Colloquium - Hadi Meidani, "Learning the Physical World: Neural Models for Data, Simulation, and Design"

Abstract: 
The physical world is rich in data and structure, yet our computational models often treat physics as a purely numerical process rather than an information system. This talk explores how advances in machine learning—particularly graph neural networks, neural operators, and generative models—can transform physical simulation and design into intelligent data-driven systems. We view physics-based models as query engines that map structured inputs such as geometry, materials, and boundary conditions to outputs like stress, flow, or other performance fields. By learning these mappings, neural models enable fast, generalizable surrogates for complex simulations and open new frontiers in design analytics. The talk highlights two threads of research: (1) fast physics simulation using neural operator and multifidelity graph architectures, and (2) graph-based modeling of infrastructure networks for resilience and risk-informed decision-making. Together, these directions illustrate how scientific computing can evolve toward scalable systems that organize, analyze, and generate knowledge about the physical world. 

Bio:
Hadi Meidani is an Associate Professor in the Department of Civil and Environmental Engineering at the University of Illinois at Urbana-Champaign (UIUC). His research focuses on uncertainty quantification, scientific machine learning, and fast surrogates for infrastructure and engineering design. He earned his Ph.D. in Civil Engineering, supervised by Prof. Roger Ghanem, his M.S. in Electrical Engineering, and his M.S. in Structural Engineering, all from the University of Southern California (USC). Prior to joining UIUC, he was a postdoctoral scholar in the Department of Aerospace and Mechanical Engineering at USC and in the Scientific Computing and Imaging Institute at the University of Utah. Dr. Meidani is the Chair of the Machine Learning Committee of the ASCE Engineering Mechanics Institute. At UIUC, he is the Founding Director of the AI in CEE M.S. Track and the Founding Chair of the Task Force on AI+CEE Professional Development Initiative, in the CEE Department. He is the recipient of an NSF CAREER Award on fast computational models for infrastructure networks.