paper
2019
Explainability, uncertainty & physics
Extremes & hazards Review, survey or tutorial
Classical ML (trees, GP, linear, kernels)CNN / U-NetNSF NCAR / UCARNOAA (incl. GFDL, PSL, GSL, NCEP/EMC)University of Oklahoma (AI2ES) Journal
2019-11-01
075
Nov 2019
Amy McGovern, Ryan Lagerquist, David John Gagne et al.
Bulletin of the American Meteorological Society
NSF NCAR / UCAR, NOAA (incl. GFDL, PSL, GSL, NCEP/EMC), University of Oklahoma (AI2ES)
Synthesizes ML interpretation methods such as saliency maps and permutation importance, demonstrated on tornado, hail and convective-mode applications.
Explainability, uncertainty & physics
Making the Black Box More Transparent: Understanding the Physical Implications of Machine Learning
In one sentence. Synthesizes ML interpretation methods such as saliency maps and permutation importance, demonstrated on tornado, hail and convective-mode applications.
Labels
- Topic
- Explainability, uncertainty & physics, Extremes & hazards
- Type
- Review, survey or tutorial
- Method
- Classical ML (trees, GP, linear, kernels), CNN / U-Net
- Domain
- Regional
- Data
- Radar, NWP analysis or forecasts (IFS, GFS, ...)
- Status
- Research
- Identifiers
- DOI:10.1175/bams-d-18-0195.1 OpenAlex:W2969309273
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.