IG3IS Webinar series 2026: Vulcan-UrbanML: A Machine-Learning-Based Global Urban Fossil Fuel CO2 Emissions Dataset and Its Implications for the Global Urban Emissions Share

Dr. Kevin Gurney, Northern Arizona University, USA

Kevin Gurney is an Atmospheric Scientist, Ecologist and Policy expert currently working in the areas of carbon cycle science, climate science, and climate science policy at Northern Arizona University where he is a Professor in the School of Informatics, Computing, and Cyber Systems. He has degrees from UC Berkeley, MIT, and Colorado State University. Gurney’s current research involves characterizing fossil fuel CO2 emissions at the global, national, and urban scales. Gurney is an IPCC lead author, an NSF CAREER award recipient, Sigma Xi Young Scientist recipient, a Fulbright scholar and has published over 190 peer-reviewed scientific articles.

In this webinar, participants will be introduced to Vulcan-UrbanML, a new machine learning-based global dataset that provides estimates of annual city-scale fossil fuel CO₂ (FFCO₂) emissions for the period from 2010 to 2022. This dataset was developed using the atmospherically validated U.S. Vulcan emissions inventory and expanded globally through region-specific training analogs. It offers a novel and consistent method for estimating urban emissions worldwide. The presentation will explore how urban emissions vary based on different geographic boundary definitions and will compare territorial emissions estimates with consumption-based accounting approaches. Participants will gain insights into the strengths and limitations of this new dataset, including its policy relevance. There will also be comparisons with self-reported city inventories and other global emissions products.