Catalysis Club of Chicago

Member-North American Catalysis Society

Applications of Machine Learned Potentials in Surface Science, Catalysis and Materials

Prof. John Kitchin

Monday, January 14, 2019

Nonna Silvia’s Restaurant
1400 Canfield Road
Park Ridge, IL 6006

Professor John Kitchin 
Department of Chemical Engineering
Carnegie Mellon University
Pittsburgh, PA 15213

Abstract

Density functional theory has been a standard tool in computational surface science, catalysis and materials. Advances in algorithms and computing power continue to increase the complexity and size of systems that can be modeled. There remain many kinds of simulations, however, where DFT is not fast enough to be practical. In Monte Carlo and molecular dynamic simulations, DFT remains too slow to use practically for many systems. Molecular potentials are often used in these applications, but these typically lack the accuracy of DFT, can be difficult to improve and/or validate, have limited utility, and they are difficult to systematically improve. We will discuss the creation, use, and limitations of Behler-Parinello neural networks (BPNN) for these applications. We will also present a brief review of how others are using these approaches to solve problems that were previously inaccessible, along with opportunities and challenges to the approach.