An implementation of artificial neural-network potentials for atomistic materials simulations: performance for TiO2

Nongnuch Artrith*, Alexander Urban

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

384 Citations (Scopus)

Abstract

Machine learning interpolation of atomic potential energy surfaces enables the nearly automatic construction of highly accurate atomic interaction potentials. Here we discuss the Behler-Parrinello approach that is based on artificial neural networks (ANNs) and detail the implementation of the method in the free and open-source atomic energy network (ænet) package. The construction and application of ANN potentials using ænet is demonstrated at the example of titanium dioxide (TiO2), an industrially relevant and well-studied material. We show that the accuracy of lattice parameters, energies, and bulk moduli predicted by the resulting TiO2 ANN potential is excellent for the reference phases that were used in its construction (rutile, anatase, and brookite) and examine the potential's capabilities for the prediction of the high-pressure phases columbite (α-PbO2 structure) and baddeleyite (ZrO2 structure).

Original languageEnglish
Pages (from-to)135-150
Number of pages16
JournalComputational Materials Science
Volume114
Early online date4 Jan 2016
DOIs
Publication statusPublished - Mar 2016

Keywords

  • Artificial neural networks
  • Atomistic simulations
  • Behler-Parrinello
  • Machine learning
  • Titanium dioxide (TiO)

Fingerprint

Dive into the research topics of 'An implementation of artificial neural-network potentials for atomistic materials simulations: performance for TiO2'. Together they form a unique fingerprint.

Cite this