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

Title: Prediction of Adsorption Energies for Chemical Species on Metal Catalyst Surfaces Using Machine Learning

Abstract

Computational catalyst screening has the potential to significantly accelerate heterogeneous catalyst discovery. Typically, this involves developing microkinetic reactor models that are based on parameters obtained from density functional theory and transition-state theory. To reduce the large computational cost involved in computing various adsorption and transition-state energies of all possible surface states on a large number of catalyst models, linear scaling relations for surface intermediates and transition states have been developed that only depend on a few, typically one or two descriptors, such as the carbon atom adsorption energy. As a result, only the descriptor values have to be computed for various active site models to generate volcano curves in activity or selectivity. Unfortunately, for more complex chemistries the predictability of linear scaling relations is unknown. Also, the selection of descriptors is essentially a trial and error process. Here, using a database of adsorption energies of the surface species involved in the decarboxylation and decarbonylation of propionic acid over eight monometalic transition-metal catalyst surfaces (Ni, Pt, Pd, Ru, Rh, Re, Cu, Ag), we tested if nonlinear machine learning (ML) models can outperform the linear scaling relations in prediction accuracy when predicting the adsorption energy for various species on a metal surfacemore » based on data from the rest of the metal surfaces. We found linear scaling relations to hold well for predictions across metals with a mean-absolute error of 0.12 eV, and ML methods being unable to outperform linear scaling relations when the training dataset contains a complete set of energies for all of the species on various metal surfaces. Only when the training dataset is incomplete, namely, contains a random subset of species’ energies for each metal, a currently unlikely scenario for catalyst screening, do kernel-based ML models significantly outperform linear scaling relations. We also found that simple coordinate-free species descriptors, such as bond counts, achieve as good results as sophisticated coordinate-based descriptors. Finally, we propose an approach for automatic discovery of appropriate metal descriptors using principal component analysis.« less

Authors:
; ; ; ; ORCiD logo;  [1]
  1. Department of Computer Science, University of North Carolina Charlotte, Charlotte, North Carolina 28223, United States
Publication Date:
Research Org.:
Univ. of South Carolina, Columbia, SC (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Basic Energy Sciences (BES) (SC-22); National Science Foundation (NSF)
OSTI Identifier:
1484052
Alternate Identifier(s):
OSTI ID: 1508777
Grant/Contract Number:  
SC0007167; AC02-05CH11231; DMREF-1534260; TG-CTS090100
Resource Type:
Journal Article: Published Article
Journal Name:
Journal of Physical Chemistry. C
Additional Journal Information:
Journal Name: Journal of Physical Chemistry. C Journal Volume: 122 Journal Issue: 49; Journal ID: ISSN 1932-7447
Publisher:
American Chemical Society
Country of Publication:
United States
Language:
English
Subject:
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY

Citation Formats

Chowdhury, Asif J., Yang, Wenqiang, Walker, Eric, Mamun, Osman, Heyden, Andreas, and Terejanu, Gabriel A. Prediction of Adsorption Energies for Chemical Species on Metal Catalyst Surfaces Using Machine Learning. United States: N. p., 2018. Web. doi:10.1021/acs.jpcc.8b09284.
Chowdhury, Asif J., Yang, Wenqiang, Walker, Eric, Mamun, Osman, Heyden, Andreas, & Terejanu, Gabriel A. Prediction of Adsorption Energies for Chemical Species on Metal Catalyst Surfaces Using Machine Learning. United States. doi:10.1021/acs.jpcc.8b09284.
Chowdhury, Asif J., Yang, Wenqiang, Walker, Eric, Mamun, Osman, Heyden, Andreas, and Terejanu, Gabriel A. Fri . "Prediction of Adsorption Energies for Chemical Species on Metal Catalyst Surfaces Using Machine Learning". United States. doi:10.1021/acs.jpcc.8b09284.
@article{osti_1484052,
title = {Prediction of Adsorption Energies for Chemical Species on Metal Catalyst Surfaces Using Machine Learning},
author = {Chowdhury, Asif J. and Yang, Wenqiang and Walker, Eric and Mamun, Osman and Heyden, Andreas and Terejanu, Gabriel A.},
abstractNote = {Computational catalyst screening has the potential to significantly accelerate heterogeneous catalyst discovery. Typically, this involves developing microkinetic reactor models that are based on parameters obtained from density functional theory and transition-state theory. To reduce the large computational cost involved in computing various adsorption and transition-state energies of all possible surface states on a large number of catalyst models, linear scaling relations for surface intermediates and transition states have been developed that only depend on a few, typically one or two descriptors, such as the carbon atom adsorption energy. As a result, only the descriptor values have to be computed for various active site models to generate volcano curves in activity or selectivity. Unfortunately, for more complex chemistries the predictability of linear scaling relations is unknown. Also, the selection of descriptors is essentially a trial and error process. Here, using a database of adsorption energies of the surface species involved in the decarboxylation and decarbonylation of propionic acid over eight monometalic transition-metal catalyst surfaces (Ni, Pt, Pd, Ru, Rh, Re, Cu, Ag), we tested if nonlinear machine learning (ML) models can outperform the linear scaling relations in prediction accuracy when predicting the adsorption energy for various species on a metal surface based on data from the rest of the metal surfaces. We found linear scaling relations to hold well for predictions across metals with a mean-absolute error of 0.12 eV, and ML methods being unable to outperform linear scaling relations when the training dataset contains a complete set of energies for all of the species on various metal surfaces. Only when the training dataset is incomplete, namely, contains a random subset of species’ energies for each metal, a currently unlikely scenario for catalyst screening, do kernel-based ML models significantly outperform linear scaling relations. We also found that simple coordinate-free species descriptors, such as bond counts, achieve as good results as sophisticated coordinate-based descriptors. Finally, we propose an approach for automatic discovery of appropriate metal descriptors using principal component analysis.},
doi = {10.1021/acs.jpcc.8b09284},
journal = {Journal of Physical Chemistry. C},
issn = {1932-7447},
number = 49,
volume = 122,
place = {United States},
year = {2018},
month = {11}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record at 10.1021/acs.jpcc.8b09284

Citation Metrics:
Cited by: 9 works
Citation information provided by
Web of Science

Figures / Tables:

Figure 1. Figure 1.: Reaction network for the decarboxylation and decarbonylation of propionic acid. The larger species among the metal descriptors (CHCHCO) is marked on the figure. The other descriptor (OH), along with COOH, CO2, CO, H2O, and H, is not included in the figure for clarity.

Save / Share:
Figures/Tables have been extracted from DOE-funded journal article accepted manuscripts.