Closed-loop Autonomous Combinatorial Experimentation for Streamlined Materials Discovery

Dr. Ichiro Takeuchi, UMCP

Host: Dr. Pratyush Tiwary

Abstract: Machine learning has become an integral part of many aspects of fundamental research. It is particularly useful in high-throughput materials exploration where it can be used to predict and navigate a series of experiments, as well as perform rapid data analysis. In this talk, I will discuss how we are incorporating active learning in combinatorial screening and discovery of functional materials. The array format with which a large number of different composition samples are laid out on combinatorial libraries is particularly conducive to active learning driven autonomous experimentation. We have previously demonstrated discovery of a new phase change memory (PCM) material using the closed-loop autonomous materials exploration and optimization (CAMEO) strategy. The discovered PCM material has been tested in various scaled-up device formats and continues to exhibit superior performance to industrial standards. Recent efforts in developing live autonomous synthesis–measurement as well as experiment-theory closed loops will be discussed. This work is performed in collaboration with A. Gilad Kusne, V. Stanev, H. Yu, H. Liang, M. Li, E. Pop, and A. Mehta. This work is funded by SRC, ONR, AFOSR, and NIST.

Statistical Physics Seminar