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

Gradient-based design of compositions for high- T c superconductors: optimising T c and formation energy while adaptively integrating domain knowledge—controlling element and enforcing small integer stoichiometry—via masks and a special loss function.

Authors

Kōji Shimizu (ORCID: https://orcid.org/0000-0001-5622-9582)
Satoshi Watanabe (ORCID: https://orcid.org/0000-0002-8069-6938)
Akihiro Fujii (ORCID: https://orcid.org/0000-0002-3712-2015)
Anh Khoa Augustin Lu

Institutions

National Institute for Materials Science (JP)
National Institute of Advanced Industrial Science and Technology (JP)
The University of Tokyo (JP)

Publication Details

Journal: Digital Discovery
Published: 2025-01-01
DOI: https://doi.org/10.1039/d5dd00250h
Primary Topic: Machine Learning in Materials Science
Type: article
Field-Weighted Citation Impact: 0.00

Funders

University of Tokyo

Controls

|||

ALL TIME

JAN

FEB

MAR

APR

MAY

JUN

JUL

AUG

SEP

OCT

article

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

Kōji Shimizu, Satoshi Watanabe, Akihiro Fujii, Anh Khoa Augustin Lu

Jan 1, 2025

Digital Discovery

Machine Learning in Materials Science

article

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

Kōji Shimizu, Satoshi Watanabe, Akihiro Fujii, Anh Khoa Augustin Lu

January 1, 2025article en

Abstract

Gradient-based design of compositions for high- T c superconductors: optimising T c and formation energy while adaptively integrating domain knowledge—controlling element and enforcing small integer stoichiometry—via masks and a special loss function.

Digital DiscoveryVol. 4(12)

National Institute for Materials Science (JP), National Institute of Advanced Industrial Science and Technology (JP), The University of Tokyo (JP)

University of Tokyo

Openalex Percentile: Top 75%

Machine Learning in Materials Science

DOI Open Access PDF OpenAlex

AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

A straightforward gradient-based approach for designing superconductors with high critical temperature: exploiting domain knowledge <i>via</i> adaptive constraints — Kōji Shimizu, Satoshi Watanabe, et al. · Digital Discovery (2025) | TGRS Research Map | TGRS