# Prediction of nanocomposite properties and process optimization using persistent homology and machine learning

https://mdr.nims.go.jp/datasets/d847f1c9-973f-4c9a-982a-4de1ac721d7d

## File

- [draft_Persistent_tomography_Micron_20240513FU.docx](https://mdr.nims.go.jp/filesets/f2596556-6f9a-4334-9743-6f70c08a2495/download) ([Detail](https://mdr.nims.go.jp/filesets/f2596556-6f9a-4334-9743-6f70c08a2495.md))

## Id

d847f1c9-973f-4c9a-982a-4de1ac721d7d

## Local identifier



## Visibility

open_to_public

## State

published

## Created at

2024-06-27T04:53:50.391535Z

## Updated at

2024-07-01T23:38:11.500847Z

## Published at

2026-05-27T23:37:05.274940Z

## Doi

https://doi.org/10.48505/nims.4564

## First published url

https://doi.org/10.1016/j.micron.2024.103664

## Date published

2024-05-28

## Recorded date published

2024-8

## Resource type

journal_article

## Manuscript type

accepted_manuscript

## Collection



## Title

- title: Prediction of nanocomposite properties and process optimization using persistent
    homology and machine learning
  title_type: original
  lang: en

## Description

- description: 'Physical property prediction and synthesis process optimization are
    key targets in material informatics. In this study, we propose a machine learning
    approach that utilizes ridge regression to predict the oxygen permeability at
    fuel cell electrode surfaces and determine the optimal process temperature. These
    predictions are based on a persistence diagram derived from tomographic images
    captured using transmission electron microscopy (TEM). Through machine learning
    analysis of the complex structures present in the Pt/CeO2 nanocomposites, we discovered
    that l2 regularization considering diverse structural elements is more appropriate
    than l1 regularization (sparse modeling). Notably, our model successfully captured
    the activation energy of oxygen permeability, a phenomenon that could not be solely
    explained by the geometric feature of the Betti numbers, as demonstrated in a
    previous study. The correspondence between the ridge regression coefficient and
    persistence diagram revealed the formation process of the local and three-dimensional
    structures of CeO2 and their contributions to pre-exponential factor and activation
    energies. This analysis facilitated the determination of the annealing temperature
    required to achieve the optimal structure and accurately predict the physical
    properties. '
  description_type: abstract
  lang: und

## Creator

- name: Fumihiko Uesugi
  role: author
  orcid: https://orcid.org/0000-0003-3346-4218
  organization: National Institute for Materials Science
  ror: https://ror.org/026v1ze26
- name: Yu Wen
  role: author
- name: Ayako Hashimoto
  role: author
  orcid: https://orcid.org/0000-0002-1985-7667
  organization: National Institute for Materials Science
  ror: https://ror.org/026v1ze26
- name: Masashi Ishii
  role: author
  orcid: https://orcid.org/0000-0003-0357-2832
  organization: National Institute for Materials Science
  ror: https://ror.org/026v1ze26

## Contact agent



## Publisher

organization: Elsevier BV

## Managing organization



## Keyword

- subject: Persistent homology
  schema: not_defined
- subject: Ridge regression
  schema: not_defined
- subject: Electron tomography
  schema: not_defined
- subject: Oxygen permeability
  schema: not_defined
- subject: Activation energy
  schema: not_defined
- subject: Annealing temperature
  schema: not_defined

## Rights

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

## Other identifier(s)



## Data origin

- data_origin_type: other

## Embargo

start_date: 2024-05-28
end_date: 2026-05-28

## Journal

- title: Micron
  issn: '09684328'
  volume: '183'
  article_number: '103664'

## Conference



## Related item



## Funding

- identifier: JPMJFR213U
  funder_name: JST

## 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: f2596556-6f9a-4334-9743-6f70c08a2495
  filename: draft_Persistent_tomography_Micron_20240513FU.docx
  content_type: application/vnd.openxmlformats-officedocument.wordprocessingml.document
  size: 5248679
  md5: 7f72da80e10865297a30adaf4dacf0a1

## Thumbnail

fileset_id: f2596556-6f9a-4334-9743-6f70c08a2495
filename: draft_Persistent_tomography_Micron_20240513FU.docx