×

Recommended by

Indexed by

Active learning of reactive Bayesian force fields applied to heterogeneous catalysis dynamics of H/Pt

Jonathan Vandermause1,2*, Yu Xie2, Jin Soo Lim3, Cameron Owen3, Boris Kozinsky2,4*

1 Department of Physics, Harvard University, Cambridge, MA 02138, USA

2 John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA 02138, USA

3 Department of Chemistry and Chemical Biology, Harvard University, Cambridge, MA 02138, USA

4 Robert Bosch LLC, Research and Technology Center, Cambridge, MA 02139, USA

* Corresponding authors emails: jonathan_vandermause@g.harvard.edu, bkoz@seas.harvard.edu
DOI10.24435/materialscloud:r0-84 [version v1]

Publication date: Jul 18, 2022

How to cite this record

Jonathan Vandermause, Yu Xie, Jin Soo Lim, Cameron Owen, Boris Kozinsky, Active learning of reactive Bayesian force fields applied to heterogeneous catalysis dynamics of H/Pt, Materials Cloud Archive 2022.92 (2022), doi: 10.24435/materialscloud:r0-84.

Description

Atomistic modeling of chemically reactive systems has so far relied on either expensive ab initio methods or bond-order force fields requiring arduous parametrization. Here, we describe a Bayesian active learning framework for autonomous ``on-the-fly'' training of fast and accurate reactive many-body force fields during molecular dynamics simulations. At each time step, predictive uncertainties of a sparse Gaussian process are evaluated to automatically determine whether additional ab initio training data are needed. We introduce a general method for mapping trained kernel models onto equivalent polynomial models whose prediction cost is much lower and independent of the training set size. As a demonstration, we perform direct two-phase simulations of heterogeneous H2 turnover on the Pt(111) catalyst surface at chemical accuracy. The model trains itself in three days and performs at twice the speed of a ReaxFF model, while maintaining much higher fidelity to DFT and excellent agreement with experiment.

Materials Cloud sections using this data

No Explore or Discover sections associated with this archive record.

Files

File name Size Description
training.zip
MD5md5:de93b69ab19392ac4900179c58d6dc9e
201.8 MiB Input and output files of the four on-the-fly training simulations described in the main text.
md.zip
MD5md5:529b04c1c5352d8838ea4a9eafc627db
107.2 MiB LAMMPS input and output files of the molecular dynamics simulations described in the main text and the custom LAMMPS potential file used to generate the trajectories.
readme.txt
MD5md5:6b468972d7a65440ebecb9ff36ec15fb
311 Bytes README file describing the directories.

License

Files and data are licensed under the terms of the following license: Creative Commons Attribution 4.0 International.
Metadata, except for email addresses, are licensed under the Creative Commons Attribution Share-Alike 4.0 International license.

Keywords

machine learning molecular dynamics density-functional theory

Version history:

2022.92 (version v1) [This version] Jul 18, 2022 DOI10.24435/materialscloud:r0-84