Structural Fingerprinting of Crystalline Materials from XRD Patterns Using Atomic Cluster Expansion Neural Network and Atomic Cluster Expansion

This study introduces a novel contrastive learning-based X-ray diffraction (XRD) analysis framework, an SE(3)-equivariant graph neural network (E3NN) based Atomic Cluster Expansion Neural Network (EACNN), which reduces the strong dependency on databases and initial models in traditional methods. By...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiao Zhang, Xitao Wang, Shunbo Hu
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/11/5851
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849330613420556288
author Xiao Zhang
Xitao Wang
Shunbo Hu
author_facet Xiao Zhang
Xitao Wang
Shunbo Hu
author_sort Xiao Zhang
collection DOAJ
description This study introduces a novel contrastive learning-based X-ray diffraction (XRD) analysis framework, an SE(3)-equivariant graph neural network (E3NN) based Atomic Cluster Expansion Neural Network (EACNN), which reduces the strong dependency on databases and initial models in traditional methods. By integrating E3NN with atomic cluster expansion (ACE) techniques, a dual-tower contrastive learning model has been developed, mapping crystal structures and XRD patterns to a continuous embedding space. The EACNN model retains hierarchical features of crystal systems through symmetry-sensitive encoding mechanisms and utilizes relationship mining via contrastive learning to replace rigid classification boundaries. This approach reveals gradual symmetry-breaking patterns between monoclinic and orthorhombic crystal systems in the latent space, effectively addressing the recognition challenges associated with low-symmetry systems and small sample space groups. Our investigation further explores the potential for model transfer to experimental data and multimodal extensions, laying the theoretical foundation for establishing a universal structure–property mapping relationship.
format Article
id doaj-art-e4123d127cb848dcaefba40ae76a6902
institution Kabale University
issn 2076-3417
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-e4123d127cb848dcaefba40ae76a69022025-08-20T03:46:50ZengMDPI AGApplied Sciences2076-34172025-05-011511585110.3390/app15115851Structural Fingerprinting of Crystalline Materials from XRD Patterns Using Atomic Cluster Expansion Neural Network and Atomic Cluster ExpansionXiao Zhang0Xitao Wang1Shunbo Hu2Institute for the Conservation of Cultural Heritage, School of Cultural Heritage and Information Management, Shanghai University, Shanghai 200444, ChinaInstitute for the Conservation of Cultural Heritage, School of Cultural Heritage and Information Management, Shanghai University, Shanghai 200444, ChinaInstitute for the Conservation of Cultural Heritage, School of Cultural Heritage and Information Management, Shanghai University, Shanghai 200444, ChinaThis study introduces a novel contrastive learning-based X-ray diffraction (XRD) analysis framework, an SE(3)-equivariant graph neural network (E3NN) based Atomic Cluster Expansion Neural Network (EACNN), which reduces the strong dependency on databases and initial models in traditional methods. By integrating E3NN with atomic cluster expansion (ACE) techniques, a dual-tower contrastive learning model has been developed, mapping crystal structures and XRD patterns to a continuous embedding space. The EACNN model retains hierarchical features of crystal systems through symmetry-sensitive encoding mechanisms and utilizes relationship mining via contrastive learning to replace rigid classification boundaries. This approach reveals gradual symmetry-breaking patterns between monoclinic and orthorhombic crystal systems in the latent space, effectively addressing the recognition challenges associated with low-symmetry systems and small sample space groups. Our investigation further explores the potential for model transfer to experimental data and multimodal extensions, laying the theoretical foundation for establishing a universal structure–property mapping relationship.https://www.mdpi.com/2076-3417/15/11/5851contrastive learningSE(3)-equivariant graph neural networkslow-symmetry crystal systems
spellingShingle Xiao Zhang
Xitao Wang
Shunbo Hu
Structural Fingerprinting of Crystalline Materials from XRD Patterns Using Atomic Cluster Expansion Neural Network and Atomic Cluster Expansion
Applied Sciences
contrastive learning
SE(3)-equivariant graph neural networks
low-symmetry crystal systems
title Structural Fingerprinting of Crystalline Materials from XRD Patterns Using Atomic Cluster Expansion Neural Network and Atomic Cluster Expansion
title_full Structural Fingerprinting of Crystalline Materials from XRD Patterns Using Atomic Cluster Expansion Neural Network and Atomic Cluster Expansion
title_fullStr Structural Fingerprinting of Crystalline Materials from XRD Patterns Using Atomic Cluster Expansion Neural Network and Atomic Cluster Expansion
title_full_unstemmed Structural Fingerprinting of Crystalline Materials from XRD Patterns Using Atomic Cluster Expansion Neural Network and Atomic Cluster Expansion
title_short Structural Fingerprinting of Crystalline Materials from XRD Patterns Using Atomic Cluster Expansion Neural Network and Atomic Cluster Expansion
title_sort structural fingerprinting of crystalline materials from xrd patterns using atomic cluster expansion neural network and atomic cluster expansion
topic contrastive learning
SE(3)-equivariant graph neural networks
low-symmetry crystal systems
url https://www.mdpi.com/2076-3417/15/11/5851
work_keys_str_mv AT xiaozhang structuralfingerprintingofcrystallinematerialsfromxrdpatternsusingatomicclusterexpansionneuralnetworkandatomicclusterexpansion
AT xitaowang structuralfingerprintingofcrystallinematerialsfromxrdpatternsusingatomicclusterexpansionneuralnetworkandatomicclusterexpansion
AT shunbohu structuralfingerprintingofcrystallinematerialsfromxrdpatternsusingatomicclusterexpansionneuralnetworkandatomicclusterexpansion