl. GFDL, PSL, GSL, NCEP/EMC)
Builds the first global nonlinear SVM and neural-network tropical cyclone intensity hindcast schemes; globally trained SVM improves skill by about 10% over regional linear schemes.
Quantifying the Benefits of Nonlinear Methods for Global Statistical Hindcasts of Tropical Cyclones Intensity
In one sentence. Builds the first global nonlinear SVM and neural-network tropical cyclone intensity hindcast schemes; globally trained SVM improves skill by about 10% over regional linear schemes.
Labels
- Topic
- Extremes & hazards
- Type
- New model or method
- Method
- Classical ML (trees, GP, linear, kernels), Other
- Time scale
- 6 h–3 days
- Domain
- Global
- Data
- NWP analysis or forecasts (IFS, GFS, ...)
- Status
- Research
- Identifiers
- DOI:10.1175/waf-d-19-0163.1 OpenAlex:W3010604541
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.