DI&A Van Tuyl Lecture, March 11, 2024, Berthoud 243, 12-1pm

Leigh Stearns, University of Kansas

Lots of Data, No Diversity: Exploring Machine Learning Algorithms and Strategies to Build Community in Glaciology

Abstract: As the cryosphere undergoes unprecedented changes due to global warming, artificial intelligence has emerged as a powerful tool in advancing research, monitoring, and risk mitigation. With conventional methodology, it is particularly challenging to detect small (temporal or spatial) scale changes over large areas. Computer vision and deep learning algorithms become indispensable for tasks such as systematically identifying calving events for all glaciers around Greenland or tracking icebergs in the Arctic Ocean. Similarly, time series prediction and clustering approaches can improve quantification of individual glaciers’ contribution to sea level rise. Harnessing the power of artificial intelligence algorithms is essential for effectively utilizing these vast observations to mitigate climate risks.

On the other side of the spectrum there is very little data, or progress, on improving diversity within cryosphere research. Because climate change acutely impacts communities that are either not consulted or excluded from key decisions, our lack of diversity limits our ability to build a workforce of future educators and researchers necessary to address local to global challenges of climate change.

In this talk I provide examples of how I currently use machine learning to better quantify and predict changes in the cryosphere. Additionally, I outline some strategies and goals for building an inclusive cryosphere community.

This lecture is scheduled in a hybrid format. If you would like to join the meeting please:

Join from PC, Mac, Linux, iOS or Android: https://mines.zoom.us/j/94670886697?pwd=bWRxTTRwcGRrdFdOTWNLWE5wbmhNdz09
Meeting ID: 946 7088 6697
Password: 288065

Food/ Refreshments will be served.