(275c) Automating Discovery: Accelerating the Search for Novel Perovskites with Robots and Data

Scientific discovery has typically been conducted in a bespoke fashion, where human experts design and perform experiments in a manual way. Advances in laboratory automation, data collection, and machine learning may enable new approaches to automating the discovery process.

In this talk, I will describe our Robotic-Accelerated Perovskite Investigation and Discovery (RAPID) project. The first generation of RAPID uses inverse temperature crystallization (ITC) to grow halide perovskite single crystals for x-ray structure determination and bulk characterization using commercial liquid handling robots. The second generation of RAPID uses antisolvent vapor diffusion, expanding the types of chemical processes we can study.

Experiment plans for the syntheses are contributed remotely, by both human scientists and algorithms trained on the reaction data, facilitated by our ESCALATE (Experiment Specification, Capture and Laboratory Automation Technology) data management software. ESCALATE is a general-purpose software system that captures and processes the comprehensive data and metadata collected during experiments into a form suitable for machine learning. I will discuss ESCALATE deployments to problems of halide perovskite crystal growth, perovskite thin film, and solid-liquid and liquid-liquid separations of actinide mixtures. In addition to presenting an abstraction layer for algorithmic-controlled experiments, the comprehensive dataset captured by ESCALATE enables “automated serendipity,” wherein we can use statistical analyses to identify hypotheses about how crystal growth depends upon poorly-controlled experimental conditions, and followed by deliberate, automated, interventional studies to confirm or reject those hypotheses.

Throughout the talk I will describe case studies about how we have used this RAPID/ESCALATE to extract new scientific insights, enhance the replicability of our scientific work, and reduce the time to discovery, which is applicable to a variety of discovery projects.