# Accurate screening of functional materials with machine-learning potential and transfer-learned regressions: Heusler alloy benchmark

https://mdr.nims.go.jp/datasets/8b4bec3a-3a6c-4cf9-ac4e-04c558b69880

## File

- [s41524-026-02013-0.pdf](https://mdr.nims.go.jp/filesets/2d0d548d-b4f9-45c9-bc8c-dab3efac9889/download) ([Detail](https://mdr.nims.go.jp/filesets/2d0d548d-b4f9-45c9-bc8c-dab3efac9889.md))

## Id

8b4bec3a-3a6c-4cf9-ac4e-04c558b69880

## Local identifier



## Visibility

open_to_public

## State

published

## Created at

2026-03-30T02:08:45.438691Z

## Updated at

2026-03-30T04:06:06.580619Z

## Published at

2026-03-30T07:24:37.201177Z

## Doi



## First published url

https://doi.org/10.1038/s41524-026-02013-0

## Date published

2026-02-19

## Recorded date published



## Resource type

journal_article

## Manuscript type

vor

## Collection



## Title

- title: 'Accurate screening of functional materials with machine-learning potential
    and transfer-learned regressions: Heusler alloy benchmark'
  title_type: original
  lang: en

## Description

- description: We present a machine learning-accelerated high-throughput (HTP) workflow
    for the discovery of functional materials. As a test case, quaternary and all-d
    Heusler compounds were screened for stable compounds with large magnetocrystalline
    anisotropy energy (Eaniso). Structure optimization and evaluation of formation
    energy and energy above the convex hull were performed using the eSEN-30M-OAM
    interatomic potential, while local magnetic moments, phonon stability, magnetic
    stability, and Eaniso were predicted by eSEN models trained on our DxMag Heusler
    database. A frozen transfer learning strategy was employed to improve accuracy.
    Candidate compounds identified by the ML-HTP workflow were validated with density
    functional theory, confirming high predictive precision. We also benchmark the
    performance of different uMLIPs, discuss the fidelity of local magnetic moment
    prediction, and demonstrate generalization to unseen elements via transfer learning
    from a universal interatomic potential.
  description_type: abstract
  lang: und

## Creator

- name: Enda Xiao
  role: author
  orcid: https://orcid.org/0000-0002-4372-1575
- name: Terumasa Tadano
  role: author
  orcid: https://orcid.org/0000-0002-8132-2161

## Contact agent



## Publisher

organization: Springer Science and Business Media LLC

## Managing organization



## Keyword

- subject: Heusler alloys
  schema: not_defined
- subject: Machine-learning potential
  schema: not_defined
- subject: Transfer learning
  schema: not_defined
- subject: First-principles calculation
  schema: not_defined
- subject: Curie temperature
  schema: not_defined
- subject: Magnetic anisotropy energy
  schema: not_defined

## Rights

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

## Other identifier(s)



## Data origin

- data_origin_type: other

## Embargo



## Journal

- title: npj Computational Materials
  issn: '20573960'
  volume: '12'
  issue: '1'
  article_number: '133'

## Conference



## Related item



## Funding

- identifier: JPMXP1020230327
  funder_name: Ministry of Education, Culture, Sports, Science and Technology
- identifier: JPMXP1122715503
  funder_name: 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: 2d0d548d-b4f9-45c9-bc8c-dab3efac9889
  filename: s41524-026-02013-0.pdf
  content_type: application/pdf
  size: 1013742
  md5: 56b064bdbf78ac278bd4572fb5c6c277

## Thumbnail

fileset_id: 2d0d548d-b4f9-45c9-bc8c-dab3efac9889
filename: s41524-026-02013-0.pdf