Machine-Learning Modeling of Elemental Ferroelectric Bismuth Monolayer DOI
Yanxing Zhang, Xinjian Ouyang, Dangqi Fang

et al.

Physical Review Letters, Journal Year: 2024, Volume and Issue: 133(26)

Published: Dec. 30, 2024

The bismuth monolayer has recently been experimentally identified as a novel platform for the investigation of two-dimensional single-element ferroelectric system. Here, we model potential energy surface by employing message-passing neural network and achieve an error smaller than 1.2 meV per atom. Empowered high accuracy fast prediction machine learning model, have embarked on in-depth large-scale atomistic simulations. These explorations are tailored to understand temperature-dependent phase transitions, with emphasis difference between free-standing monolayers those constrained substrate. Furthermore, large system used in simulations, also able observe domains within these systems shed light their intrinsic lattice thermal conductivity.

Language: Английский

Impact of crystal structure symmetry in training datasets on GNN-based energy assessments for chemically disordered CsPbI3 DOI Creative Commons
A. Krautsou, Innokentiy S. Humonen, Vladimir D. Lazarev

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: March 14, 2025

Robust solutions combining computational chemistry and data-driven approaches are in high demand various areas of materials science. For instance, such methods can use machine learning models trained on a limited dataset to make structure-to-property predictions over large search spaces. This paper examines the impact data selection mechanisms thermodynamic property assessments for chemically modified lead halide perovskite γ-CsPbI3 non-perovskite δ-CsPbI3. disordered states these phases, complete composition/configuration spaces built by adding Cd or Zn substitutions Pb Br I comprise 2,946,709 2,995,462 inequivalent spatial arrangements substituents, respectively. Using properties 1162 entries evaluated means density functional theory, we implement independent procedures training graph neural networks (GNNs). In each them, is constructed depending defect contents presence low- high-symmetry structures. The results show that symmetries structures significantly influence quality subsequent GNNs' result twofold increase errors due preferential

Language: Английский

Citations

0
Quantification of switchable thermal conductivity of ferroelectric materials through second-principles calculation DOI
Jingtong Zhang, Chengwen Bin, Yunhong Zhao

et al.

Materials Today Physics, Journal Year: 2024, Volume and Issue: 41, P. 101347 - 101347

Published: Jan. 26, 2024

Language: Английский

Citations

0
Modeling ferroelectric phase transitions with graph convolutional neural networks DOI Open Access
Xinjian Ouyang, Yanxing Zhang, Zhilong Wang

et al.

Acta Physica Sinica, Journal Year: 2024, Volume and Issue: 73(8), P. 086301 - 086301

Published: Jan. 1, 2024

Ferroelectric materials are widely used in functional devices, however, it has been a long-standing issue to achieve convenient and accurate theoretical modeling of them. Herein, noval approach ferroelectric is proposed by using graph convolutional neural networks (GCNs). In this approach, the potential energy surface described GCNs, which then serves as calculator conduct large-scale molecular dynamics simulations. Given atomic positions, well-trained GCN model can provide predictions forces, with an accuracy reaching up 1 meV per atom. The GCNs comparable that <i>ab inito</i> calculations, while computing speed faster than calculations few orders. Benefiting from high fast prediction model, we further combine simulations investigate two representative materials—bulk GeTe CsSnI<sub>3</sub>, successfully produce their temperature-dependent structural phase transitions, good agreement experimental observations. For GeTe, observe unusual negative thermal expansion around region its transition, reported previous experiments. correctly obtain octahedron tilting patterns associated transition sequence. These results demonstrate reliability surfaces for materials, thus providing universal investigating them theoretically.

Language: Английский

Citations

0
Latent space active learning with message passing neural network: The case of HfO2 DOI
Xinjian Ouyang,

Zhilong Wang,

Xiao Hua Jie

et al.

Physical Review Materials, Journal Year: 2024, Volume and Issue: 8(10)

Published: Oct. 11, 2024

Language: Английский

Citations

0
Machine-Learning Modeling of Elemental Ferroelectric Bismuth Monolayer DOI
Yanxing Zhang, Xinjian Ouyang, Dangqi Fang

et al.

Physical Review Letters, Journal Year: 2024, Volume and Issue: 133(26)

Published: Dec. 30, 2024

The bismuth monolayer has recently been experimentally identified as a novel platform for the investigation of two-dimensional single-element ferroelectric system. Here, we model potential energy surface by employing message-passing neural network and achieve an error smaller than 1.2 meV per atom. Empowered high accuracy fast prediction machine learning model, have embarked on in-depth large-scale atomistic simulations. These explorations are tailored to understand temperature-dependent phase transitions, with emphasis difference between free-standing monolayers those constrained substrate. Furthermore, large system used in simulations, also able observe domains within these systems shed light their intrinsic lattice thermal conductivity.

Language: Английский

Citations

0