Active learning path-dependent properties using a cloud-based materials acceleration platform
We demonstrate a framework for real-time active learning in state-changing experimental systems, integrating path-dependent acquisition functions with a fully autonomous, cloud-controlled experimental platform to accelerate materials discovery.
Authors
- Kevin C Tran (ORCID: https://orcid.org/0000-0002-8162-4477)
- Dan Guevarra (ORCID: https://orcid.org/0000-0002-9592-3195)
- Santosh K. Suram (ORCID: https://orcid.org/0000-0001-8170-2685)
- Joel A. Haber (ORCID: https://orcid.org/0000-0001-7847-5506)
- John M. Gregoire (ORCID: https://orcid.org/0000-0002-2863-5265)
- Michael J. Statt (ORCID: https://orcid.org/0000-0002-7923-6029)
- Kostiantyn Popovich
- Willie Neiswanger (ORCID: https://orcid.org/0000-0002-9619-5572)
- Brian A. Rohr (ORCID: https://orcid.org/0000-0003-4696-0149)
Institutions
- University of Southern California (US)
- California Institute of Technology (US)
- nLIGHT (United States) (US)
- Palo Alto Institute (US)
- Toyota Research Institute
- Toyota Industries (United States) (US)
Publication Details
- Journal
- Digital Discovery
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1039/d5dd00325c
- Primary Topic
- Machine Learning in Materials Science
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- U.S. Department of Energy
- Toyota Research Institute
- Office of Science
- Basic Energy Sciences