Monthly Meeting

Technical Program

“Navigating Chemical Experiments with AI and Automation”

First, we proposed a novel ML-guided materials discovery platform that combines synergistic innovations in automated flow synthesis and automated machine learning (AutoML) method development. A software-controlled, continuous polymer synthesis platform enables rapid iterative experimental–computational cycles that result in the synthesis of hundreds of unique copolymer compositions within a multi-variable compositional space. The non-intuitive design criteria identified by ML, accomplished by exploring less than 1% of overall compositional space, upended conventional wisdom in the materials design.

Second, many chemical methods, such as HPLC, still require experimental setup based on domain-knowledgeable human experts. Experimental automation coupled with autonomy in the Cloud Lab environment has led to substantial growth in the availability of historical data on HPLC method development. This highlighted the need for automatic on-the-fly validation of acquired experimental results. Herein, we developed an automated ML-based approach to characterize HPLC data retrospectively and autonomously validate the massive parallel HPLC execution at the CMU Cloud Lab facility.