Machine learning surrogate models for ...
Document type :
Article dans une revue scientifique
Permalink :
Title :
Machine learning surrogate models for prediction of point defect vibrational entropy
Author(s) :
Lapointe, Clovis [Auteur]
Département des Matériaux pour le Nucléaire [DMN]
Swinburne, Thomas D. [Auteur]
Centre National de la Recherche Scientifique [CNRS]
Centre Interdisciplinaire de Nanoscience de Marseille [CINaM]
Thiry, Louis [Auteur]
Mallat, Stéphane [Auteur]
Centre de Mathématiques Appliquées [CMAP]
Collège de France - Chaire Sciences des données
Proville, Laurent [Auteur]
Becquart, Charlotte [Auteur]
Unité Matériaux et Transformations - UMR 8207 [UMET]
Marinica, Mihai-Cosmin [Auteur]
Département des Matériaux pour le Nucléaire [DMN]
Swinburne, Thomas D. [Auteur]
Centre National de la Recherche Scientifique [CNRS]
Centre Interdisciplinaire de Nanoscience de Marseille [CINaM]
Thiry, Louis [Auteur]
Mallat, Stéphane [Auteur]
Centre de Mathématiques Appliquées [CMAP]
Collège de France - Chaire Sciences des données
Proville, Laurent [Auteur]
Becquart, Charlotte [Auteur]
Unité Matériaux et Transformations - UMR 8207 [UMET]
Marinica, Mihai-Cosmin [Auteur]
Journal title :
Physical Review Materials
Abbreviated title :
Phys. Rev. Materials
Volume number :
4
Publisher :
American Physical Society (APS)
Publication date :
2020-06-15
ISSN :
2475-9953
HAL domain(s) :
Chimie/Matériaux
Physique [physics]/Matière Condensée [cond-mat]/Science des matériaux [cond-mat.mtrl-sci]
Physique [physics]/Matière Condensée [cond-mat]/Science des matériaux [cond-mat.mtrl-sci]
English abstract : [en]
The temperature variation of the defect densities in a crystal depends on vibrational entropy. This contribution to the system thermodynamics remains computationally challenging as it requires a diagonalization of the ...
Show more >The temperature variation of the defect densities in a crystal depends on vibrational entropy. This contribution to the system thermodynamics remains computationally challenging as it requires a diagonalization of the system's Hessian which scales as O(N3) for a crystal made of N atoms. Here, to circumvent such a heavy computational task and make it feasible even for systems containing millions of atoms, the harmonic vibrational entropy of point defects is estimated directly from the relaxed atomic positions through a linear-in-descriptor machine learning approach of order O(N). With a size-independent descriptor dimension and fixed model parameters, an excellent predictive power is demonstrated on a wide range of defect configurations, supercell sizes, and external deformations well outside the training database. In particular, formation entropies in a range of 250kB are predicted with less than 1.6kB error from a training database whose formation entropies span only 25kB (training error less than 1.0kB). This exceptional transferability is found to hold even when the training is limited to a low-energy superbasin in the phase space while the tests are performed for a different liquid-like superbasin at higher energies.Show less >
Show more >The temperature variation of the defect densities in a crystal depends on vibrational entropy. This contribution to the system thermodynamics remains computationally challenging as it requires a diagonalization of the system's Hessian which scales as O(N3) for a crystal made of N atoms. Here, to circumvent such a heavy computational task and make it feasible even for systems containing millions of atoms, the harmonic vibrational entropy of point defects is estimated directly from the relaxed atomic positions through a linear-in-descriptor machine learning approach of order O(N). With a size-independent descriptor dimension and fixed model parameters, an excellent predictive power is demonstrated on a wide range of defect configurations, supercell sizes, and external deformations well outside the training database. In particular, formation entropies in a range of 250kB are predicted with less than 1.6kB error from a training database whose formation entropies span only 25kB (training error less than 1.0kB). This exceptional transferability is found to hold even when the training is limited to a low-energy superbasin in the phase space while the tests are performed for a different liquid-like superbasin at higher energies.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Administrative institution(s) :
Université de Lille
CNRS
INRA
ENSCL
CNRS
INRA
ENSCL
Collections :
Research team(s) :
Métallurgie Physique et Génie des Matériaux
Submission date :
2020-11-02T15:37:43Z
2020-11-07T21:03:52Z
2020-11-16T10:38:44Z
2020-11-25T15:36:41Z
2020-11-07T21:03:52Z
2020-11-16T10:38:44Z
2020-11-25T15:36:41Z
Files
- Entropy_Final_version.pdf
- Version finale acceptée pour publication (postprint)
- Open access
- Access the document