A Multiple Filter Based Neural Network Approach to the Extrapolation of Adsorption Energies on Metal Surfaces for Catalysis Applications
Abstract
Computational catalyst discovery involves the development of microkinetic reactor models based on estimated parameters determined from density functional theory (DFT). For complex surface chemistries, the number of reaction intermediates can be very large, and the cost of calculating the adsorption energies by DFT for all surface intermediates even for one active site model can become prohibitive. In this paper, we have identified appropriate descriptors and machine learning models that can be used to predict a significant part of these adsorption energies given data on the rest of them. Furthermore, our investigations also included the case when the species data used to train the predictive model are of different size relative to the species the model tries to predict—this is an extrapolation in the data space which is typically difficult with regular machine learning models. Due to the relative size of the available data sets, we have attempted to extrapolate from the larger species to the smaller ones in the current work. Here, we have developed a neural network based predictive model that combines an established additive atomic contribution based model with the concepts of a convolutional neural network that, when extrapolating, achieves a statistically significant improvement over the previous models.
- Authors:
-
[1];
- University of South Carolina, Columbia, SC (United States)
- University of North Carolina, Charlotte, NC (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); National Science Foundation (NSF); San Diego Supercomputer Center (SDSC) and Texas Advanced Computing Center (TACC)
- OSTI Identifier:
- 1656919
- Grant/Contract Number:
- SC0007167; DMREF-1534260; OIA-1632824; TG-CTS090; AC02-05CH11231100
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Journal of Chemical Theory and Computation
- Additional Journal Information:
- Journal Volume: 16; Journal Issue: 2; Journal ID: ISSN 1549-9618
- Publisher:
- American Chemical Society
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY; Energy; Neural networks; Molecular modeling; Adsorption; Molecules
Citation Formats
Chowdhury, Asif J., Yang, Wenqiang, Abdelfatah, Kareem E., Zare, Mehdi, Heyden, Andreas, and Terejanu, Gabriel A. A Multiple Filter Based Neural Network Approach to the Extrapolation of Adsorption Energies on Metal Surfaces for Catalysis Applications. United States: N. p., 2020.
Web. doi:10.1021/acs.jctc.9b00986.
Chowdhury, Asif J., Yang, Wenqiang, Abdelfatah, Kareem E., Zare, Mehdi, Heyden, Andreas, & Terejanu, Gabriel A. A Multiple Filter Based Neural Network Approach to the Extrapolation of Adsorption Energies on Metal Surfaces for Catalysis Applications. United States. https://doi.org/10.1021/acs.jctc.9b00986
Chowdhury, Asif J., Yang, Wenqiang, Abdelfatah, Kareem E., Zare, Mehdi, Heyden, Andreas, and Terejanu, Gabriel A. Tue .
"A Multiple Filter Based Neural Network Approach to the Extrapolation of Adsorption Energies on Metal Surfaces for Catalysis Applications". United States. https://doi.org/10.1021/acs.jctc.9b00986. https://www.osti.gov/servlets/purl/1656919.
@article{osti_1656919,
title = {A Multiple Filter Based Neural Network Approach to the Extrapolation of Adsorption Energies on Metal Surfaces for Catalysis Applications},
author = {Chowdhury, Asif J. and Yang, Wenqiang and Abdelfatah, Kareem E. and Zare, Mehdi and Heyden, Andreas and Terejanu, Gabriel A.},
abstractNote = {Computational catalyst discovery involves the development of microkinetic reactor models based on estimated parameters determined from density functional theory (DFT). For complex surface chemistries, the number of reaction intermediates can be very large, and the cost of calculating the adsorption energies by DFT for all surface intermediates even for one active site model can become prohibitive. In this paper, we have identified appropriate descriptors and machine learning models that can be used to predict a significant part of these adsorption energies given data on the rest of them. Furthermore, our investigations also included the case when the species data used to train the predictive model are of different size relative to the species the model tries to predict—this is an extrapolation in the data space which is typically difficult with regular machine learning models. Due to the relative size of the available data sets, we have attempted to extrapolate from the larger species to the smaller ones in the current work. Here, we have developed a neural network based predictive model that combines an established additive atomic contribution based model with the concepts of a convolutional neural network that, when extrapolating, achieves a statistically significant improvement over the previous models.},
doi = {10.1021/acs.jctc.9b00986},
journal = {Journal of Chemical Theory and Computation},
number = 2,
volume = 16,
place = {United States},
year = {Tue Jan 21 00:00:00 EST 2020},
month = {Tue Jan 21 00:00:00 EST 2020}
}
Free Publicly Available Full Text
Publisher's Version of Record
Other availability
Search WorldCat to find libraries that may hold this journal
Cited by: 15 works
Citation information provided by
Web of Science
Web of Science
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.
Works referenced in this record:
The role of computational results databases in accelerating the discovery of catalysts
journal, October 2018
- Bo, Carles; Maseras, Feliu; López, Núria
- Nature Catalysis, Vol. 1, Issue 11
Density functional theory in surface chemistry and catalysis
journal, January 2011
- Norskov, J. K.; Abild-Pedersen, F.; Studt, F.
- Proceedings of the National Academy of Sciences, Vol. 108, Issue 3
Linear scaling relationships and volcano plots in homogeneous catalysis – revisiting the Suzuki reaction
journal, January 2015
- Busch, Michael; Wodrich, Matthew D.; Corminboeuf, Clémence
- Chemical Science, Vol. 6, Issue 12
Scaling Properties of Adsorption Energies for Hydrogen-Containing Molecules on Transition-Metal Surfaces
journal, July 2007
- Abild-Pedersen, F.; Greeley, J.; Studt, F.
- Physical Review Letters, Vol. 99, Issue 1
Theoretical Heterogeneous Catalysis: Scaling Relationships and Computational Catalyst Design
journal, June 2016
- Greeley, Jeffrey
- Annual Review of Chemical and Biomolecular Engineering, Vol. 7, Issue 1
A theory of learning from different domains
journal, October 2009
- Ben-David, Shai; Blitzer, John; Crammer, Koby
- Machine Learning, Vol. 79, Issue 1-2
Microkinetic modeling of the decarboxylation and decarbonylation of propanoic acid over Pd(111) model surfaces based on parameters obtained from first principles
journal, September 2013
- Lu, Jianmin; Behtash, Sina; Faheem, Muhammad
- Journal of Catalysis, Vol. 305
Machine Learning Methods to Predict Density Functional Theory B3LYP Energies of HOMO and LUMO Orbitals
journal, December 2016
- Pereira, Florbela; Xiao, Kaixia; Latino, Diogo A. R. S.
- Journal of Chemical Information and Modeling, Vol. 57, Issue 1
Prediction of Adsorption Energies for Chemical Species on Metal Catalyst Surfaces Using Machine Learning
journal, November 2018
- Chowdhury, Asif J.; Yang, Wenqiang; Walker, Eric
- The Journal of Physical Chemistry C, Vol. 122, Issue 49
Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
journal, January 2012
- Rupp, Matthias; Tkatchenko, Alexandre; Müller, Klaus-Robert
- Physical Review Letters, Vol. 108, Issue 5
Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space
journal, June 2015
- Hansen, Katja; Biegler, Franziska; Ramakrishnan, Raghunathan
- The Journal of Physical Chemistry Letters, Vol. 6, Issue 12
Atom-centered symmetry functions for constructing high-dimensional neural network potentials
journal, February 2011
- Behler, Jörg
- The Journal of Chemical Physics, Vol. 134, Issue 7
A Density-Functional Theory-Based Neural Network Potential for Water Clusters Including van der Waals Corrections
journal, April 2013
- Morawietz, Tobias; Behler, Jörg
- The Journal of Physical Chemistry A, Vol. 117, Issue 32
Perspective: Machine learning potentials for atomistic simulations
journal, November 2016
- Behler, Jörg
- The Journal of Chemical Physics, Vol. 145, Issue 17
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
Extended-Connectivity Fingerprints
journal, April 2010
- Rogers, David; Hahn, Mathew
- Journal of Chemical Information and Modeling, Vol. 50, Issue 5
Machine learning in chemoinformatics and drug discovery
journal, August 2018
- Lo, Yu-Chen; Rensi, Stefano E.; Torng, Wen
- Drug Discovery Today, Vol. 23, Issue 8
Inverse molecular design using machine learning: Generative models for matter engineering
journal, July 2018
- Sanchez-Lengeling, Benjamin; Aspuru-Guzik, Alán
- Science, Vol. 361, Issue 6400
MoleculeNet: a benchmark for molecular machine learning
journal, January 2018
- Wu, Zhenqin; Ramsundar, Bharath; Feinberg, Evan N.
- Chemical Science, Vol. 9, Issue 2
Molecular graph convolutions: moving beyond fingerprints
journal, August 2016
- Kearnes, Steven; McCloskey, Kevin; Berndl, Marc
- Journal of Computer-Aided Molecular Design, Vol. 30, Issue 8
Machine Learning for Quantum Mechanical Properties of Atoms in Molecules
journal, July 2015
- Rupp, Matthias; Ramakrishnan, Raghunathan; von Lilienfeld, O. Anatole
- The Journal of Physical Chemistry Letters, Vol. 6, Issue 16
Generating Focused Molecule Libraries for Drug Discovery with Recurrent Neural Networks
journal, December 2017
- Segler, Marwin H. S.; Kogej, Thierry; Tyrchan, Christian
- ACS Central Science, Vol. 4, Issue 1
3D deep convolutional neural networks for amino acid environment similarity analysis
journal, June 2017
- Torng, Wen; Altman, Russ B.
- BMC Bioinformatics, Vol. 18, Issue 1
Constant size descriptors for accurate machine learning models of molecular properties
journal, June 2018
- Collins, Christopher R.; Gordon, Geoffrey J.; von Lilienfeld, O. Anatole
- The Journal of Chemical Physics, Vol. 148, Issue 24
ImageNet classification with deep convolutional neural networks
journal, May 2017
- Krizhevsky, Alex; Sutskever, Ilya; Hinton, Geoffrey E.
- Communications of the ACM, Vol. 60, Issue 6
Receptive fields of single neurones in the cat's striate cortex
journal, October 1959
- Hubel, D. H.; Wiesel, T. N.
- The Journal of Physiology, Vol. 148, Issue 3
Mapping receptive fields in primary visual cortex: Mapping receptive fields in primary visual cortex
journal, July 2004
- Ringach, Dario L.
- The Journal of Physiology, Vol. 558, Issue 3
Gradient-based learning applied to document recognition
journal, January 1998
- Lecun, Y.; Bottou, L.; Bengio, Y.
- Proceedings of the IEEE, Vol. 86, Issue 11
A comparative investigation of non-linear activation functions in neural controllers for search-based game AI engineering
journal, December 2011
- Tan, Tse Guan; Teo, Jason; Anthony, Patricia
- Artificial Intelligence Review, Vol. 41, Issue 1