×

Indexed by

Fast Bayesian force fields from active learning: study of inter-dimensional transformation of stanene

Yu Xie1*, Jonathan Vandermause1*, Lixin Sun1*, Andrea Cepellotti1*, Boris Kozinsky1,2*

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

2 Robert Bosch LLC, Research and Technology Center, Cambridge, Massachusetts 02142, USA

* Corresponding authors emails: xiey@g.harvard.edu, jonathan_vandermause@g.harvard.edu, lixinsun@g.harvard.edu, acepellotti@seas.harvard.edu, bkoz@g.harvard.edu
DOI10.24435/materialscloud:cs-tf [version v2]

Publication date: Aug 24, 2020

How to cite this record

Yu Xie, Jonathan Vandermause, Lixin Sun, Andrea Cepellotti, Boris Kozinsky, Fast Bayesian force fields from active learning: study of inter-dimensional transformation of stanene, Materials Cloud Archive 2020.99 (2020), doi: 10.24435/materialscloud:cs-tf.

Description

Gaussian process (GP) regression is one promising technique of constructing machine learning force fields with built-in uncertainty quantification, which can be used to monitor the quality of model predictions. A current limitation of existing GP force fields is that the prediction cost grows linearly with the size of the training data set, making accurate GP predictions slow. In this work, we exploit the special structure of the kernel function to construct a mapping of the trained Gaussian process model, including both forces and their uncertainty predictions, onto spline functions of low-dimensional structural features. This method is incorporated in the Bayesian active learning workflow for training of Bayesian force fields. To demonstrate the capabilities of this method, we construct a force field for stanene and perform large scale dynamics simulation of its structural evolution. We provide a fully open-source implementation of our method, as well as the training and testing examples with the stanene dataset.

Materials Cloud sections using this data

No Explore or Discover sections associated with this archive record.

Files

File name Size Description
README.txt
MD5md5:bba77ddb993e2b57a34767a01ba409b0
936 Bytes README file
flare.zip
MD5md5:62cbb48b16b2703d0eb31dfc7cc4341a
94.1 KiB Python code of this method, including building spline interpolations and Bayesian active learning
data.zip
MD5md5:a147d2f8a8d8f2479110735a4159f61d
374.8 KiB The extracted training and testing data of stanene
Atoms3k_Temp200K.zip
MD5md5:3b5915815e162c942f682b627b673700
137.0 MiB Large-scale molecular dynamics simulation of monolayer-bulk transition process of stanene, including MGP pair style coefficient file, LAMMPS input, data, log and trajectory files
Atoms10k_Temp500K.zip
MD5md5:619ab5cec9b5b277f2bec47ec24c0886
94.2 MiB Large-scale molecular dynamics simulation of melting process of stanene, including MGP pair style coefficient file, LAMMPS input, data, log and trajectory files
LMP.zip
MD5md5:980dac59df745cebcd8acb74f3616a27
3.4 MiB LAMMPS source code of MGP pair style, also including an executable

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.

External references

Preprint
Y. Xie, J. Vandermause, L. Sun, A. Cepellotti, B. Kozinsky, in preparation.
Journal reference (Paper and code on which this method is based)
Software (Code in which the method is implemented)

Keywords

machine learning molecular dynamics Bayesian inference stanene phase transition

Version history:

2020.99 (version v2) [This version] Aug 24, 2020 DOI10.24435/materialscloud:cs-tf
2020.90 (version v1) Aug 03, 2020 DOI10.24435/materialscloud:7k-9g