Accelerating Scientific Discovery with Machine Learning and AI

Richard Miller Family Endowed Mathematics Lecture Series

A major challenge in the study of science and engineering systems is that of model discovery: turning data into dynamical models that are not just predictive but provide insight into the nature of the underlying physics and dynamics that generated the data. This lecture will introduce data-driven strategies for discovering nonlinear multiscale dynamical systems and their embeddings from data. Neural networks are used in targeted ways to aid in the model reduction process. These approaches provide a suite of mathematical strategies for reducing the data required to discover and model unknown phenomena, giving a robust paradigm for modern AI-aided learning of physics and engineering principles.

J. Nathan Kutz is the Boeing Professor of AI and Data-Driven Engineering in the Department of Applied Mathematics and Electrical and Computer Engineering at the University of Washington. Professor Kutz is also the director of the university’s AI Institute in Dynamic Systems. His bachelor’s degree in physics and mathematics is from the University of Washington and his doctorate in applied mathematics is from Northwestern University. Professor Kutz’s interests include neuroscience and fluid dynamics, where he integrates machine learning with dynamical systems and control.

This lecture recording can be found on the Available Recordings page approximately two business days after the event and will remain accessible for three weeks.