# Effects of data bias on machine-learning–based material discovery using experimental property data

https://mdr.nims.go.jp/datasets/95874088-27fb-444c-8db6-86d93d85fa21

## Download

- [Effects of data bias on machine-learning based material discovery using experimental property data.pdf](https://mdr.nims.go.jp/filesets/1779332f-f974-4de0-8a16-7db08e08c6fe/download)

## Id

95874088-27fb-444c-8db6-86d93d85fa21

## Local identifier



## Visibility

open_to_public

## State

published

## Created at

2024-11-14T05:15:21.418462Z

## Updated at

2024-11-15T23:31:01.113522Z

## Published at

2024-11-15T23:31:01.183593Z

## Doi



## First published url

https://doi.org/10.1080/27660400.2022.2109447

## Date published

2022-12-31

## Recorded date published

2022-12-31

## Resource type

journal_article

## Manuscript type

vor

## Collection



## Title

- title: Effects of data bias on machine-learning–based material discovery using experimental
    property data
  title_type: original
  lang: en

## Description

- description: 本研究では、機械学習（ML）を用いた材料インフォマティクス（MI）において、大規模な材料データの偏りが機械学習モデルに与える影響を明らかにした。特に、適用領域の概念とクラスタリングを組み合わせ、データの偏りがMLモデルの予測誤差と信頼性に影響を与えることを示した。適用領域内での予測は信頼性が高い一方、適用領域外では予測の信頼性が低下する。この結果から、MLモデルが信頼できる材料探索の範囲は限られていることがわかったが、それでも新材料の提案は可能である。
  description_type: abstract
  lang: und

## Creator

- name: Masaya Kumagai
  role: author
- name: Yuki Ando
  role: author
- name: Atsumi Tanaka
  role: author
- name: Koji Tsuda
  role: author
  orcid: https://orcid.org/0000-0002-4288-1606
  organization: National Institute for Materials Science
  ror: https://ror.org/026v1ze26
- name: Yukari Katsura
  role: author
  orcid: https://orcid.org/0000-0002-8905-2995
  organization: National Institute for Materials Science
  ror: https://ror.org/026v1ze26
- name: Ken Kurosaki
  role: author
  orcid: https://orcid.org/0000-0002-3015-3206

## Contact agent



## Publisher

organization: Informa UK Limited

## Managing organization



## Keyword

- subject: Machine learning
  schema: not_defined
- subject: material informatics
  schema: not_defined
- subject: large-scale material data
  schema: not_defined
- subject: data bias
  schema: not_defined

## Rights

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

## Other identifier(s)



## Data origin

- data_origin_type: other

## Embargo



## Journal

- title: 'Science and Technology of Advanced Materials: Methods'
  issn: '27660400'
  volume: '2'
  issue: '1'
  start_page: 302
  end_page: 309

## Conference



## Related item



## Funding

- identifier: JP20K22466
  funder_name: JSPS KAKENHI

## 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: 1779332f-f974-4de0-8a16-7db08e08c6fe
  filename: Effects of data bias on machine-learning based material discovery using
    experimental property data.pdf
  content_type: application/pdf
  size: 6430866
  md5: 108cdb9f9057fce7d606b0aa905dd486

## Thumbnail

fileset_id: 1779332f-f974-4de0-8a16-7db08e08c6fe
filename: Effects of data bias on machine-learning based material discovery using
  experimental property data.pdf