Past Event: Oden Institute Seminar

Time-parallel wave propagation in heterogeneous media aided by deep learning

Richard Tsai, Professor, Department of Mathematics, and Core Faculty, Oden Institute, UT Austin

Abstract

We present a deep learning framework for learning multiscale wave propagation in heterogeneous media. The framework involves the construction of linear feed-forward networks (experts) that specialize in different media groups and a nonlinear "committee" network that gives an improved approximation of wave propagation in more complicated media. The framework is then applied to stabilize the "parareal" schemes of Lions, Maday, and Turinici, which are time-parallelization schemes for evolutionary problems. BIO Richard Tsai earned his Ph.D. in mathematics from the University of California, Los Angeles. He is a professor in mathematics, a member of the Oden Institute's Core Faculty, a member of the Oden Institute Graduate Studies Committee (GSC), and affiliated with the Oden Institute Center for Numerical Analysis. His current research interests include multiscale modeling and computation, inverse source problems, interface problems, robotic path planning problems involving visibility optimization, and image processing. His current works involve applications in crystal growth, porous media flow, seismic imaging, robotics, oscillatory mechanical systems, and endoscopic image analysis. He is a recipient of an Alfred Sloan Research Fellowship, a FEMLAB prize, and a 2018 Peter O’Donnell Distinguished Research Award. Note: Please join this Zoom seminar online with the "Audio Only" function (no video)