Back to Search Start Over

Bond sensitive graph neural networks for predicting high temperature superconductors

Bond sensitive graph neural networks for predicting high temperature superconductors

Authors :
Liang Gu
Yang Liu
Pin Chen
Haiyou Huang
Ning Chen
Yang Li
Turab Lookman
Yutong Lu
Yanjing Su
Source :
Materials Genome Engineering Advances, Vol 2, Iss 2, Pp n/a-n/a (2024)
Publication Year :
2024
Publisher :
Wiley-VCH, 2024.

Abstract

Abstract Finding high temperature superconductors (HTS) has been a continuing challenge due to the difficulty in predicting the transition temperature (Tc) of superconductors. Recently, the efficiency of predicting Tc has been greatly improved via machine learning (ML). Unfortunately, prevailing ML models have not shown adequate generalization ability to find new HTS, yet. In this work, a graph neural network model is trained to predict the maximal Tc (Tcmax) of various materials. Our model reveals a close connection between Tcmax and chemical bonds. It suggests that shorter bond lengths are favored by high Tc, which is in coherence with previous domain knowledge. More importantly, it also indicates that chemical bonds consisting of some specific chemical elements are responsible for high Tc, which is new even to the human experts. It can provide a convenient guidance to the materials scientists in search of HTS.

Details

Language :
English
ISSN :
29409497 and 29409489
Volume :
2
Issue :
2
Database :
Directory of Open Access Journals
Journal :
Materials Genome Engineering Advances
Publication Type :
Academic Journal
Accession number :
edsdoj.9de4da3fcf99408e855f255c1e7ab0c5
Document Type :
article
Full Text :
https://doi.org/10.1002/mgea.48