materialscloud:2020.155
Published December 1, 2020 | Version v3
Dataset Open

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

Creators

  • 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

* Contact person

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.

Files

File preview

All files

Files (618.3 MiB)

Name Size
md5:c3d517b0c8b69254be964c2f35282615
592 Bytes Preview Download
md5:4dd1cbfc0b81b93cb5a4877e94f5a59a
460.2 KiB Preview Download
md5:62cbb48b16b2703d0eb31dfc7cc4341a
94.1 KiB Preview Download
md5:3177c52a24b94c6bc2edfeda19e1e217
3.4 MiB Preview Download
md5:8ab5b2285543e668ade1bd07b6e77fb7
228.6 MiB Preview Download
md5:9d36b692a81ba8cd4338f6ccf1390440
385.8 MiB Preview Download
md5:c78306356a58379e40453bc94fa0cfb4
1.1 KiB Preview Download

References

Journal reference (Journal article in which the method is described and the data is discussed)
Xie, Y., Vandermause, J., Sun, L. et al. Bayesian force fields from active learning for simulation of inter-dimensional transformation of stanene. npj Comput Mater 7, 40 (2021)., doi: 10.1038/s41524-021-00510-y

Journal reference (Paper and code on which this method is based)
J. Vandermause, S.B. Torrisi, S. Batzner, Y. Xie, L. Sun, A.M. Kolpak, B. Kozinsky, npj Comput Mater 6, 20 (2020)., doi: 10.1038/s41524-020-0283-z

Software (Code in which the method is implemented)
J. Vandermause, S.B. Torrisi, S. Batzner, Y. Xie, L. Sun, A.M. Kolpak, B. Kozinsky, npj Comput Mater 6, 20 (2020).