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:
-
- Stanford Univ., CA (United States); SLAC National Accelerator Lab., Menlo Park, CA (United States)
- 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 Laboratory (SLAC), Menlo Park, CA (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC), Basic Energy Sciences (BES)
- 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. https://doi.org/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. https://doi.org/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 = {Sat Mar 16 00:00:00 EDT 2019},
month = {Sat Mar 16 00:00:00 EDT 2019}
}
Web of Science
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
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
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
Addressing uncertainty in atomistic machine learning
journal, January 2017
- Peterson, Andrew A.; Christensen, Rune; Khorshidi, Alireza
- Physical Chemistry Chemical Physics, Vol. 19, Issue 18
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
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
Further considerations on the thermodynamics of chemical equilibria and reaction rates
journal, January 1936
- Evans, M. G.; Polanyi, M.
- Transactions of the Faraday Society, Vol. 32
Soft self-consistent pseudopotentials in a generalized eigenvalue formalism
journal, April 1990
- Vanderbilt, David
- Physical Review B, Vol. 41, Issue 11, p. 7892-7895
Stochastic Neural Network Approach for Learning High-Dimensional Free Energy Surfaces
journal, October 2017
- Schneider, Elia; Dai, Luke; Topper, Robert Q.
- Physical Review Letters, Vol. 119, Issue 15
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
Amp: A modular approach to machine learning in atomistic simulations
journal, October 2016
- Khorshidi, Alireza; Peterson, Andrew A.
- Computer Physics Communications, Vol. 207
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
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
Machine-Learning Methods Enable Exhaustive Searches for Active Bimetallic Facets and Reveal Active Site Motifs for CO 2 Reduction
journal, August 2017
- Ulissi, Zachary W.; Tang, Michael T.; Xiao, Jianping
- ACS Catalysis, Vol. 7, Issue 10
Toward computational screening in heterogeneous catalysis: Pareto-optimal methanation catalysts
journal, April 2006
- Andersson, M.; Bligaard, T.; Kustov, A.
- Journal of Catalysis, Vol. 239, Issue 2
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
Bypassing the Kohn-Sham equations with machine learning
journal, October 2017
- Brockherde, Felix; Vogt, Leslie; Li, Li
- Nature Communications, Vol. 8, Issue 1
Theoretical surface science and catalysis—calculations and concepts
book, January 2000
- Hammer, B.; Nørskov, J. K.
- Impact of Surface Science on Catalysis, p. 71-129
SISSO: A compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates
journal, August 2018
- Ouyang, Runhai; Curtarolo, Stefano; Ahmetcik, Emre
- Physical Review Materials, Vol. 2, Issue 8
Works referencing / citing this record:
Machine learning for the modeling of interfaces in energy storage and conversion materials
journal, July 2019
- Artrith, Nongnuch
- Journal of Physics: Energy, Vol. 1, Issue 3
Machine Learning in Catalysis, From Proposal to Practicing
journal, December 2019
- Yang, Wenhong; Fidelis, Timothy Tizhe; Sun, Wen-Hua
- ACS Omega, Vol. 5, Issue 1