Abstract
Machine learning is a rapidly evolving field in computer science with increasingly many applications to other domains. In this thesis, I present a Bayesian machine learning approach to solving a problem in theoretical surface science: calculating the preferred active site on a catalyst surface for a given adsorbate molecule. I formulate the problem as a low-dimensional objective function. I show how the objective function can be approximated into a certain confidence interval using just one iteration of the self-consistent field (SCF) loop in density functional theory (DFT). I then use Bayesian optimization to perform a global search for the solution. My approach outperforms the current state-of-the-art method, constrained minima hopping, for CO on ferric oxide by a factor of 75 to 1. This thesis is the first documented application of Bayesian optimization to surface science.
Committee Chair
Roman Garnett
Committee Members
Cynthia Lo Roman Garnett Michael Brent
Degree
Master of Science (MS)
Author's Department
Computer Science & Engineering
Document Type
Thesis
Date of Award
Winter 12-2015
Language
English (en)
DOI
https://doi.org/10.7936/K78C9TJ1
Author's ORCID
https://orcid.org/0000-0002-8953-6164
Recommended Citation
Carr, Shane, "Applying Bayesian Machine Learning Methods to Theoretical Surface Science" (2015). McKelvey School of Engineering Theses & Dissertations. 122.
The definitive version is available at https://doi.org/10.7936/K78C9TJ1
Included in
Applied Statistics Commons, Artificial Intelligence and Robotics Commons, Catalysis and Reaction Engineering Commons, Computational Engineering Commons, Materials Chemistry Commons
Comments
Permanent URL: https://doi.org/10.7936/K78C9TJ1