# Machine learning-driven analysis and process optimization of FePt-BN granular films for HAMR applications

https://mdr.nims.go.jp/datasets/cd54e408-c716-4362-b1f1-19c0dbc82e93

## File

- [20250803 FePt-BN_WAVEBASE_cleancopy_manuscript.docx](https://mdr.nims.go.jp/filesets/bd998604-1a7b-440e-827b-b23d2392f0e5/download) ([Detail](https://mdr.nims.go.jp/filesets/bd998604-1a7b-440e-827b-b23d2392f0e5.md))

## Id

cd54e408-c716-4362-b1f1-19c0dbc82e93

## Local identifier



## Visibility

open_to_public

## State

published

## Created at

2026-11-13T03:57:33.141781Z

## Updated at

2026-11-16T00:49:23.710172Z

## Published at

2026-11-17T09:29:04.391361Z

## Doi

https://doi.org/10.48505/nims.8734

## First published url

https://doi.org/10.1080/14686996.2026.2699076

## Date published

2026-12-31

## Recorded date published

2026-12-31

## Resource type

journal_article

## Manuscript type

accepted_manuscript

## Collection



## Title

- title: Machine learning-driven analysis and process optimization of FePt-BN granular
    films for HAMR applications
  title_type: original
  lang: en

## Description

- description: The ever-increasing demand for high-density, energy-efficient data
    storage, propelled by AI and cloud infrastructures, is driving advancements in
    heat-assisted magnetic recording (HAMR)media. L10-ordered FePt granular thin films
    are recognized as leading candidates owing to their exceptional thermal stability
    and potential for sub-10 nm grain sizes. Here, we investigate FePt-BN granular
    films, systematically optimizing their microstructure and magnetic properties
    by tuning process parameters including BN atomic fraction of FePt-BN targets,
    N2 gas flow, andfilm thickness. Employing a hybrid workflow that integrates conventional
    trial-and-error experi-mentation with machine learning such as principle component
    analysis, random forest regressionand Bayesian optimization, we identify key determinants
    governing average main- and sub-grainsize (D1, D2), coercivity (μ0Hc), and chemical
    ordering. Machine-learning analysis reveals that thedegree of L10 order is the
    primary factor for μ0Hc, while D1 is mainly influenced by BN content andmicrostructural
    attributes derived from transmission electron microscopy data. Active-learning-guided
    Bayesian optimization enabled us to rapidly achieve FePt-BN media with high μ0Hc
    (2.4 T),sub 6 nm grain diameters, and areal grain densities exceeding 12 Tgrains/in2
    outperformingtraditional heuristic approaches with fewer experiments. Our results
    underscore the power ofdata-driven process optimization for accelerated HAMR materials
    development, enabling therealization of next-generation hard disk drives with
    ultra-high recording densities
  description_type: abstract
  lang: und

## Creator

- name: Daisuke Ogawa
  role: author
  orcid: https://orcid.org/0000-0002-4373-6435
- name: Tetsuya Shoji
  role: author
- name: Masao Yano
  role: author
- name: Yusuke Matsuoka
  role: author
  orcid: https://orcid.org/0000-0001-5300-1726
- name: Yukiko K. Takahashi
  role: author
  orcid: https://orcid.org/0000-0001-9197-7236

## Contact agent



## Publisher

organization: Informa UK Limited

## Managing organization



## Keyword

- subject: FePt-BN granular films
  schema: not_defined
- subject: process optimization
  schema: not_defined
- subject: machine learning
  schema: not_defined

## Rights

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

## Other identifier(s)



## Data origin



## Embargo



## Journal

- title: Science and Technology of Advanced Materials
  issn: '14686996'
  volume: '27'
  issue: '1'
  article_number: '2699076'

## Conference



## Related item



## Funding

- identifier: JPMJC22C3
  funder_name: Japan Science and Technology Agency (JST) through the Core Research
    for Evolutional Science and Technology (CREST) program
- identifier: JPMXP1122715503
  funder_name: Ministry of Education, Culture, Sports, Science and Technology, Japan
    (MEXT), through the Data Creation and Utilization-Type Material Research and Development
    Project

## 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: bd998604-1a7b-440e-827b-b23d2392f0e5
  filename: 20250803 FePt-BN_WAVEBASE_cleancopy_manuscript.docx
  content_type: application/vnd.openxmlformats-officedocument.wordprocessingml.document
  size: 6720469
  md5: 06a3fac8166b940bb7200a7e674f0a23

## Thumbnail

fileset_id: bd998604-1a7b-440e-827b-b23d2392f0e5
filename: 20250803 FePt-BN_WAVEBASE_cleancopy_manuscript.docx