Overcoming the chemical complexity bottleneck in on-the-fly machine learned molecular dynamics simulations

Lucas R. Timmerman; Shashikant Kumar; Phanish Suryanarayana; Andrew J. Medford

Overcoming the chemical complexity bottleneck in on-the-fly machine learned molecular dynamics simulations

Computational Physics 2024-06-13 v2 Materials Science Chemical Physics

Authors: Lucas R. Timmerman , Shashikant Kumar , Phanish Suryanarayana , Andrew J. Medford

Abstract

We develop a framework for on-the-fly machine learned force field molecular dynamics simulations based on the multipole featurization scheme that overcomes the bottleneck with the number of chemical elements. Considering bulk systems with up to 6 elements, we demonstrate that the number of density functional theory calls remains approximately independent of the number of chemical elements, in contrast to the increase in the smooth overlap of atomic positions scheme.

Keywords

machine learned force field molecular dynamics on-the-fly simulation multipole featurization density functional theory chemical complexity

Cite

@article{arxiv.2404.07961,
  title  = {Overcoming the chemical complexity bottleneck in on-the-fly machine learned molecular dynamics simulations},
  author = {Lucas R. Timmerman and Shashikant Kumar and Phanish Suryanarayana and Andrew J. Medford},
  journal= {arXiv preprint arXiv:2404.07961},
  year   = {2024}
}

Comments

15 total pages including references and SI, 4 main figures, 1 supplemental, 6 supplemental tables. Submitted to ACS Journal of Chemical Theory and Computation. Written and reviewed by all

Overcoming the chemical complexity bottleneck in on-the-fly machine learned molecular dynamics simulations

Abstract

Keywords

Cite

Comments

Related papers