Closed-loop superconducting materials discovery

• Published in: npj computational materials Vol. 9; no. 1; pp. 181 - 8
• Main Authors: Pogue, Elizabeth A., New, Alexander, McElroy, Kyle, Le, Nam Q., Pekala, Michael J., McCue, Ian, Gienger, Eddie, Domenico, Janna, Hedrick, Elizabeth, McQueen, Tyrel M., Wilfong, Brandon, Piatko, Christine D., Ratto, Christopher R., Lennon, Andrew, Chung, Christine, Montalbano, Timothy, Bassen, Gregory, Stiles, Christopher D.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 05.10.2023; Nature Publishing Group; Nature Portfolio
• Subjects: 639/301/119/1003; 639/766/119/1003; Characterization and Evaluation of Materials; Chemistry and Materials Science; Closed loops; Computational Intelligence; Datasets; Feedback; Machine learning; Materials Science; Mathematical and Computational Engineering; Mathematical and Computational Physics; Mathematical Modeling and Industrial Mathematics; Phase diagrams; Physics; Superconductivity; Superconductors; Theoretical; Zirconium
• ISSN: 2057-3960; 2057-3960
• DOI: 10.1038/s41524-023-01131-3

Discovery of novel materials is slow but necessary for societal progress. Here, we demonstrate a closed-loop machine learning (ML) approach to rapidly explore a large materials search space, accelerating the intentional discovery of superconducting compounds. By experimentally validating the results of the ML-generated superconductivity predictions and feeding those data back into the ML model to refine, we demonstrate that success rates for superconductor discovery can be more than doubled. Through four closed-loop cycles, we report discovery of a superconductor in the Zr-In-Ni system, re-discovery of five superconductors unknown in the training datasets, and identification of two additional phase diagrams of interest for new superconducting materials. Our work demonstrates the critical role experimental feedback provides in ML-driven discovery, and provides a blueprint for how to accelerate materials progress.