Improving accuracy of interatomic potentials: more physics or more data? A case study of silica

Ivan S. Novikov, Alexander V. Shapeev

Research output: Contribution to journalArticlepeer-review

19 Citations (Scopus)

Abstract

In this paper we test two strategies to improving the accuracy of machine-learning potentials, namely adding more fitting parameters thus making use of large volumes of available quantum-mechanical data, and adding a charge-equilibration model to account for ionic nature of the SiO2 bonding. To that end, we compare Moment Tensor Potentials (MTPs) and MTPs combined with the charge-equilibration (QEq) model (MTP+QEq) fitted to a density functional theory dataset of α-quartz SiO2-based structures. In order to make a meaningful comparison, in addition to the accuracy, we assess the uncertainty of predictions of each potential. It is shown that adding the QEq model to MTP does not make any improvement over the MTP potential alone, while adding more parameters does improve the accuracy and uncertainty of its predictions.

Original languageEnglish
Pages (from-to)74-80
Number of pages7
JournalMaterials Today Communications
Volume18
DOIs
Publication statusPublished - Mar 2019

Keywords

  • Charge-equilibration model
  • Machine-learning interatomic potentials
  • Moment Tensor Potential
  • Uncertainty quantification

Fingerprint

Dive into the research topics of 'Improving accuracy of interatomic potentials: more physics or more data? A case study of silica'. Together they form a unique fingerprint.

Cite this