https://doi.org/10.1140/epjp/s13360-024-05947-w
Regular Article
Deep learning-based superconductivity prediction and experimental tests
1
Department of Physics and Astronomy, Rutgers University, 136 Frelinghuysen Road, 08854, Piscataway, NJ, USA
2
Department of Chemistry, Michigan State University, 578 S Shaw Lane, 48824, East Lansing, Michigan, USA
3
Department of Physics and Astronomy, University of South Carolina, 516 Main Street, 29208, Columbia, SC, USA
4
Department of Chemistry, Princeton University, Washington Road, 08544, Princeton, NJ, USA
5
Center for Computational Quantum Physics, Flatiron Institute, 162 5th Avenue, 10010, New York, NY, USA
6
Center for Computational Mathematics, Flatiron Institute, 162 5th Avenue, 10010, New York, NY, USA
a
anirvans.physics@gmail.com
b
xieweiwe@msu.edu
Received:
16
July
2024
Accepted:
27
December
2024
Published online:
22
January
2025
The discovery of novel superconducting materials is a long-standing challenge in materials science, with a wealth of potential for applications in energy, transportation and computing. Recent advances in artificial intelligence (AI) have enabled expediting the search for new materials by efficiently utilizing vast materials databases. In this study, we developed an approach based on deep learning (DL) to predict new superconducting materials. We have synthesized a compound derived from our DL network and confirmed its superconducting properties in agreement with our prediction. Our approach is also compared to previous work based on random forests (RFs). In particular, RFs require knowledge of the chemical properties of the compound, while our neural net inputs depend solely on the chemical composition. With the help of hints from our network, we discover a new ternary compound Mo20Re6Si4, which becomes superconducting below 5.4 K. We further discuss the existing limitations and challenges associated with using AI to predict and, along with potential future research directions.
© The Author(s) 2025
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
