Artificial Intelligence

AI in the paleogeosciences: progress, challenges, and opportunities

When:
Friday, July 17, 2020, 11:00am - 12:00pm PDTiCal
Where:
Virtually via Zoom
This event is open to the public.
Type:
AI Seminar
Speaker:
Deborah Khider, USC/ISI
Video:
https://youtu.be/xNDZmxDfNSg
Description:

Abstract: “The past is the key to the future.” In a seminal paper from the 1980’s, Bruce Doe recognized the importance of the then emergent field of paleoclimatology to decisions federal agencies would have to make in the face of rising greenhouse gases concentrations. The promise of paleoclimatology is two-folds: (1) to assess the current climate change in the context of climate variations across the decades and centuries, and (2) to validate climate model outputs. But it wasn’t until recently, with advances in geoinformatics, that paleoclimatology could fully fulfill its promises.

In this talk, I will walk through examples of how advances in artificial intelligence have benefited the paleogeosciences, and in particular paleoclimatology. In the first part of this talk, I will demonstrate (1) how knowledge representation has helped with the day-to-day work of paleoclimatologists by broadening access to data and to automated cutting-edge data analytic tools and (2) how deep learning techniques represent a yet untapped opportunity for paleoclimate datasets to be used in weather forecasting (“a machine can learn from the past to predict the future”).

In the last part of this talk, I will elaborate on how (paleo)climate scientists share their work on social media platforms and the feedback they receive in a time of rising anti-science sentiment.

Bio: Deborah Khider is a Data Scientist at the Information Sciences Institute. Her research interests involve (paleo)climate informatics. She received a PhD in Ocean Sciences from the University of Southern California. Prior to joining ISI, she held postdoctoral appointments at the University of Texas at Austin, the University of California Santa Barbara, and the University of Southern California. Her work focused on paleoclimate time series analysis and uncertainty quantification. She is currently involved in several projects for representing and capturing metadata for (paleo)geoscience data and model as well automating workflows in this domain.

« Return to Events