TY - JOUR
T1 - Accurate and scalable graph neural network force field and molecular dynamics with direct force architecture
AU - Park, Cheol Woo
AU - Kornbluth, Mordechai
AU - Vandermause, Jonathan
AU - Wolverton, Chris
AU - Kozinsky, Boris
AU - Mailoa, Jonathan P.
N1 - Funding Information:
This work was performed in and funded by Bosch Research and Technology Center. This work was partially supported by ARPA-E Award No. DE-AR0000775. This research used resources of the Oak Ridge Leadership Computing Facility at Oak Ridge National Laboratory, which is supported by the Office of Science of the Department of Energy under Contract DE-AC05-00OR22725. C.W.P. and C.W. also acknowledge financial assistance from Award No.70NANB14H012 from US Department of Commerce, National Institute of Standards and Technology as part of the Center for Hierarchical Materials Design (CHiMaD) and the Toyota Research Institute (TRI). The authors also thank Eric Isaacs and Yizhou Zhu for helpful discussion.
Publisher Copyright:
© 2021, The Author(s).
PY - 2021/12
Y1 - 2021/12
N2 - Recently, machine learning (ML) has been used to address the computational cost that has been limiting ab initio molecular dynamics (AIMD). Here, we present GNNFF, a graph neural network framework to directly predict atomic forces from automatically extracted features of the local atomic environment that are translationally-invariant, but rotationally-covariant to the coordinate of the atoms. We demonstrate that GNNFF not only achieves high performance in terms of force prediction accuracy and computational speed on various materials systems, but also accurately predicts the forces of a large MD system after being trained on forces obtained from a smaller system. Finally, we use our framework to perform an MD simulation of Li7P3S11, a superionic conductor, and show that resulting Li diffusion coefficient is within 14% of that obtained directly from AIMD. The high performance exhibited by GNNFF can be easily generalized to study atomistic level dynamics of other material systems.
AB - Recently, machine learning (ML) has been used to address the computational cost that has been limiting ab initio molecular dynamics (AIMD). Here, we present GNNFF, a graph neural network framework to directly predict atomic forces from automatically extracted features of the local atomic environment that are translationally-invariant, but rotationally-covariant to the coordinate of the atoms. We demonstrate that GNNFF not only achieves high performance in terms of force prediction accuracy and computational speed on various materials systems, but also accurately predicts the forces of a large MD system after being trained on forces obtained from a smaller system. Finally, we use our framework to perform an MD simulation of Li7P3S11, a superionic conductor, and show that resulting Li diffusion coefficient is within 14% of that obtained directly from AIMD. The high performance exhibited by GNNFF can be easily generalized to study atomistic level dynamics of other material systems.
UR - http://www.scopus.com/inward/record.url?scp=85106582892&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85106582892&partnerID=8YFLogxK
U2 - 10.1038/s41524-021-00543-3
DO - 10.1038/s41524-021-00543-3
M3 - Article
AN - SCOPUS:85106582892
SN - 2057-3960
VL - 7
JO - npj Computational Materials
JF - npj Computational Materials
IS - 1
M1 - 73
ER -