# A straightforward gradient-based approach for designing superconductors with high critical temperature: exploiting domain knowledge                    <i>via</i>                    adaptive constraints

https://mdr.nims.go.jp/datasets/fd90e605-478b-4c7c-aad2-0306a05cbd39

## File

- [Fujii-DigitalDiscovery2025.pdf](https://mdr.nims.go.jp/filesets/332e6194-7e0d-430e-9b69-a74a9408ec50/download) ([Detail](https://mdr.nims.go.jp/filesets/332e6194-7e0d-430e-9b69-a74a9408ec50.md))

## Id

fd90e605-478b-4c7c-aad2-0306a05cbd39

## Local identifier



## Visibility

open_to_public

## State

published

## Created at

2026-05-18T05:27:56.957660Z

## Updated at

2026-05-18T05:53:14.771929Z

## Published at

2026-05-18T07:23:13.877230Z

## Doi



## First published url

https://doi.org/10.1039/d5dd00250h

## Date published

2025-10-29

## Recorded date published

2025-12-3

## Resource type

journal_article

## Manuscript type

vor

## Collection



## Title

- title: 'A straightforward gradient-based approach for designing superconductors
    with high critical temperature: exploiting domain knowledge                    <i>via</i>                    adaptive
    constraints'
  title_type: original
  lang: en

## Description

- description: Materials design aims to discover novel compounds with desired properties.
    However, prevailing strategies face critical trade-offs. Conventional element-substitution
    approaches readily and adaptively incorporate various domain knowledge but remain
    confined to a narrow search space. In contrast, deep generative models efficiently
    explore vast compositional landscapes, yet they struggle to flexibly integrate
    domain knowledge. To address these trade-offs, we propose a gradient-based material
    design framework that combines these strengths, offering both efficiency and adaptability.
    In our method, chemical compositions are optimised to achieve target properties
    by using property prediction models and their gradients. In order to seamlessly
    enforce diverse constraints—including those reflecting domain insights such as
    oxidation states, discretised compositional ratios, types of elements, and their
    abundance, we apply masks and employ a special loss function, namely the integer
    loss. Furthermore, we initialise the optimisation using promising candidates from
    existing datasets, effectively guiding the search away from unfavourable regions
    and thus helping to avoid poor solutions. Our approach demonstrates a more efficient
    exploration of superconductor candidates, uncovering candidate materials with
    higher critical temperature than conventional element-substitution and generative
    models. Importantly, it could propose new compositions beyond those found in existing
    databases, including new hydride superconductors absent from the training dataset
    but which share compositional similarities with materials found in the literature.
    This synergy of domain knowledge and machine-learning-based scalability provides
    a robust foundation for rapid, adaptive, and comprehensive materials design for
    superconductors and beyond.
  description_type: abstract
  lang: und

## Creator

- name: Akihiro Fujii
  role: author
- name: Anh Khoa Augustin Lu
  role: author
  orcid: https://orcid.org/0000-0003-4702-0933
  organization: National Institute for Materials Science
- name: Koji Shimizu
  role: author
- name: Satoshi Watanabe
  role: author
  orcid: https://orcid.org/0000-0002-8069-6938
  organization: National Institute for Materials Science

## Contact agent



## Publisher

organization: Royal Society of Chemistry (RSC)

## Managing organization



## Keyword

- subject: Gradient-based optimization
  schema: not_defined
- subject: Superconductor
  schema: not_defined
- subject: Domain knowledge integration
  schema: not_defined
- subject: Materials discovery
  schema: not_defined
- subject: Critical temperature
  schema: not_defined
- subject: Machine learning
  schema: not_defined

## Rights

- description: 'This article is licensed under a Creative Commons Attribution 3.0
    Unported Licence. '
  identifier: https://creativecommons.org/licenses/by/3.0/
  date_licensed: 2025-10-29

## Other identifier(s)



## Data origin

- data_origin_type: other

## Embargo



## Journal

- title: Digital Discovery
  issn: 2635098X
  volume: '4'
  issue: '12'
  start_page: 3662
  end_page: 3673

## Conference



## Related item



## Funding

- funder_name: University of Tokyo

## 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: 332e6194-7e0d-430e-9b69-a74a9408ec50
  filename: Fujii-DigitalDiscovery2025.pdf
  content_type: application/pdf
  size: 917321
  md5: 3d5ffdd01d361f4d356631ba39b025d0

## Thumbnail

fileset_id: 332e6194-7e0d-430e-9b69-a74a9408ec50
filename: Fujii-DigitalDiscovery2025.pdf