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

Title: Predicting Chemical Reaction Barriers with a Machine Learning Model

Abstract

In the past few decades, tremendous advances have been made in the understanding of catalysis at solid surfaces. Despite this, most discoveries of materials for improved catalytic performance are made by a slow trial and error process in an experimental laboratory. Computational simulations have begun to provide a way to rationally design materials for optimizing catalytic performance, but due to the high computational expense of calculating transition state energies, simulations cannot adequately screen the phase space of materials. In this work, we attempt to mitigate this expense by using a machine learning approach to predict the most expensive and most important parameter in a catalyst’s affinity for a reaction: the reaction barrier. Previous methods which used the step reaction energy as the only parameter in a linear regression had a mean absolute error (MAE) on the order of 0.4 eV, too high to be used predictively. Here in our work, we achieve a MAE of about 0.22 eV, a marked improvement towards the goal of computational prediction of catalytic activity.

Authors:
 [1];  [1];  [1];  [2]
  1. Stanford Univ., CA (United States); SLAC National Accelerator Lab., Menlo Park, CA (United States)
  2. Stanford Univ., CA (United States); SLAC National Accelerator Lab., Menlo Park, CA (United States); Technical Univ. of Denmark, Lyngby (Denmark)
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:
1546783
Grant/Contract Number:  
AC02-76SF00515
Resource Type:
Accepted Manuscript
Journal Name:
Catalysis Letters
Additional Journal Information:
Journal Volume: 149; Journal Issue: 9; Journal ID: ISSN 1011-372X
Publisher:
Springer
Country of Publication:
United States
Language:
English
Subject:
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY

Citation Formats

Singh, Aayush R., Rohr, Brian A., Gauthier, Joseph A., and Nørskov, Jens K. Predicting Chemical Reaction Barriers with a Machine Learning Model. United States: N. p., 2019. Web. doi:10.1007/s10562-019-02705-x.
Singh, Aayush R., Rohr, Brian A., Gauthier, Joseph A., & Nørskov, Jens K. Predicting Chemical Reaction Barriers with a Machine Learning Model. United States. doi:10.1007/s10562-019-02705-x.
Singh, Aayush R., Rohr, Brian A., Gauthier, Joseph A., and Nørskov, Jens K. Sat . "Predicting Chemical Reaction Barriers with a Machine Learning Model". United States. doi:10.1007/s10562-019-02705-x. https://www.osti.gov/servlets/purl/1546783.
@article{osti_1546783,
title = {Predicting Chemical Reaction Barriers with a Machine Learning Model},
author = {Singh, Aayush R. and Rohr, Brian A. and Gauthier, Joseph A. and Nørskov, Jens K.},
abstractNote = {In the past few decades, tremendous advances have been made in the understanding of catalysis at solid surfaces. Despite this, most discoveries of materials for improved catalytic performance are made by a slow trial and error process in an experimental laboratory. Computational simulations have begun to provide a way to rationally design materials for optimizing catalytic performance, but due to the high computational expense of calculating transition state energies, simulations cannot adequately screen the phase space of materials. In this work, we attempt to mitigate this expense by using a machine learning approach to predict the most expensive and most important parameter in a catalyst’s affinity for a reaction: the reaction barrier. Previous methods which used the step reaction energy as the only parameter in a linear regression had a mean absolute error (MAE) on the order of 0.4 eV, too high to be used predictively. Here in our work, we achieve a MAE of about 0.22 eV, a marked improvement towards the goal of computational prediction of catalytic activity.},
doi = {10.1007/s10562-019-02705-x},
journal = {Catalysis Letters},
number = 9,
volume = 149,
place = {United States},
year = {2019},
month = {3}
}

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

Citation Metrics:
Cited by: 2 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Universal transition state scaling relations for (de)hydrogenation over transition metals
journal, January 2011

  • Wang, S.; Petzold, V.; Tripkovic, V.
  • Physical Chemistry Chemical Physics, Vol. 13, Issue 46
  • DOI: 10.1039/c1cp20547a

Automated Discovery and Construction of Surface Phase Diagrams Using Machine Learning
journal, September 2016

  • Ulissi, Zachary W.; Singh, Aayush R.; Tsai, Charlie
  • The Journal of Physical Chemistry Letters, Vol. 7, Issue 19
  • DOI: 10.1021/acs.jpclett.6b01254

Machine-Learning-Augmented Chemisorption Model for CO 2 Electroreduction Catalyst Screening
journal, August 2015

  • Ma, Xianfeng; Li, Zheng; Achenie, Luke E. K.
  • The Journal of Physical Chemistry Letters, Vol. 6, Issue 18
  • DOI: 10.1021/acs.jpclett.5b01660

Addressing uncertainty in atomistic machine learning
journal, January 2017

  • Peterson, Andrew A.; Christensen, Rune; Khorshidi, Alireza
  • Physical Chemistry Chemical Physics, Vol. 19, Issue 18
  • DOI: 10.1039/C7CP00375G

Machine learning-based screening of complex molecules for polymer solar cells
journal, June 2018

  • Jørgensen, Peter Bjørn; Mesta, Murat; Shil, Suranjan
  • The Journal of Chemical Physics, Vol. 148, Issue 24
  • DOI: 10.1063/1.5023563

Assessment and Validation of Machine Learning Methods for Predicting Molecular Atomization Energies
journal, July 2013

  • Hansen, Katja; Montavon, Grégoire; Biegler, Franziska
  • Journal of Chemical Theory and Computation, Vol. 9, Issue 8
  • DOI: 10.1021/ct400195d

Soft self-consistent pseudopotentials in a generalized eigenvalue formalism
journal, April 1990


A dimer method for finding saddle points on high dimensional potential surfaces using only first derivatives
journal, October 1999

  • Henkelman, Graeme; Jónsson, Hannes
  • The Journal of Chemical Physics, Vol. 111, Issue 15
  • DOI: 10.1063/1.480097

Amp: A modular approach to machine learning in atomistic simulations
journal, October 2016


A climbing image nudged elastic band method for finding saddle points and minimum energy paths
journal, December 2000

  • Henkelman, Graeme; Uberuaga, Blas P.; Jónsson, Hannes
  • The Journal of Chemical Physics, Vol. 113, Issue 22, p. 9901-9904
  • DOI: 10.1063/1.1329672

Improved tangent estimate in the nudged elastic band method for finding minimum energy paths and saddle points
journal, December 2000

  • Henkelman, Graeme; Jónsson, Hannes
  • The Journal of Chemical Physics, Vol. 113, Issue 22
  • DOI: 10.1063/1.1323224

Machine-Learning Methods Enable Exhaustive Searches for Active Bimetallic Facets and Reveal Active Site Motifs for CO 2 Reduction
journal, August 2017


Toward computational screening in heterogeneous catalysis: Pareto-optimal methanation catalysts
journal, April 2006


To address surface reaction network complexity using scaling relations machine learning and DFT calculations
journal, March 2017

  • Ulissi, Zachary W.; Medford, Andrew J.; Bligaard, Thomas
  • Nature Communications, Vol. 8, Issue 1
  • DOI: 10.1038/ncomms14621

Bypassing the Kohn-Sham equations with machine learning
journal, October 2017


Theoretical surface science and catalysis—calculations and concepts
book, January 2000


SISSO: A compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates
journal, August 2018