Nature Communications (Nov 2020)
On-the-fly closed-loop materials discovery via Bayesian active learning
- A. Gilad Kusne,
- Heshan Yu,
- Changming Wu,
- Huairuo Zhang,
- Jason Hattrick-Simpers,
- Brian DeCost,
- Suchismita Sarker,
- Corey Oses,
- Cormac Toher,
- Stefano Curtarolo,
- Albert V. Davydov,
- Ritesh Agarwal,
- Leonid A. Bendersky,
- Mo Li,
- Apurva Mehta,
- Ichiro Takeuchi
Affiliations
- A. Gilad Kusne
- Materials Measurement Science Division, National Institute of Standards and Technology
- Heshan Yu
- Materials Science and Engineering Department, University of Maryland
- Changming Wu
- Electrical & Computer Engineering Department, University of Washington
- Huairuo Zhang
- Materials Science and Engineering Division, National Institute of Standards and Technology
- Jason Hattrick-Simpers
- Materials Measurement Science Division, National Institute of Standards and Technology
- Brian DeCost
- Materials Measurement Science Division, National Institute of Standards and Technology
- Suchismita Sarker
- Stanford Synchrotron Radiation Lightsource, SLAC National Accelerator Laboratory
- Corey Oses
- Mechanical Engineering and Materials Science Department and Center for Autonomous Materials Design, Duke University
- Cormac Toher
- Mechanical Engineering and Materials Science Department and Center for Autonomous Materials Design, Duke University
- Stefano Curtarolo
- Mechanical Engineering and Materials Science Department and Center for Autonomous Materials Design, Duke University
- Albert V. Davydov
- Materials Science and Engineering Division, National Institute of Standards and Technology
- Ritesh Agarwal
- Materials Science and Engineering Department, University of Pennsylvania
- Leonid A. Bendersky
- Materials Science and Engineering Division, National Institute of Standards and Technology
- Mo Li
- Electrical & Computer Engineering Department, University of Washington
- Apurva Mehta
- Stanford Synchrotron Radiation Lightsource, SLAC National Accelerator Laboratory
- Ichiro Takeuchi
- Materials Science and Engineering Department, University of Maryland
- DOI
- https://doi.org/10.1038/s41467-020-19597-w
- Journal volume & issue
-
Vol. 11,
no. 1
pp. 1 – 11
Abstract
Machine learning driven research holds big promise towards accelerating materials’ discovery. Here the authors demonstrate CAMEO, which integrates active learning Bayesian optimization with practical experiments execution, for the discovery of new phase- change materials using X-ray diffraction experiments.
