paper
2020
Extremes & hazards
Evaluation or intercomparison of existing models
Classical ML (trees, GP, linear, kernels)CNN / U-Net6 h–3 days Preprint
2020-01-01
008
Jan 2020
Brice E. Coffer, Michaela Kubacki, Yixin Wen et al.
Maryland Shared Open Access Repository (USMAI Consortium)
Random forest and CNN on RUC pre-storm soundings predict supercell tornadoes, reaching about 66% accuracy for tornadic cases after resampling.
Using Machine Learning Techniques for Supercell Tornado Prediction with Environmental Sounding Data
In one sentence. Random forest and CNN on RUC pre-storm soundings predict supercell tornadoes, reaching about 66% accuracy for tornadic cases after resampling.
Labels
- Topic
- Extremes & hazards
- Type
- Evaluation or intercomparison of existing models
- Method
- Classical ML (trees, GP, linear, kernels), CNN / U-Net
- Time scale
- 6 h–3 days
- Domain
- Regional
- Data
- NWP analysis or forecasts (IFS, GFS, ...)
- Status
- Research
- Identifiers
- DOI:10.13016/m2izgp-yw55 OpenAlex:W3045538543
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.