Machine learning interatomic potential can infer electrical response

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhong, Peichen, Kim, Dongjin, King, Daniel S., Cheng, Bingqing
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913780692156416
author Zhong, Peichen
Kim, Dongjin
King, Daniel S.
Cheng, Bingqing
author_facet Zhong, Peichen
Kim, Dongjin
King, Daniel S.
Cheng, Bingqing
contents Modeling the response of material and chemical systems to electric fields remains a longstanding challenge. Machine learning interatomic potentials (MLIPs) offer an efficient and scalable alternative to quantum mechanical methods but do not by themselves incorporate electrical response. Here, we show that polarization and Born effective charge (BEC) tensors can be directly extracted from long-range MLIPs within the Latent Ewald Summation (LES) framework, solely by learning from energy and force data. Using this approach, we predict the infrared spectra of bulk water under zero or finite external electric fields, ionic conductivities of high-pressure superionic ice, and the phase transition and hysteresis in ferroelectric PbTiO$_3$ perovskite. This work thus extends the capability of MLIPs to predict electrical response--without training on charges or polarization or BECs--and enables accurate modeling of electric-field-driven processes in diverse systems at scale.
format Preprint
id arxiv_https___arxiv_org_abs_2504_05169
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Machine learning interatomic potential can infer electrical response
Zhong, Peichen
Kim, Dongjin
King, Daniel S.
Cheng, Bingqing
Materials Science
Machine Learning
Chemical Physics
Computational Physics
Modeling the response of material and chemical systems to electric fields remains a longstanding challenge. Machine learning interatomic potentials (MLIPs) offer an efficient and scalable alternative to quantum mechanical methods but do not by themselves incorporate electrical response. Here, we show that polarization and Born effective charge (BEC) tensors can be directly extracted from long-range MLIPs within the Latent Ewald Summation (LES) framework, solely by learning from energy and force data. Using this approach, we predict the infrared spectra of bulk water under zero or finite external electric fields, ionic conductivities of high-pressure superionic ice, and the phase transition and hysteresis in ferroelectric PbTiO$_3$ perovskite. This work thus extends the capability of MLIPs to predict electrical response--without training on charges or polarization or BECs--and enables accurate modeling of electric-field-driven processes in diverse systems at scale.
title Machine learning interatomic potential can infer electrical response
topic Materials Science
Machine Learning
Chemical Physics
Computational Physics
url https://arxiv.org/abs/2504.05169