Combining phonon accuracy with high transferability in Gaussian approximation potential models

  • Janine George
    Institute of Condensed Matter and Nanosciences, Université catholique de Louvain 1 , Chemin des Étoiles 8, 1348 Louvain-la-Neuve, Belgium
  • Geoffroy Hautier
    Institute of Condensed Matter and Nanosciences, Université catholique de Louvain 1 , Chemin des Étoiles 8, 1348 Louvain-la-Neuve, Belgium
  • Albert P. Bartók
    Department of Physics and Warwick Centre for Predictive Modelling, School of Engineering, University of Warwick 2 , Coventry CV4 7AL, United Kingdom
  • Gábor Csányi
    Engineering Laboratory, University of Cambridge 3 , Cambridge CB2 1PZ, United Kingdom
  • Volker L. Deringer
    Department of Chemistry, Inorganic Chemistry Laboratory, University of Oxford 4 , Oxford OX1 3QR, United Kingdom

抄録

<jats:p>Machine learning driven interatomic potentials, including Gaussian approximation potential (GAP) models, are emerging tools for atomistic simulations. Here, we address the methodological question of how one can fit GAP models that accurately predict vibrational properties in specific regions of configuration space while retaining flexibility and transferability to others. We use an adaptive regularization of the GAP fit that scales with the absolute force magnitude on any given atom, thereby exploring the Bayesian interpretation of GAP regularization as an “expected error” and its impact on the prediction of physical properties for a material of interest. The approach enables excellent predictions of phonon modes (to within 0.1 THz–0.2 THz) for structurally diverse silicon allotropes, and it can be coupled with existing fitting databases for high transferability across different regions of configuration space, which we demonstrate for liquid and amorphous silicon. These findings and workflows are expected to be useful for GAP-driven materials modeling more generally.</jats:p>

収録刊行物

被引用文献 (1)*注記

もっと見る

詳細情報 詳細情報について

問題の指摘

ページトップへ