paper
2021
Extremes & hazards
New model or method
Classical ML (trees, GP, linear, kernels)University of Oklahoma (AI2ES) Journal
2021-10-07
026
Oct 2021
Vittorio A. Gensini, Cody Converse, Walker S. Ashley et al.
Weather and Forecasting
University of Oklahoma (AI2ES)
Random forest trained on 150,000 ERA5 proximity soundings best classifies significant tornadoes and hail, with SHAP-derived thresholds for operational nowcasting.
Machine learning classification of significant tornadoes and hail in the U.S. using ERA5 proximity soundings
In one sentence. Random forest trained on 150,000 ERA5 proximity soundings best classifies significant tornadoes and hail, with SHAP-derived thresholds for operational nowcasting.
Labels
- Topic
- Extremes & hazards
- Type
- New model or method
- Method
- Classical ML (trees, GP, linear, kernels)
- Domain
- Regional
- Data
- ERA5 / reanalysis
- Status
- Research
- Identifiers
- DOI:10.1175/waf-d-21-0056.1 OpenAlex:W3203266641
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.