2024-03-29T01:46:56Z
https://archive.materialscloud.org/xml
oai:materialscloud.org:645
2021-03-21T16:48:39Z
DOI
Xie, Yu
Vandermause, Jonathan
Sun, Lixin
Cepellotti, Andrea
Kozinsky, Boris
2020-12-01
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.
https://archive.materialscloud.org/record/2020.155
doi:10.24435/materialscloud:qg-99
mcid:2020.155
oai:materialscloud.org:645
en
Materials Cloud
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode
machine learning
molecular dynamics
Bayesian inference
stanene
phase transition
Fast Bayesian force fields from active learning: study of inter-dimensional transformation of stanene
Dataset