AM Seminar: Data Driven Modeling for Scientific Discovery and Digital Twins

Presenter: Dongbin Xiu, Professor, Ohio State University

Description:We present a data-driven modeling framework for scientific discovery, termed Flow Map Learning (FML). This framework enables the construction of accurate predictive models for complex systems that are not amenable to traditional modeling approaches. By leveraging data and the expressiveness of deep neural networks (DNNs), FML facilitates long-term system modeling and prediction even when governing equations are unavailable. FML is particularly powerful in the context of Digital Twins, an emerging concept in digital transformation. With sufficient offline learning, FML enables the construction of simulation models for key quantities of interest (QoIs) in complex Digital Twins, when direct mathematical modeling of the QoIs is infeasible. During the online execution of a Digital Twin, the learned FML model can simulate the QoIs without reverting to the computationally intensive Digital Twin simulation model. As a result, FML serves as an enabling methodology for real-time control and optimization for complex systems.

Bio: Dongbin Xiu received his Ph.D degree from the Division of Applied Mathematics of Brown University in 2004. He joined the Department of Mathematics of Purdue University in 2005 and moved to the University of Utah in 2013. In 2016, He joined The Ohio State University as Professor of Mathematics and Ohio Eminent Scholar. He received NSF CAREER award in 2007 and was elected to SIAM Fellow in 2023. He is currently the Editor-in-Chief of the Journal of Computational Physics and the founding Editor-in-Chief of Journal of Machine Learning for Modeling and Computing (JMLMC). His current research focuses on developing efficient numerical methods for scientific machine learning, data driven discovery and digital twins.

Hosted by: Daniele Venturi, Applied Mathematics