Predicting Chemical Reaction Barriers with a Machine Learning Model

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 beg...

Full description

Saved in:
Bibliographic Details
Published in:Catalysis letters Vol. 149; no. 9; pp. 2347 - 2354
Main Authors: Singh, Aayush R., Rohr, Brian A., Gauthier, Joseph A., Nørskov, Jens K.
Format: Journal Article
Language:English
Published: New York Springer US 01.09.2019
Springer
Springer Nature B.V
Subjects:
Catalysis
Catalytic activity
Chemical reactions
Chemistry
Chemistry and Materials Science
Computer simulation
Costs
Design optimization
Industrial Chemistry/Chemical Engineering
INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY
Machine learning
Organometallic Chemistry
Parameters
Physical Chemistry
Solid surfaces
Kinetic modeling
Density functional theory
Machine learning
ISSN:1011-372X, 1572-879X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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. In our work, we achieve a MAE of about 0.22 eV, a marked improvement towards the goal of computational prediction of catalytic activity. Graphical Abstract
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
USDOE Office of Science (SC), Basic Energy Sciences (BES)
AC02-76SF00515
ISSN:1011-372X
1572-879X
DOI:10.1007/s10562-019-02705-x