Equivariant machine learning of Electric Field Gradients -- Predicting the quadrupolar coupling constant in the MAPbI$_3$ phase transition

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Schmiedmayer, Bernhard, Wolffs, J. W., de Wijs, Gilles A., Kentgens, Arno P. M., Lahnsteiner, Jonathan, Kresse, Georg
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913959917912064
author Schmiedmayer, Bernhard
Wolffs, J. W.
de Wijs, Gilles A.
Kentgens, Arno P. M.
Lahnsteiner, Jonathan
Kresse, Georg
author_facet Schmiedmayer, Bernhard
Wolffs, J. W.
de Wijs, Gilles A.
Kentgens, Arno P. M.
Lahnsteiner, Jonathan
Kresse, Georg
contents We present a strategy combining machine learning and first-principles calculations to achieve highly accurate nuclear quadrupolar coupling constant predictions. Our approach employs two distinct machine-learning frameworks: a machine-learned force field to generate molecular dynamics trajectories and a second model for electric field gradients that preserves rotational and translational symmetries. By incorporating thermostat-driven molecular dynamics sampling, we enable the prediction of quadrupolar coupling constants in highly disordered materials at finite temperatures. We validate our method by predicting the tetragonal-to-cubic phase transition temperature of the organic-inorganic halide perovskite MAPbI$_3$, obtaining results that closely match experimental data.
format Preprint
id arxiv_https___arxiv_org_abs_2507_19435
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Equivariant machine learning of Electric Field Gradients -- Predicting the quadrupolar coupling constant in the MAPbI$_3$ phase transition
Schmiedmayer, Bernhard
Wolffs, J. W.
de Wijs, Gilles A.
Kentgens, Arno P. M.
Lahnsteiner, Jonathan
Kresse, Georg
Materials Science
We present a strategy combining machine learning and first-principles calculations to achieve highly accurate nuclear quadrupolar coupling constant predictions. Our approach employs two distinct machine-learning frameworks: a machine-learned force field to generate molecular dynamics trajectories and a second model for electric field gradients that preserves rotational and translational symmetries. By incorporating thermostat-driven molecular dynamics sampling, we enable the prediction of quadrupolar coupling constants in highly disordered materials at finite temperatures. We validate our method by predicting the tetragonal-to-cubic phase transition temperature of the organic-inorganic halide perovskite MAPbI$_3$, obtaining results that closely match experimental data.
title Equivariant machine learning of Electric Field Gradients -- Predicting the quadrupolar coupling constant in the MAPbI$_3$ phase transition
topic Materials Science
url https://arxiv.org/abs/2507.19435