Active learning of linearly parametrized interatomic potentials

Evgeny V. Podryabinkin, Alexander V. Shapeev

Research output: Contribution to journalArticlepeer-review

211 Citations (Scopus)

Abstract

This paper introduces an active learning approach to the fitting of machine learning interatomic potentials. Our approach is based on the D-optimality criterion for selecting atomic configurations on which the potential is fitted. It is shown that the proposed active learning approach is highly efficient in training potentials on the fly, ensuring that no extrapolation is attempted and leading to a completely reliable atomistic simulation without any significant decrease in accuracy. We apply our approach to molecular dynamics and structure relaxation, and we argue that it can be applied, in principle, to any other type of atomistic simulation. The software, test cases, and examples of usage are published at http://gitlab.skoltech.ru/shapeev/mlip/.

Original languageEnglish
Pages (from-to)171-180
Number of pages10
JournalComputational Materials Science
Volume140
DOIs
Publication statusPublished - Dec 2017

Keywords

  • Active learning
  • Atomistic simulation
  • Interatomic potential
  • Learning on the fly
  • Machine learning
  • Moment tensor potentials

Fingerprint

Dive into the research topics of 'Active learning of linearly parametrized interatomic potentials'. Together they form a unique fingerprint.

Cite this