skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Automated discovery and construction of surface phase diagrams using machine learning

Abstract

Surface phase diagrams are necessary for understanding surface chemistry in electrochemical catalysis, where a range of adsorbates and coverages exist at varying applied potentials. These diagrams are typically constructed using intuition, which risks missing complex coverages and configurations at potentials of interest. More accurate cluster expansion methods are often difficult to implement quickly for new surfaces. We adopt a machine learning approach to rectify both issues. Using a Gaussian process regression model, the free energy of all possible adsorbate coverages for surfaces is predicted for a finite number of adsorption sites. Our result demonstrates a rational, simple, and systematic approach for generating accurate free-energy diagrams with reduced computational resources. Finally, the Pourbaix diagram for the IrO 2(110) surface (with nine coverages from fully hydrogenated to fully oxygenated surfaces) is reconstructed using just 20 electronic structure relaxations, compared to approximately 90 using typical search methods. Similar efficiency is demonstrated for the MoS 2 surface.

Authors:
 [1];  [1];  [1];  [1]
  1. Stanford Univ., Stanford, CA (United States); SLAC National Accelerator Lab., Menlo Park, CA (United States)
Publication Date:
Research Org.:
SLAC National Accelerator Lab., Menlo Park, CA (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Basic Energy Sciences (BES) (SC-22)
OSTI Identifier:
1350539
Grant/Contract Number:
AC02-76SF00515
Resource Type:
Journal Article: Accepted Manuscript
Journal Name:
Journal of Physical Chemistry Letters
Additional Journal Information:
Journal Volume: 7; Journal Issue: 19; Journal ID: ISSN 1948-7185
Publisher:
American Chemical Society
Country of Publication:
United States
Language:
English
Subject:
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY; 97 MATHEMATICS AND COMPUTING

Citation Formats

Ulissi, Zachary W., Singh, Aayush R., Tsai, Charlie, and Nørskov, Jens K. Automated discovery and construction of surface phase diagrams using machine learning. United States: N. p., 2016. Web. doi:10.1021/acs.jpclett.6b01254.
Ulissi, Zachary W., Singh, Aayush R., Tsai, Charlie, & Nørskov, Jens K. Automated discovery and construction of surface phase diagrams using machine learning. United States. doi:10.1021/acs.jpclett.6b01254.
Ulissi, Zachary W., Singh, Aayush R., Tsai, Charlie, and Nørskov, Jens K. Wed . "Automated discovery and construction of surface phase diagrams using machine learning". United States. doi:10.1021/acs.jpclett.6b01254. https://www.osti.gov/servlets/purl/1350539.
@article{osti_1350539,
title = {Automated discovery and construction of surface phase diagrams using machine learning},
author = {Ulissi, Zachary W. and Singh, Aayush R. and Tsai, Charlie and Nørskov, Jens K.},
abstractNote = {Surface phase diagrams are necessary for understanding surface chemistry in electrochemical catalysis, where a range of adsorbates and coverages exist at varying applied potentials. These diagrams are typically constructed using intuition, which risks missing complex coverages and configurations at potentials of interest. More accurate cluster expansion methods are often difficult to implement quickly for new surfaces. We adopt a machine learning approach to rectify both issues. Using a Gaussian process regression model, the free energy of all possible adsorbate coverages for surfaces is predicted for a finite number of adsorption sites. Our result demonstrates a rational, simple, and systematic approach for generating accurate free-energy diagrams with reduced computational resources. Finally, the Pourbaix diagram for the IrO2(110) surface (with nine coverages from fully hydrogenated to fully oxygenated surfaces) is reconstructed using just 20 electronic structure relaxations, compared to approximately 90 using typical search methods. Similar efficiency is demonstrated for the MoS2 surface.},
doi = {10.1021/acs.jpclett.6b01254},
journal = {Journal of Physical Chemistry Letters},
number = 19,
volume = 7,
place = {United States},
year = {Wed Aug 24 00:00:00 EDT 2016},
month = {Wed Aug 24 00:00:00 EDT 2016}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 3works
Citation information provided by
Web of Science

Save / Share: