| Description | Speaker: Professor Elizabeth A. Barnes, Colorado State University (and Incoming Dalton Chair of Environmental Data Science and Professor of Computing & Data Sciences and Professor of Earth & Environment at Boston University)
Title: Explainable AI for Earth System Prediction: From Black Box to Window into the Future
Host: Eric Mei, emei@uw.edu, Sky Gale, skycgale@uw.edu Abstract: The coupled, complex nature of the Earth system makes it incredibly challenging to predict. Progress in this area requires integrating diverse approaches, from physics-based climate models to deep learning emulators. In this presentation, I will discuss our progress in developing and applying artificial intelligence (AI) tools to enhance Earth system prediction across time and space. These tools are designed to emulate scientific reasoning, improving intrinsic interpretability and predictive capabilities. I will demonstrate how integrating domain knowledge with AI methods and thoughtful model development can make these tools more transparent and useful to the scientists using them. About the Speaker: Dr. Elizabeth (Libby) Barnes is a leading expert in climate variability and climate change, specializing in subseasonal-to-decadal prediction and the innovative application of machine learning to climate science. Her groundbreaking work in “explainable” artificial intelligence (AI) has advanced the ability to identify the role of natural variability to reconcile discrepancies between observations and climate models. Dr. Barnes’s research exemplifies the integration of cutting-edge computational tools with fundamental climate science, driving new insights into the predictability and dynamics of Earth’s climate system. Dr. Barnes has been recognized by several awards, including the AGU James R. Holton Junior Scientist Award in 2014, the NSF CAREER Award in 2018, the AMS Clarence Leroy Meisinger Award in 2020, named an AGU Fellow in 2021, and the AGU James B. Macelwane Medal in 2021 for significant contributions to Earth and space sciences. She was recently awarded the Presidential Early Career Award for Scientists and Engineers (PECASE) for her interdisciplinary, impactful climate AI work. The University of Washington is committed to providing access and accommodation in its services, programs, and activities. To make a request connected to a disability or health condition contact Atmospheric and Climate Science, 206-543-4250, atmadmin@uw.edu, at least five days before the event. |
|---|