A Data-Driven Future for Atmospheric Chemistry, Wildfires, Climate, and Society

Explore the intersection of atmospheric chemistry, wildfires, climate change, and society in this 57-minute lecture by Makoto Kelp from Stanford University. Discover how machine learning and data-driven approaches are revolutionizing atmospheric modeling and air quality research. Learn about the development of stable, faster emulators for global atmospheric chemistry models, the optimal design of equitable air pollution sensor networks, and data-informed modeling of prescribed fires to mitigate megafire risks. Gain insights into how these advanced techniques are addressing environmental justice issues and enhancing our understanding of land-climate-human interactions, particularly in the context of increasing wildfires in the Western United States.