Elucidating structure-property correlations in ferroelectric Hf0.5Zr0.5O2 films using variational autoencoders

While Hf0.5Zr0.5O2 (HZO) thin films hold significant promise for modern nanoelectronic devices, a comprehensive understanding of the interplay between their polycrystalline structure and electrical properties remains elusive. Here, we present a novel framework combining phase-field (PF) modeling wit...

Full description

Saved in:
Bibliographic Details
Main Authors: Kévin Alhada-Lahbabi, Brice Gautier, Damien Deleruyelle, Grégoire Magagnin
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Materials & Design
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S026412752500440X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850119514400751616
author Kévin Alhada-Lahbabi
Brice Gautier
Damien Deleruyelle
Grégoire Magagnin
author_facet Kévin Alhada-Lahbabi
Brice Gautier
Damien Deleruyelle
Grégoire Magagnin
author_sort Kévin Alhada-Lahbabi
collection DOAJ
description While Hf0.5Zr0.5O2 (HZO) thin films hold significant promise for modern nanoelectronic devices, a comprehensive understanding of the interplay between their polycrystalline structure and electrical properties remains elusive. Here, we present a novel framework combining phase-field (PF) modeling with Variational Autoencoders (VAEs) to uncover structure-property correlations in polycrystalline HZO. Leveraging PF simulations, we constructed a high-fidelity dataset of P-V loops by systematically varying critical material parameters, including grain size, polar grain fraction, and crystalline orientation. The VAEs effectively encoded hysteresis loops into a low-dimensional latent space, capturing electrical properties while disentangling complex material parameters' interdependencies. We further demonstrate a VAE-based inverse design approach to optimize P-V loop features, enabling the tailored design of device-specific key performance indicators (KPIs), including coercive field, remanent polarization, and loop area. The proposed approach offers a pathway to systematically explore and optimize the material design space for ferroelectric nanoelectronics.
format Article
id doaj-art-ebd6a26ccb404c6188515f545883e54b
institution OA Journals
issn 0264-1275
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series Materials & Design
spelling doaj-art-ebd6a26ccb404c6188515f545883e54b2025-08-20T02:35:36ZengElsevierMaterials & Design0264-12752025-06-0125411402010.1016/j.matdes.2025.114020Elucidating structure-property correlations in ferroelectric Hf0.5Zr0.5O2 films using variational autoencodersKévin Alhada-Lahbabi0Brice Gautier1Damien Deleruyelle2Grégoire Magagnin3INSA Lyon, CNRS, Ecole Centrale de Lyon, Université Claude Bernard Lyon 1, CPE Lyon, INL, UMR5270, 69621 Villeurbanne, France; Corresponding authors.INSA Lyon, CNRS, Ecole Centrale de Lyon, Université Claude Bernard Lyon 1, CPE Lyon, INL, UMR5270, 69621 Villeurbanne, FranceINSA Lyon, CNRS, Ecole Centrale de Lyon, Université Claude Bernard Lyon 1, CPE Lyon, INL, UMR5270, 69621 Villeurbanne, FranceCNRS, Ecole Centrale de Lyon, INSA Lyon, Université Claude Bernard Lyon 1, CPE Lyon, INL, UMR5270, 69621 Villeurbanne, France; Corresponding authors.While Hf0.5Zr0.5O2 (HZO) thin films hold significant promise for modern nanoelectronic devices, a comprehensive understanding of the interplay between their polycrystalline structure and electrical properties remains elusive. Here, we present a novel framework combining phase-field (PF) modeling with Variational Autoencoders (VAEs) to uncover structure-property correlations in polycrystalline HZO. Leveraging PF simulations, we constructed a high-fidelity dataset of P-V loops by systematically varying critical material parameters, including grain size, polar grain fraction, and crystalline orientation. The VAEs effectively encoded hysteresis loops into a low-dimensional latent space, capturing electrical properties while disentangling complex material parameters' interdependencies. We further demonstrate a VAE-based inverse design approach to optimize P-V loop features, enabling the tailored design of device-specific key performance indicators (KPIs), including coercive field, remanent polarization, and loop area. The proposed approach offers a pathway to systematically explore and optimize the material design space for ferroelectric nanoelectronics.http://www.sciencedirect.com/science/article/pii/S026412752500440XFerroelectricsPhase-fieldMachine learningVAEHafnium oxide
spellingShingle Kévin Alhada-Lahbabi
Brice Gautier
Damien Deleruyelle
Grégoire Magagnin
Elucidating structure-property correlations in ferroelectric Hf0.5Zr0.5O2 films using variational autoencoders
Materials & Design
Ferroelectrics
Phase-field
Machine learning
VAE
Hafnium oxide
title Elucidating structure-property correlations in ferroelectric Hf0.5Zr0.5O2 films using variational autoencoders
title_full Elucidating structure-property correlations in ferroelectric Hf0.5Zr0.5O2 films using variational autoencoders
title_fullStr Elucidating structure-property correlations in ferroelectric Hf0.5Zr0.5O2 films using variational autoencoders
title_full_unstemmed Elucidating structure-property correlations in ferroelectric Hf0.5Zr0.5O2 films using variational autoencoders
title_short Elucidating structure-property correlations in ferroelectric Hf0.5Zr0.5O2 films using variational autoencoders
title_sort elucidating structure property correlations in ferroelectric hf0 5zr0 5o2 films using variational autoencoders
topic Ferroelectrics
Phase-field
Machine learning
VAE
Hafnium oxide
url http://www.sciencedirect.com/science/article/pii/S026412752500440X
work_keys_str_mv AT kevinalhadalahbabi elucidatingstructurepropertycorrelationsinferroelectrichf05zr05o2filmsusingvariationalautoencoders
AT bricegautier elucidatingstructurepropertycorrelationsinferroelectrichf05zr05o2filmsusingvariationalautoencoders
AT damiendeleruyelle elucidatingstructurepropertycorrelationsinferroelectrichf05zr05o2filmsusingvariationalautoencoders
AT gregoiremagagnin elucidatingstructurepropertycorrelationsinferroelectrichf05zr05o2filmsusingvariationalautoencoders