Credit: Provided / Penn State. All Rights Reserved.

Institute for Computational and Data Sciences

Machine learning for materials science is focus of Feb. 14 AI seminar

4:00 PM - 5:00 PM / February 14, 2022

UNIVERSITY PARK, Pa. — Using machine learning to predict the properties of materials will be the focus of an upcoming Center for Artificial Intelligence Foundations and Scientific Applications (CENSAI) distinguished seminar. The event will be held online at 4 p.m. on Monday, Feb. 14.

Dane Morgan, the Harvey D. Spangler Professor of Engineering, University of Wisconsin-Madison, will present a lecture on his group’s work in the fields of machine learning and materials characterization.

Morgan’s group investigates ways that computational methods can help shed light on the properties of materials. A major focus of Morgan’s work is energy applications, including fuel cells, batteries and nuclear materials, but he also investigates areas such as thermionic emitters and defect properties in semiconductors. Morgan and his team use atomic scale modeling to understand and design new materials. They use many techniques, including supercomputing, to analyze up to hundreds of millions of atoms simultaneously.

The talk will highlight his group’s assessment of common Bayesian and ensemble methods for materials prediction. Morgan plans to discuss ways that automated deep learning can identify the location and size of defects in materials, which impact their properties, as well as share information about his group’s work on machine learning methods to improve simulations of interactions between molecules.

Morgan received three degrees in physics: a bachelor’s degree from Swarthmore College, and both a master’s and doctoral degree from the University of California, Berkeley. His research combines thermostatistics, thermokinetics and informatics analysis with atomic scale calculations to understand and predict materials properties.

Housed in the Institute for Computational and Data Sciences (ICDS), CENSAI enables Penn State researchers to explore the use of artificial intelligence as a tool to dramatically accelerate the scientific process.

View the abstract and speaker bio, or  register to attend the seminar.