Organohalide perovskites are a promising new material for low-cost, high-performance photovoltaics, but existing compounds—such as methylammonium lead iodide—suffer from environmental instability and use potentially toxic elements. The tremendous structural diversity that can be achieved by modifying the organic and inorganic building units presents the possibility of developing new, stable, high performance materials, but presents the challenge of a tremendous chemical space that must be explored. Very little is known about the mechanistic details of the crystal formation, and the range of possibilities is too vast to explore by brute force methods. Can machine learning approaches help accelerate the discovery of new materials?  To address this problem, we have developed the Robotic-Accelerated Perovskite Investigation and Discovery (RAPID) platform. This consists of an open source software package—ESCALATE (Experiment Specification, Capture and Laboratory Automation Technology), for experiment description and data collection—combined with lab automation hardware. 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. Collected characterizations includes qualitative measurements of crystal quality (including photographic images of the samples), powder X-Ray diffraction, and spectroscopic measurements along with background laboratory conditions. The second generation of RAPID is extended to include antisolvent precipitation synthesis of perovskite single crystals and perovskite thin film synthesis and characterization including remote monitoring of long-term environmental stability.  The comprehensive data of all experimental successes and failures is fed into an analysis pipeline that generate machine learning models relating reagent properties, composition, and reaction conditions to crystal formation, reports human-interpretable insights into the formation process, and creates recommendations for follow-up reactions. In addition to reporting on the chemical “successes”, we will also describe work on benchmarking the effectiveness of different experiment recommendation algorithms for identifying new compounds.

RAPID data-driven automated discovery of new organohalide perovskites

Macromolecular Chemistry: The Second Century

[Author Benefits](https://scimeetings.acs.org/?utm_source=pubs_content_marketing&utm_medium=website&utm_campaign=0320_MCF_NPI_Launch_Spring_Homepage&ref=pubs_content_marketing)

[How to use SciMeetings](https://storage.googleapis.com/dl.morressier.com/acs/SciMeetings-ACSSpring2020-HowToGuide_M3020-Final.pdf)

[Frequently Asked Questions](https://storage.googleapis.com/dl.morressier.com/acs/SciMtng_ACSNMSp2020_FAQ_M3120_Final.pdf)

ACS Spring 2020 National Meeting & Expo

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.