Closed-loop superconducting materials discovery
Abstract 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 th...
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-10-01
|
| Series: | npj Computational Materials |
| Online Access: | https://doi.org/10.1038/s41524-023-01131-3 |
| _version_ | 1797557780940324864 |
|---|---|
| author | Elizabeth A. Pogue Alexander New Kyle McElroy Nam Q. Le Michael J. Pekala Ian McCue Eddie Gienger Janna Domenico Elizabeth Hedrick Tyrel M. McQueen Brandon Wilfong Christine D. Piatko Christopher R. Ratto Andrew Lennon Christine Chung Timothy Montalbano Gregory Bassen Christopher D. Stiles |
| author_facet | Elizabeth A. Pogue Alexander New Kyle McElroy Nam Q. Le Michael J. Pekala Ian McCue Eddie Gienger Janna Domenico Elizabeth Hedrick Tyrel M. McQueen Brandon Wilfong Christine D. Piatko Christopher R. Ratto Andrew Lennon Christine Chung Timothy Montalbano Gregory Bassen Christopher D. Stiles |
| author_sort | Elizabeth A. Pogue |
| collection | DOAJ |
| description | Abstract 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. |
| first_indexed | 2024-03-10T17:21:01Z |
| format | Article |
| id | doaj.art-0f288a1057e2432db4f684a6df63cc72 |
| institution | Directory Open Access Journal |
| issn | 2057-3960 |
| language | English |
| last_indexed | 2024-03-10T17:21:01Z |
| publishDate | 2023-10-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Computational Materials |
| spelling | doaj.art-0f288a1057e2432db4f684a6df63cc722023-11-20T10:19:03ZengNature Portfolionpj Computational Materials2057-39602023-10-01911810.1038/s41524-023-01131-3Closed-loop superconducting materials discoveryElizabeth A. Pogue0Alexander New1Kyle McElroy2Nam Q. Le3Michael J. Pekala4Ian McCue5Eddie Gienger6Janna Domenico7Elizabeth Hedrick8Tyrel M. McQueen9Brandon Wilfong10Christine D. Piatko11Christopher R. Ratto12Andrew Lennon13Christine Chung14Timothy Montalbano15Gregory Bassen16Christopher D. Stiles17Research and Exploratory Development Department, Johns Hopkins University Applied Physics LaboratoryResearch and Exploratory Development Department, Johns Hopkins University Applied Physics LaboratoryResearch and Exploratory Development Department, Johns Hopkins University Applied Physics LaboratoryResearch and Exploratory Development Department, Johns Hopkins University Applied Physics LaboratoryResearch and Exploratory Development Department, Johns Hopkins University Applied Physics LaboratoryResearch and Exploratory Development Department, Johns Hopkins University Applied Physics LaboratoryResearch and Exploratory Development Department, Johns Hopkins University Applied Physics LaboratoryResearch and Exploratory Development Department, Johns Hopkins University Applied Physics LaboratoryDepartment of Materials Science and Engineering, Johns Hopkins UniversityDepartment of Materials Science and Engineering, Johns Hopkins UniversityDepartment of Chemistry, Johns Hopkins UniversityResearch and Exploratory Development Department, Johns Hopkins University Applied Physics LaboratoryResearch and Exploratory Development Department, Johns Hopkins University Applied Physics LaboratoryResearch and Exploratory Development Department, Johns Hopkins University Applied Physics LaboratoryResearch and Exploratory Development Department, Johns Hopkins University Applied Physics LaboratoryResearch and Exploratory Development Department, Johns Hopkins University Applied Physics LaboratoryDepartment of Chemistry, Johns Hopkins UniversityResearch and Exploratory Development Department, Johns Hopkins University Applied Physics LaboratoryAbstract 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.https://doi.org/10.1038/s41524-023-01131-3 |
| spellingShingle | Elizabeth A. Pogue Alexander New Kyle McElroy Nam Q. Le Michael J. Pekala Ian McCue Eddie Gienger Janna Domenico Elizabeth Hedrick Tyrel M. McQueen Brandon Wilfong Christine D. Piatko Christopher R. Ratto Andrew Lennon Christine Chung Timothy Montalbano Gregory Bassen Christopher D. Stiles Closed-loop superconducting materials discovery npj Computational Materials |
| title | Closed-loop superconducting materials discovery |
| title_full | Closed-loop superconducting materials discovery |
| title_fullStr | Closed-loop superconducting materials discovery |
| title_full_unstemmed | Closed-loop superconducting materials discovery |
| title_short | Closed-loop superconducting materials discovery |
| title_sort | closed loop superconducting materials discovery |
| url | https://doi.org/10.1038/s41524-023-01131-3 |
| work_keys_str_mv | AT elizabethapogue closedloopsuperconductingmaterialsdiscovery AT alexandernew closedloopsuperconductingmaterialsdiscovery AT kylemcelroy closedloopsuperconductingmaterialsdiscovery AT namqle closedloopsuperconductingmaterialsdiscovery AT michaeljpekala closedloopsuperconductingmaterialsdiscovery AT ianmccue closedloopsuperconductingmaterialsdiscovery AT eddiegienger closedloopsuperconductingmaterialsdiscovery AT jannadomenico closedloopsuperconductingmaterialsdiscovery AT elizabethhedrick closedloopsuperconductingmaterialsdiscovery AT tyrelmmcqueen closedloopsuperconductingmaterialsdiscovery AT brandonwilfong closedloopsuperconductingmaterialsdiscovery AT christinedpiatko closedloopsuperconductingmaterialsdiscovery AT christopherrratto closedloopsuperconductingmaterialsdiscovery AT andrewlennon closedloopsuperconductingmaterialsdiscovery AT christinechung closedloopsuperconductingmaterialsdiscovery AT timothymontalbano closedloopsuperconductingmaterialsdiscovery AT gregorybassen closedloopsuperconductingmaterialsdiscovery AT christopherdstiles closedloopsuperconductingmaterialsdiscovery |