Applying artificial intelligence to materials research requires abundant curated experimental data and the ability for algorithms to request new experiments. ESCALATE (Experiment Specification, Capture and Laboratory Automation Technology) is an ontological framework and open-source software package that solves this problem by providing an abstraction layer for human- and machine-readable experiment specification, comprehensive and extensible (meta-)data capture, and structured data reporting. ESCALATE simplifies the initial data collection process, and its reporting and experiment generation mechanisms simplify machine learning integration. In this way it helps turn automated and semi-automated laboratory experimentation into a subroutine that can be called by external programmers, filling an unmet need that is between that of traditional electronic laboratory notebook (ELN) software and more heavy-duty automation solutions. In this talk, I will discuss "lessons learned" from an initial ESCALATE implementation for metal halide perovskite discovery, which has been used to perform thousands of algorithmically-controlled experiments at multiple laboratory sites, with participants across the country.

Experiment specification, capture and laboratory automation technology (ESCALATE): Software pipeline for automated chemical experimentation and data management, with application to metal halide perovskite discovery

2019 Fall National Meeting

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