LANS Seminar

Seminar Title: Scientific Machine Learning for Computational Design and Management of Engineering Systems

Speaker: Dr. Hadi Meidani, Associate Professor, Department of Civil and Environmental Engineering, University of Illinois at Urbana-Champaign

Date/Time: May 22, 2024/ 10:30 AM-11:30 AM
Location: See Meeting URL on the cels-seminars website which will require an Argonne login.

Description: Advances in machine learning are revolutionizing the analysis, design and control of engineering systems, ranging from engineered materials to large-scale infrastructure networks. In this presentation, we first present our research on physics-informed neural networks (PINNs), and physics-informed neural operators. In particular, uncertainty quantification, improved training and generalizability of these methods will be focused. In the second part, we focus on graph neural networks and show how they can create a digital twin for large-scale infrastructure networks and serve as a computational decision support for robust and cost-effective management of these critical systems.

Bio: Dr. Hadi Meidani is an Associate Professor in the Department of Civil and Environmental Engineering at the University of Illinois at Urbana-Champaign. He earned his Ph.D. in Civil Engineering, his M.S. in Electrical Engineering and his M.S. in Structural Engineering from the University of Southern California (USC) in 2012. Prior to joining UIUC, he was a postdoctoral research associate in the School of Computing at the University of Utah in 2013-2014 and in the Department of Aerospace and Mechanical Engineering at USC in 2012-2013. He is the Founding Director of the Data Science M.S. Track in the CEE Department at UIUC. His research interests include uncertainty quantification, scientific machine learning, and computational methods for infrastructure engineering. He is the recipient of the NSF CAREER Award to study fast computational models for infrastructure networks.

Please note that the meeting URL for this event can be seen on the cels-seminars website which requires an Argonne login.