Transferability of neural network potentials for varying stoichiometry: Phonons and thermal conductivity of Mn x Ge y compounds - Université Grenoble Alpes Accéder directement au contenu
Article Dans Une Revue Journal of Applied Physics Année : 2020

Transferability of neural network potentials for varying stoichiometry: Phonons and thermal conductivity of Mn x Ge y compounds

Claudia Mangold
  • Fonction : Auteur
Shunda Chen
Giuseppe Barbalinardo
Jörg Behler
Pascal Pochet
Yang Han
Laurent Chaput
  • Fonction : Auteur
David Lacroix
Davide Donadio

Résumé

Germanium manganese compounds exhibit a variety of stable and metastable phases with different stoichiometries. These materials entail interesting electronic, magnetic, and thermal properties both in their bulk form and as heterostructures. Here, we develop and validate a transferable machine learning potential, based on the high-dimensional neural network formalism, to enable the study of MnxGey materials over a wide range of compositions. We show that a neural network potential fitted on a minimal training set reproduces successfully the structural and vibrational properties and the thermal conductivity of systems with different local chemical environments, and it can be used to predict phononic effects in nanoscale heterostructures.

Dates et versions

hal-04596768 , version 1 (31-05-2024)

Identifiants

Citer

Claudia Mangold, Shunda Chen, Giuseppe Barbalinardo, Jörg Behler, Pascal Pochet, et al.. Transferability of neural network potentials for varying stoichiometry: Phonons and thermal conductivity of Mn x Ge y compounds. Journal of Applied Physics, 2020, 127 (24), pp.23711-23720. ⟨10.1063/5.0009550⟩. ⟨hal-04596768⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More