Active learning - the field of machine learning (ML) dedicated to optimal experiment design, has played a part in science as far back as the 18th century when Laplace used it to guide his discovery of celestial mechanics [1]. In this work we focus a closed-loop, active learning-driven autonomous system on another major challenge, the discovery of advanced materials against the exceedingly complex synthesis-processes-structure-property landscape. We demonstrate autonomous research methodology (i.e. autonomous hypothesis definition and evaluation) that can place complex, advanced materials in reach, allowing scientists to fail smarter, learn faster, and spend less resources in their studies, while simultaneously improving trust in scientific results and machine learning tools. Additionally, this robot science enables science-over-the-network, reducing the economic impact of scientists being physically separated from their labs. We used the real-time closed-loop, autonomous system for materials exploration and optimization (CAMEO) at the synchrotron beamline to accelerate the fundamentally interconnected tasks of rapid phase mapping and property optimization, with each cycle taking seconds to minutes, resulting in the discovery of a novel epitaxial nanocomposite phase-change memory material.
@article{arxiv.2006.06141,
title = {On-the-fly Closed-loop Autonomous Materials Discovery via Bayesian Active Learning},
author = {A. Gilad Kusne and Heshan Yu and Changming Wu and Huairuo Zhang and Jason Hattrick-Simpers and Brian DeCost and Suchismita Sarker and Corey Oses and Cormac Toher and Stefano Curtarolo and Albert V. Davydov and Ritesh Agarwal and Leonid A. Bendersky and Mo Li and Apurva Mehta and Ichiro Takeuchi},
journal= {arXiv preprint arXiv:2006.06141},
year = {2020}
}
Comments
30 pages and 13 figures in PDF including Methods section