The incorporation of hydrogen bonding motifs into organic semiconductive polymers (SP) has been shown to be beneficial for material properties as they can aid in self-assembly, improve mechanical properties intrinsically (stretchability, self-healing), and modulate electronic performance. Despite these reported advantages, the fundamental implications of hydrogen bonding in polymer processing as a methodology for optimizing device performance (charge transport, mechanical properties) has yet to be explored and could provide novel insights for future material designs. Here, we present a machine learning (ML) driven approach where Bayesian optimization coded robotic platform (dubbed “Polybot”) that automates the doctor-blading of a series of amide containing SPs towards optimize charge transport in, uncovering trends in processing conditions such as anisotropic charge transport and relation of hydrogen bonding content to overall OFET hole transport mobility. The combination of ML driven processing of SPs provides new insights into designing materials and relating their performance to processing conditions, ultimately providing new dimensional parameters with regards to rational chemical structure design and device fabrication.

Uncovering trends in hydrogen-bonding containing semiconductive polymers using Bayesian optimization driven machine learning

Where thousands of chemistry professionals meet to share ideas and advance scientific and technical knowledge. Spring 2023 abstracts, posters, and presentations will launch at the end of March.

ACS Spring 2023

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