Download file (896 KB)
Download as zip (663 KB)

Collection

Citation

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.

Rights:

• https://creativecommons.org/licenses/by/3.0/
  

  This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Keyword: Gradient-based optimization, Superconductor, Domain knowledge integration, Materials discovery, Critical temperature, Machine learning

Date published: 2025-10-29

Publisher: Royal Society of Chemistry (RSC)

Journal:

• Digital Discovery (ISSN: 2635098X) vol. 4 issue. 12 p. 3662-3673

Funding:

• University of Tokyo

Manuscript type: Publisher's version (Version of record)

MDR DOI:

First published URL: https://doi.org/10.1039/d5dd00250h

Related item:

Other identifier(s):

Contact agent:

Updated at: 2026-05-18 14:53:14 +0900

Published on MDR: 2026-05-18 16:23:13 +0900