# Data-driven optimization of FePt heat-assisted magnetic recording media accelerated by deep learning TEM image segmentation

https://mdr.nims.go.jp/datasets/f990c8ad-de6e-4119-b269-4489f4afc132

## File

- [Manuscript.pdf](https://mdr.nims.go.jp/filesets/12a96c0e-a23d-45ff-9cac-8ac79eb2a09f/download) ([Detail](https://mdr.nims.go.jp/filesets/12a96c0e-a23d-45ff-9cac-8ac79eb2a09f.md))

## Id

f990c8ad-de6e-4119-b269-4489f4afc132

## Local identifier



## Visibility

open_to_public

## State

published

## Created at

2024-10-22T02:01:54.985310Z

## Updated at

2025-05-26T23:30:20.657798Z

## Published at

2025-05-26T23:21:21.559160Z

## Doi

https://doi.org/10.48505/nims.4883

## First published url

https://doi.org/10.1016/j.actamat.2023.119039

## Date published

2023-05-27

## Recorded date published

2023-8

## Resource type

journal_article

## Manuscript type

accepted_manuscript

## Collection



## Title

- title: Data-driven optimization of FePt heat-assisted magnetic recording media accelerated
    by deep learning TEM image segmentation
  title_type: original
  lang: en

## Description

- description: The main bottleneck for heat-assisted magnetic recording (HAMR) to
    achieve a potential areal density of 4 Tb/in2 is the difficulty in obtaining FePt-X
    nanogranular media with an ideal stacking structure of perfectly isolated L10-FePt
    columnar nanograins. Here, we present a fully automated routine that combines
    a convolutional neural network and machine vision to enable data mining from transmission
    electron microscopy images of FePt-C nanogranular media. This allowed us to generate
    a dataset and implement a machine learning optimization model that guides process
    parameters to achieve the desired nanostructure, i.e., small grain size with unimodal
    distribution and a large coercivity, which was successfully validated experimentally.
    This work demonstrates the promise of data-driven design of high-density HAMR
    media.
  description_type: abstract
  lang: und

## Creator

- name: N. Kulesh
  role: author
  orcid: https://orcid.org/0000-0001-7046-2671
  organization: National Institute for Materials Science
  ror: https://ror.org/026v1ze26
- name: A. Bolyachkin
  role: author
  orcid: https://orcid.org/0000-0003-0420-1806
  organization: National Institute for Materials Science
  ror: https://ror.org/026v1ze26
- name: I. Suzuki
  role: author
  orcid: https://orcid.org/0000-0002-8932-8226
  organization: National Institute for Materials Science
- name: Y.K. Takahashi
  role: author
  orcid: https://orcid.org/0000-0001-9197-7236
  organization: National Institute for Materials Science
  ror: https://ror.org/026v1ze26
- name: H. Sepehri-Amin
  role: author
  orcid: https://orcid.org/0000-0002-7856-7897
  organization: National Institute for Materials Science
  ror: https://ror.org/026v1ze26
- name: K. Hono
  role: author
  orcid: https://orcid.org/0000-0001-7367-0193
  organization: National Institute for Materials Science
  ror: https://ror.org/026v1ze26

## Contact agent



## Publisher

organization: Elsevier BV

## Managing organization



## Keyword

- subject: Heat-assisted magnetic recording (HAMR)
  schema: not_defined
- subject: FePt
  schema: not_defined
- subject: Deep learning
  schema: not_defined
- subject: Machine learning
  schema: not_defined
- subject: Image segmentation
  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: 2023-05-27
end_date: 2025-05-27

## Journal

- title: Acta Materialia
  issn: '13596454'
  volume: '255'
  article_number: '119039'

## Conference



## Related item



## Funding

- funder_name: Japan Science and Technology Agency
- funder_name: Government of Japan Ministry of Education Culture Sports Science and
    Technology

## 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: 12a96c0e-a23d-45ff-9cac-8ac79eb2a09f
  filename: Manuscript.pdf
  content_type: application/pdf
  size: 1721121
  md5: 0ad56953f0d65cffcbbe9d22a8924a3b

## Thumbnail

fileset_id: 12a96c0e-a23d-45ff-9cac-8ac79eb2a09f
filename: Manuscript.pdf