Bond sensitive graph neural networks for predicting high temperature superconductors
Open Access
- 16 June 2024
- journal article
- research article
- Published by Wiley in Materials Genome Engineering Advances
- Vol. 2 (2)
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.Keywords
This publication has 51 references indexed in Scilit:
- Prospects of materials genome engineering frontiersMaterials Genome Engineering Advances, 2023
- Improving Material Property Prediction by Leveraging the Large-Scale Computational Database and Deep LearningThe Journal of Physical Chemistry C, 2022
- Benchmarking Coordination Number Prediction Algorithms on Inorganic Crystal StructuresInorganic Chemistry, 2021
- Graph Networks as a Universal Machine Learning Framework for Molecules and CrystalsChemistry of Materials, 2019
- Epilogue: Superconducting materials past, present and futurePhysica C: Superconductivity and its Applications, 2015
- Superconducting materials classes: Introduction and overviewPhysica C: Superconductivity and its Applications, 2015
- What T tellsPhysica C: Superconductivity and its Applications, 2015
- Materials Cartography: Representing and Mining Materials Space Using Structural and Electronic FingerprintsChemistry of Materials, 2015
- Relationship between crystal structure and superconductivity in iron-based superconductorsSolid State Communications, 2012
- The inorganic crystal structure data baseJournal of Chemical Information and Computer Sciences, 1983