[Eoas-seminar] Reminder: EOAS Colloquium today at 3pm: online

[eoas-seminar at lists.fsu.edu]

This week's EOAS Colloquium will be held online today at 3pm. We will NOT use Room 1050 to avoid any potential technical problems, especially during the Q/A period.

Title: Machine Learning In Earth System Modeling

Speaker: Dr. Dan Lu, Oak Ridge National Laboratory, Oak Ridge, TN

Abstract:
Predictions of the Earth system have significant societal impacts, and they are one of the main goals of understanding the Earth system across scales. However, Earth system prediction is challenging. The observing system sees only part of the Earth, so the Earth system model is required to fill out the space, time, and spectral regions not covered by observations. Earth system models have substantially changed over time, from empirical model, to theoretical model, to computational model, and now are moving to data-driven machine learning (ML) model. This talk presents four ML methods to advance the Earth system modeling. Specifically, we developed a surrogate modeling technique and an inversion-free prediction framework to reduce computational costs in the physics-based Earth system model prediction, and developed an interpretable ML model with uncertainty quantification for trustworthy data-driven Earth system model prediction. The applications of these methods cover terrestrial ecosystem model, hydrological model, and geological carbon storage.

Bio: Dan Lu is a staff scientist at Oak Ridge National Laboratory (ORNL). She earned her Ph.D. in Computational Hydrology at Florida State University in 2012. Dan has broad research interests including: Machine Learning (ML), Uncertainty Quantification (UQ), and Numerical Simulations in Earth, Climate and Environment Sciences. Dan is co-leading the Artificial Intelligence (AI) Initiative, which is a $25 million project for 5 years, and is in the leadership team of Climate Change Science Institute at ORNL. She is the PI of a UQ for ML project, the PI of a Hydropower project, and the PI of a Geological Carbon Storage project. Dan authored about 60 publications and co-developed two software. She has been actively involved in AGU Groundwater Technical Committee, NeurIPS Climate Change AI Program Committee and organized several workshops on AI for Robust Engineering and Science. Dan is currently serving as an Associate Editor of the journal Artificial Intelligence for the Earth Systems, an Associate Editor of the journal Frontiers in Water, and a Topic Editor of the journal Geoscientific Model Development. Her work has been recognized by several ORNL News and she obtained the Distinguished Scientific Achievement Award in ORNL last year.

--
Ming Ye, Ph.D.
Professor in Hydrogeology
Department of Earth, Ocean, and Atmospheric Science
Department of Scientific Computing
Florida State University
Tallahassee, FL 32306-4520
Office: 3015 EOAS Building (1011 Academic Way)
Phone: 850-645-4987
Cell: 850-567-4488
Email: mye at fsu.edu<mailto:mye at fsu.edu>
http://earth.eoas.fsu.edu/~mye/<https://urldefense.proofpoint.com/v2/url?u=http-3A__earth.eoas.fsu.edu_-7Emye_&d=DwMD-g&c=sJ6xIWYx-zLMB3EPkvcnVg&r=Mhyd37dJicOv2Y4TdrFHog&m=M6HuCNdoexq-OmjpdYhuF9nJRk-CZjJK4J9E8OiYagE&s=Zw0EKGXRi_xmXoT5hozL7qQqQGvB5xxO4xHJB-s1icA&e=>

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.fsu.edu/pipermail/eoas-seminar/attachments/20230203/a9a1d389/attachment.html>
-------------- next part --------------
_______________________________________________
Eoas-seminar mailing list
Eoas-seminar at lists.fsu.edu
https://lists.fsu.edu/mailman/listinfo/eoas-seminar