Session 12B Artificial Intelligence for Wildfire Forecasting and Management

Wednesday, 15 January 2025: 4:30 PM-6:00 PM
245 (New Orleans Ernest N. Morial Convention Center)
Host: 24th Conference on Artificial Intelligence for Environmental Science
Submitters:
Kyle A. Hilburn; Christina E. Kumler, CIRA, Boulder, CO and Tiago Quintino, ECMWF, Forecast Department, Reading
Cochairs:
John Cintineo, University of Wisconsin, SSEC/CIMSS, Madison, WI and Lena Heuscher

Research and applications on wildfire forecasting and management have become increasingly critical due to escalating climate change and variability. Wildfires pose severe threats to communities, economies, and ecosystems, resulting in extensive damage and presenting hard challenges for disaster response and resource management. Advanced tools and techniques are essential to improve our ability to predict, mitigate, and manage wildfire risks effectively. However, applications in wildfire forecasting often lack good training datasets, and artificial intelligence can be limited by the lack of interpretability. This session solicits applications of artificial intelligence to address the multi-disciplinary challenges in wildfire forecasting and management. Topics could include, but are not limited to, real-time wildfire forecasting and early warning systems, ignition modelling, monitoring and supression strategies, post-fire impact analysis and recovery, monitoring and sensor integration, etc.

Papers:
4:30 PM
12B.1
A Deep Learning Approach for Monitoring and Forecasting Fire Weather Conditions in Southern California
Charles Jones, Univ. of California, Santa Barbara, CA; and C. F. Thompson, D. M. Siuta, N. Quinn, and N. Sette

4:45 PM
12B.2
Toward Seasonal Lightning Outlooks for the Alaska Fire Season with a SOM-RF Model
Joshua Hostler, Univ. of Alaska Fairbanks, Fairbanks, AK; and U. S. Bhatt, P. A. Bieniek, T. J. Ballinger, C. Borries-Strigle, M. Burgard, E. Fischer, R. Lader, E. Stevens, H. Strader, R. Thoman, C. F. Waigl, and Z. Parish

5:15 PM
12B.4
Wildfire Ignition Prediction using Machine Learning
Sita Baaba Nyame, University of Connecticut, Storrs, CT; University of Connecticut, Storrs, CT; and W. O. Taylor, F. Yang, M. Koukoula, A. Spaulding, and D. Cerrai

5:30 PM
12B.5
5:45 PM
12B.6
An Approach to Reducing the Dimensionality of a Wildfire Machine Learning Application
Paul J. Roebber, Univ. of Wisconsin - Milwaukee, Milwaukee, WI

- Indicates paper has been withdrawn from meeting
- Indicates an Award Winner