Title: “Machine Learning-Based Detection of Precipitation Extremes and Regional Climate Impacts”

Speaker: Katie Dagon (NSF NCAR)

Format: Hybrid

Virtual: Zoom link provided upon registration

Katie will present remotely, but attendees are welcome to gather and watch together at the Columbia Engineering Innovation Hub.

*Please note that in-person space is limited.*

__________________________________________________________________________________

Abstract: Extreme precipitation events have wide-ranging impacts on humans and the environment. Machine learning-based detection algorithms can help with the automated classification of the synoptic-scale weather features that produce extreme precipitation events, such as fronts and atmospheric rivers (ARs). Here we use a suite of deep learning algorithms to identify weather fronts and ARs in high-resolution Community Earth System Model (CESM) simulations and evaluate the results using observational and reanalysis products. To study how these features might change with climate change, we compare results between CESM simulations using present-day and future climate forcing. We further investigate regional climate impacts, such as precipitation associated with fronts and ARs over the United States. We find that detected synoptic events in CESM have seasonally varying spatial patterns and responses to climate change and are found to be associated with modeled changes in large-scale circulation.

Bio: Katie Dagon is a climate scientist at the NSF National Center for Atmospheric Research in Boulder, Colorado. Her research focuses on modeling the impacts of climate change on land-atmosphere interactions, climate variability, and extreme events. She is also interested in machine learning approaches to climate science and modeling. She received her Ph.D. in Earth and Planetary Sciences from Harvard University and her B.S. in Mathematics-Physics from Brown University.

Time: 12:30-1:30 pm EST

Free!

Registration