Session: Explainable Artificial Intelligence (XAI) for Environmental Science I (104th AMS Annual Meeting)

Monday, 29 January 2024: 1:45 PM-3:00 PM

345/346 (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

3.1

Meteorological Interpretation of XAI Output Applied to a 3D Convolutional Neural Network Fog Prediction Model

Waylon G. Collins, NOAA/National Weather Service, Corpus Christi, TX; and E. Krell, P. E. Tissot, and S. A. King

2:00 PM

3.2

Identifying Data Sources and Physical Strategies Used By Neural Networks to Predict TC Rapid Intensification

Ryan A. Lagerquist, CIRA and NOAA/ESRL/GSL, Boulder, CO; and J. Knaff, C. Slocum, K. Musgrave, and I. Ebert-Uphoff

2:15 PM

3.3

Insights Gained from Explainable Artificial Intelligence for Convective Initiation Prediction