Visionary Talk Series
Facebook Labs and University of Washington, USA.
Nonlinear model reduction: Using AI to enable rapid simulation of extreme-scale physics models
Abstract: Physics-based modeling and simulation has become indispensable across many applications in science and engineering, ranging from autonomous-vehicle control to designing new materials. However, achieving high predictive fidelity necessitates modeling fine spatiotemporal resolution, which can lead to extreme-scale computational models whose simulations consume months on thousands of computing cores. This constitutes a formidable computational barrier: the cost of truly high-fidelity simulations renders them impractical for important time-critical applications (e.g., rapid design, control, real-time simulation) in engineering and science. In this talk, I will present several advances in the field of nonlinear model reduction that leverage AI techniques ranging from convolutional autoencoders to LSTM networks to overcome this barrier. In particular, these methods produce low-dimensional counterparts to high-fidelity models called reduced-order models (ROMs) that exhibit 1) accuracy, 2) low cost, 3) physical-property preservation, 4) guaranteed generalization performance, and 5) error quantification.
Bio: Kevin Carlberg is an AI Research Science Manager Facebook Reality Labs and an Affiliate Associate Professor of Applied Mathematics and Mechanical Engineering at the University of Washington. He leads a research team focused on enabling the future of augmented and virtual reality through AI-driven innovations. His individual research combines concepts from machine learning, computational physics, and high-performance computing to drastically reduce the cost of simulating nonlinear dynamical systems at extreme scale. Previously, Kevin was a Distinguished Member of Technical Staff at Sandia National Laboratories in Livermore, California, where he led a research group of PhD students, postdocs, and technical staff in applying these techniques to a range of national-security applications in mechanical and aerospace engineering.