Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Invariant Molecular Representations for Heterogeneous Catalysis

Journal Article · · Journal of Chemical Information and Modeling

Catalyst screening is a critical step in the discovery and development of heterogeneous catalysts, which are vital for a wide range of chemical processes. In recent years, computational catalyst screening, primarily through density functional theory (DFT), has gained significant attention as a method for identifying promising catalysts. However, the computation of adsorption energies for all likely chemical intermediates present in complex surface chemistries is computationally intensive and costly due to the expensive nature of these calculations and the intrinsic idiosyncrasies of the methods or data sets used. This study introduces a novel machine learning (ML) method to learn adsorption energies from multiple DFT functionals by using invariant molecular representations (IMRs). To do this, we first extract molecular fingerprints for the reaction intermediates and later use a Siamese-neural-network-based training strategy to learn invariant molecular representations or the IMR across all available functionals. Our Siamese network-based representations demonstrate superior performance in predicting adsorption energies compared with other molecular representations. Notably, when considering mean absolute values of adsorption energies as 0.43 eV (PBE-D3), 0.46 eV (BEEF-vdW), 0.81 eV (RPBE), and 0.37 eV (scan+rVV10), our IMR method has achieved the lowest mean absolute errors (MAEs) of 0.18 0.10, 0.16, and 0.18 eV, respectively. These results emphasize the superior predictive capacity of our Siamese network-based representations. The empirical findings in this study illuminate the efficacy, robustness, and dependability of our proposed ML paradigm in predicting adsorption energies, specifically for propane dehydrogenation on a platinum catalyst surface.

Research Organization:
Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States). National Energy Research Scientific Computing Center (NERSC)
Sponsoring Organization:
USDOE Office of Science (SC), Basic Energy Sciences (BES). Scientific User Facilities (SUF); National Science Foundation (NSF); San Diego Supercomputer Center (SDSC)
Grant/Contract Number:
AC02-05CH11231
OSTI ID:
2471146
Journal Information:
Journal of Chemical Information and Modeling, Journal Name: Journal of Chemical Information and Modeling Journal Issue: 2 Vol. 64; ISSN 1549-9596
Publisher:
American Chemical SocietyCopyright Statement
Country of Publication:
United States
Language:
English

References (49)

Fundamental Concepts in Heterogeneous Catalysis book January 2014
The Computational Road to Better Catalysts journal March 2014
Generative Recurrent Networks for De Novo Drug Design journal November 2017
A comparative investigation of non-linear activation functions in neural controllers for search-based game AI engineering journal December 2011
Molecular graph convolutions: moving beyond fingerprints journal August 2016
A theory of learning from different domains journal October 2009
Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set journal July 1996
Machine learning in chemoinformatics and drug discovery journal August 2018
Microkinetic Modeling: A Tool for Rational Catalyst Design journal November 2020
Machine Learning Methods to Predict Density Functional Theory B3LYP Energies of HOMO and LUMO Orbitals journal December 2016
A Multiple Filter Based Neural Network Approach to the Extrapolation of Adsorption Energies on Metal Surfaces for Catalysis Applications journal January 2020
Comparative Study on the Machine Learning-Based Prediction of Adsorption Energies for Ring and Chain Species on Metal Catalyst Surfaces journal August 2021
Prediction of Adsorption Energies for Chemical Species on Metal Catalyst Surfaces Using Machine Learning journal November 2018
Benchmarking the Accuracy of Density Functional Theory against the Random Phase Approximation for the Ethane Dehydrogenation Network on Pt(111) journal November 2023
Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space journal June 2015
Machine Learning for Quantum Mechanical Properties of Atoms in Molecules journal July 2015
Open Catalyst 2020 (OC20) Dataset and Community Challenges journal May 2021
Propane Dehydrogenation on Platinum Catalysts: Identifying the Active Sites through Bayesian Analysis journal February 2022
Open Challenges in Developing Generalizable Large-Scale Machine-Learning Models for Catalyst Discovery journal July 2022
Machine-Learning Methods Enable Exhaustive Searches for Active Bimetallic Facets and Reveal Active Site Motifs for CO 2 Reduction journal August 2017
Generating Focused Molecule Libraries for Drug Discovery with Recurrent Neural Networks journal December 2017
The Generation of a Unique Machine Description for Chemical Structures-A Technique Developed at Chemical Abstracts Service. journal May 1965
Extended-Connectivity Fingerprints journal April 2010
A Density-Functional Theory-Based Neural Network Potential for Water Clusters Including van der Waals Corrections journal April 2013
The role of computational results databases in accelerating the discovery of catalysts journal October 2018
Linear scaling relationships and volcano plots in homogeneous catalysis – revisiting the Suzuki reaction journal January 2015
MoleculeNet: a benchmark for molecular machine learning journal January 2018
A consistent and accurate ab initio parametrization of density functional dispersion correction (DFT-D) for the 94 elements H-Pu journal April 2010
Atom-centered symmetry functions for constructing high-dimensional neural network potentials journal February 2011
Perspective: Machine learning potentials for atomistic simulations journal November 2016
Perspective: On the active site model in computational catalyst screening journal January 2017
Constant size descriptors for accurate machine learning models of molecular properties journal June 2018
Density functional theory in surface chemistry and catalysis journal January 2011
Catalysis making the world a better place
  • Catlow, C. Richard; Davidson, Matthew; Hardacre, Christopher
  • Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 374, Issue 2061 https://doi.org/10.1098/rsta.2015.0089
journal February 2016
Ab initiomolecular dynamics for liquid metals journal January 1993
Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set journal October 1996
Improved adsorption energetics within density-functional theory using revised Perdew-Burke-Ernzerhof functionals journal March 1999
Density functionals for surface science: Exchange-correlation model development with Bayesian error estimation journal June 2012
Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning journal January 2012
Generalized Gradient Approximation Made Simple journal October 1996
Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces journal April 2007
Scaling Properties of Adsorption Energies for Hydrogen-Containing Molecules on Transition-Metal Surfaces journal July 2007
Versatile van der Waals Density Functional Based on a Meta-Generalized Gradient Approximation journal October 2016
Gradient-based learning applied to document recognition journal January 1998
Learning a Similarity Metric Discriminatively, with Application to Face Verification conference January 2005
Assessing the reliability of calculated catalytic ammonia synthesis rates journal July 2014
Inverse molecular design using machine learning: Generative models for matter engineering journal July 2018
Theoretical Heterogeneous Catalysis: Scaling Relationships and Computational Catalyst Design journal June 2016
3D deep convolutional neural networks for amino acid environment similarity analysis journal June 2017