Joint Session 37 Physical Interpretability in Machine Learning

Wednesday, 15 January 2020: 8:30 AM-10:00 AM
260 (Boston Convention and Exhibition Center)

Cochairs:
Elizabeth Satterfield, NRL, Monterey, CA and Philippe Tissot, Texas A&M University - Corpus Christi, Conrad Blucher Institute, Corpus Christi, TX

Description:

Physical interpretability in machine learning


Papers:
8:30 AM
J37.1
Multi-resolution Cluster Analysis - Addressing Trust in Climate Classification
Derek DeSantis, LANL, Los Alamos, NM; and P. Wolfram and B. Alexandrov

8:45 AM
J37.2
Understanding What Deep Learning Has Learned About Tornadoes
Ryan A. Lagerquist, CIMMS, Norman, OK; and A. McGovern, D. J. Gagne II, C. R. Homeyer, and T. M. Smith

9:00 AM
J37.3
Selected Methods from Explainable AI to Improve Understanding of Neural Network Reasoning for Environmental Science Applications
Imme Ebert-Uphoff, CIRA - Colorado State University, Fort Collins, CO; and K. Hilburn, B. A. Toms, and E. A. Barnes

9:15 AM
J37.4
Emulation of Bin Microphysical Processes with Machine Learning
David John Gagne II, NCAR, Boulder, CO; and C. C. Chen and A. Gettelman

9:30 AM
J37.6
Lessons Learned Using ML For Knowledge Discovery In the Atmospheric Sciences
Amy McGovern, University of Oklahoma, Norman, OK

Abstract Submissions Closed



See more of: 26th Conference on Probability and Statistics
<< Previous Session | Next Session >>