Abstract: Machine learning is increasingly used by chemists and materials scientists. However, many of these demonstrations have been based on computational datasets. Experimental data presents unique challenges—it is often limited in scale, biased by human choices, and often only semi-structured, all of which present challenges for machine learning applications. Automated experimentation provides the opportunity to improve the quality and scale of experimental data, and also create opportunities to test algorithmically-designed experiments in the laboratory.

In this talk, I will describe our efforts in developing RAPID (Robotic-Accelerated Perovskite Investigation and Discovery)—a platform for doing semi-automated syntheses of metal halide perovskites—and ESCALATE (Experiment Specification, Capture and Laboratory Automation Technology) an adaptable open-source package for experiment description and data collection. I will discuss several example applications where we have been able to use this hardware and software combination to accelerate the discovery of new materials, find scientific insights latent in our historical datasets, perform model-driven quality control on our scientific experiments, and automate serendipity by statistical analysis of experimental metadata.

Bio: Joshua Schrier is a physical chemist interested in using computers to accelerate the discovery of new materials, by using a combination of physics-based simulations, cheminformatics, machine learning, and automated experimentation.