Machine Learning can Produce Actual Learning
The next presentation in the Distinguished Lecture Series in Energy, featuring Dr. Michael Baldea, the holder of the Henry Beckman Professorship in Chemical Engineering at The University of Texas at Austin, will be held on Wednesday, March 27, 2024, from 11:00 a.m. – 12:00 p.m. CDT (UTC -5:00) in the Frederick E. Giesecke Engineering Research Building (GERB) Third Floor Conference Room and through a Zoom Meeting. The topic will be “Machine Learning can Produce Actual Learning.”
Abstract
Explainable artificial intelligence has received significant attention in the recent past. Central to this effort is directing machine learning algorithms to obtain fundamental physical insights from large amounts of experimental data. In this talk, we present a novel class of algorithms inspired by control theory (in particular, dynamic optimization and moving horizon estimation) for learning the governing equations of physical and chemical reaction systems. Our framework addresses inherent limitations of existing tools based on sparse regression, is scalable and robust to noisy data. Examples of learning the dynamics of canonical dynamical systems will be presented, and novel application to learning and reduction of the mechanisms of chemical reactions will be discussed.
Biography
Michael Baldea is the Henry Beckman Professor in the McKetta Department of Chemical Engineering, and a core faculty member in the Oden Institute for Computational Engineering and Sciences (ICES) at The University of Texas at Austin. He obtained his Diploma and M.Sc. in Chemical Engineering from “Babes-Bolyai” University in Cluj-Napoca, Romania, and a doctorate in Chemical Engineering from the University of Minnesota. Prior to joining The University of Texas, he held an industrial research position with Praxair (now Linde) Technology Center in Tonawanda, NY. He has received several research and service awards, including the AIChE Institute Award for Excellence in Industrial Gases Technology, the Outstanding Young Researcher Award from the Computing and Systems Technology Division of AIChE, the NSF CAREER award, the Moncrief Grand Challenges Award, the ACS Doctoral New Investigator award, and the Model-Based Innovation Prize from Process Systems Enterprise (twice). He was also recognized with referee awards by the Journal of Process Control and Industrial & Engineering Chemistry Research. His research interests include the dynamics, optimization and control of process and energy systems, areas in which he has published three books and over 200 peer-reviewed journal and conference articles. Dr. Baldea served on the advisory boards of several commercial and non-profit entities, and is Executive Editor for Industrial & Engineering Chemistry Research.