NOTE: Due to tech issues, audio begins at 0:56, we apologize for the inconvenience.
Title: Learning physics-based models from data: Perspectives from projection-based model reduction
Speaker: Karen Willcox
Director, Oden Institute for Computational Engineering and Sciences
Associate Vice President for Research
Professor of Aerospace Engineering and Engineering Mechanics
University of Texas at Austin
Abstract: Reduced-order models play a critical role in achieving design, control and uncertainty quantification for complex systems. They are also a key enabling technology for predictive digital twins. Operator Inference is a method for learning predictive reduced-order models from data. The method targets the derivation of a reduced-order model of an expensive high-fidelity simulator that solves known governing equations. Rather than learn a generic approximation with weak enforcement of the physics, we learn low-dimensional operators of a dynamical system whose structure is defined by the physical problem being modeled. These reduced operators are determined by solving a linear least squares problem, making Operator Inference scalable to high-dimensional problems. The method is entirely non-intrusive, meaning that it requires simulation snapshot data but does not require access to or modification of the high-fidelity source code. The approach is demonstrated for large-scale engineering problems in rocket combustion, additive manufacturing and materials modeling.
![](https://s2.save4k.ru/pic/DKVngMjjKXY/maxresdefault.jpg)