# Uncovering crystal structure evolution via nanobeam X-ray diffraction with a continuity-driven machine learning approach

https://mdr.nims.go.jp/datasets/d57d41c7-f55f-423b-b181-625813b034e4

## File

- [Wu Mater Design 2026 nanoXRD ML.pdf](https://mdr.nims.go.jp/filesets/8fc54d0d-968c-4a6a-be61-b590a853c1c6/download) ([Detail](https://mdr.nims.go.jp/filesets/8fc54d0d-968c-4a6a-be61-b590a853c1c6.md))

## Id

d57d41c7-f55f-423b-b181-625813b034e4

## Local identifier



## Visibility

open_to_public

## State

published

## Created at

2026-02-25T06:16:54.264920Z

## Updated at

2026-02-26T03:30:06.191860Z

## Published at

2026-02-26T00:41:08.356910Z

## Doi



## First published url

https://doi.org/10.1016/j.matdes.2026.115669

## Date published

2026-02-15

## Recorded date published

2026-3

## Resource type

journal_article

## Manuscript type

vor

## Collection



## Title

- title: Uncovering crystal structure evolution via nanobeam X-ray diffraction with
    a continuity-driven machine learning approach
  title_type: original
  lang: en

## Description

- description: Nanobeam X-ray diffraction (nanoXRD) enables nanoscale mapping of crystal
    structures across wafer-scale crystals, offering unique insight into microstructural
    evolution during crystal growth. However, the resulting large and complex diffraction
    datasets make it challenging to quantitatively resolve local structural transitions
    and their connection to growth processes using conventional analysis. Here, we
    present a continuity-driven, unsupervised, and generalized analysis framework,
    referred to as the neighborhood-based similarity metric, which integrates spatial
    coordinates with nanoXRD data to reveal structural variations across growth sectors,
    interfaces, and defect-related regions without requiring prior knowledge or labels.
    By introducing Jaccard similarity scores to compare local neighborhoods in spatial
    and diffraction domains, the method quantitatively detects discontinuities where
    structural evolution disrupts the local continuity of diffraction patterns. Our
    unsupervised approach, validated with synthetic data and nanoXRD measurements
    of bulk GaN crystals, successfully identified both known defects and previously
    hidden structural discontinuities. The results provide new insights into the relationship
    between growth conditions, local strain evolution, and defect formation, establishing
    a robust and interpretable approach for linking processing and structural characteristics
    in complex crystalline materials.
  description_type: abstract
  lang: und

## Creator

- name: Zhendong Wu
  role: author
  orcid: https://orcid.org/0000-0002-9882-4133
- name: Tetsuya Tohei
  role: author
  orcid: https://orcid.org/0000-0002-4113-2566
- name: Yusuke Hayashi
  role: author
  orcid: https://orcid.org/0000-0001-5672-1497
- name: Shigeyoshi Usami
  role: author
- name: Masayuki Imanishi
  role: author
- name: Yusuke Mori
  role: author
- name: Junichi Takino
  role: author
- name: Kazushi Sumitani
  role: author
- name: Yasuhiko Imai
  role: author
  orcid: https://orcid.org/0000-0003-4686-2629
- name: Shigeru Kimura
  role: author
  orcid: https://orcid.org/0000-0003-1064-7572
- name: Akira Sakai
  role: author
  orcid: https://orcid.org/0000-0002-0654-504X

## Contact agent



## Publisher

organization: Elsevier BV

## Managing organization



## Keyword

- subject: GaN
  schema: not_defined
- subject: nanoXRD
  schema: not_defined
- subject: ML
  schema: not_defined

## Rights

- identifier: https://creativecommons.org/licenses/by/4.0/

## Other identifier(s)



## Data origin



## Embargo



## Journal

- title: Materials & Design
  issn: '02641275'
  volume: '263'
  article_number: '115669'

## Conference



## Related item



## Funding

- funder_name: Murata Science and Education Foundation
- identifier: JP16H06423
  funder_name: Japan Society for the Promotion of Science
- identifier: JP20H00352
  funder_name: Japan Society for the Promotion of Science
- identifier: JP22KK0055
  funder_name: Japan Society for the Promotion of Science
- identifier: JP23H01447
  funder_name: Japan Society for the Promotion of Science

## Instrument



## Instrument operator



## Instrument managing organization



## Measurement method



## Specimen



## Chemical composition



## Structure for specimen



## Structural feature for specimen



## Specific property for specimen



## Process for specimen treatment



## Computational method



## Energy level/transition state



## Software



## Custom property



## Fileset

- id: 8fc54d0d-968c-4a6a-be61-b590a853c1c6
  filename: Wu Mater Design 2026 nanoXRD ML.pdf
  content_type: application/pdf
  size: 8210671
  md5: d5acd4c8d071d454d2142f65c9e92429

## Thumbnail

fileset_id: 8fc54d0d-968c-4a6a-be61-b590a853c1c6
filename: Wu Mater Design 2026 nanoXRD ML.pdf