Session 15B Explainable Artificial Intelligence (XAI) for Environmental Science II

Thursday, 1 February 2024: 1:45 PM-3:00 PM
338 (The Baltimore Convention Center)
Host: 23rd Conference on Artificial Intelligence for Environmental Science
Cochairs:
Christina E. Kumler, CIRA, Boulder, CO and Aaron J. Hill, Colorado State University, Atmospheric Science, Fort Collins, CO

This session invites abstracts on projects utilizing explainable artificial intelligence methods in their models and/or post processing applications. We particularly encourage abstracts that describe how the XAI methods impacted the final model development and analysis and/or were utilized with model users in mind.

Papers:
1:45 PM
15B.1
Assessing the Predictability of Downslope Windstorms in the Rocky Mountain Front Range Using Explainable Convolutional Neural Networks
Casey L Zoellick, M.S. in Atmospheric Sciences, Colorado State Univ., Fort Collins, CO; and R. S. Schumacher

2:00 PM
15B.2
Explaining the Role of Lightning Data in Hail Nowcasting
Jay Calder Rothenberger, Vaisala, Louisville, CO; National Science Foundation Trustworthy AI Institute for Weather Climate and Coastal Oceanography, Norman, OK; and E. P. Grimit, M. J. Murphy, and R. Wallace, PhD

2:15 PM
15B.3
Distinguishing the Regional Emergence of United States Summer Temperatures Between Observations and Climate Model Large Ensembles
Zachary Michael Labe, PhD, Princeton University, Princeton, NJ; and N. Johnson and T. L. Delworth

Handout (18.0 MB)

2:30 PM
15B.4
Comparing Predictor Influence for a Machine Learning Model in the Southwest United States for Three Different Excessive Rainfall Events
Jacob A Escobedo, Colorado State Univ., Fort Collins, CO; and R. S. Schumacher

2:45 PM
15B.5
Ingredients-Based Explainability: Using Tree Interpreter to Disaggregate a Random Forest's Severe Weather Predictions
Alexandra Mazurek, Colorado State Univ., Fort Collins, CO; and A. J. Hill, R. S. Schumacher, and H. J. McDaniel

Recorded Presentation
- Indicates paper has been withdrawn from meeting
- Indicates an Award Winner
See more of: 23rd Conference on Artificial Intelligence for Environmental Science
<< Previous Session | Next Session >>