Automating Materials Synthesis: An Enabling Technology for Data Collection and AI in Materials Research

Information	Photo
Name Joshua Schrier Affiliation Fordham University, 441 E. Fordham Road, The Bronx, New York 10458, USA

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 creates opportunities to capture large, complete, machine-readable records of laboratory processes. In this talk, I will describe 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 describe how comprehensive data capture enabled us to extract new scientific insights, develop new active and meta-learning algorithms, and experimentally test the performance of AI methods for materials synthesis.

Biography

Automating Materials Synthesis: An Enabling Technology for Data Collection and AI in Materials Research

Joshua Schrier is a physical chemist interested in using computation and data to accelerate the discovery of new materials, using a combination of physics-based simulations, cheminformatics, machine learning, and automated experimentation. He is the Kim B. and Stephen E. Bepler Professor of Chemistry at Fordham University in New York City. Prior to joining Fordham in 2018, he was on the faculty at Haverford College. As a faculty member, he has received awards including the Dreyfus Teacher-Scholar, U.S. Department of Energy Visiting Faculty, and Fulbright scholar awards. He received his doctoral degree from the University of California, Berkeley, and was the Luis W. Alvarez Postdoctoral Fellow in Computational Sciences at Lawrence Berkeley National Laboratory. In addition to research work, he is interested in undergraduate education in computational approaches to chemistry (broadly defined) and is the author of the textbook Introduction to Computational Physical Chemistry.