Speaker
Description
The versatility of organic molecules generates a rich design space for organic semiconductors (OSCs) considered for electronics applications. Offering unparalleled promise for materials discovery, the vastness of this design space also dictates efficient search strategies. Here, we present different strategies that explore vast OSC design spaces and evaluate the suitability of OSC candidates on the basis of charge injection and mobility descriptors. We also discuss their strengths and weaknesses. Among them, an active machine learning (AML) approach explores an unlimited search space through consecutive application of molecular morphing operation and queries predictive-quality first-principles calculations to build a refining surrogate model.[1] This optimized AML approach rapidly identifies well-known and hitherto unknown molecular OSC candidates with superior charge conduction properties. Additionally, we critically assess and systematically improve supervised ML models for reorganization energies of flexible molecules.
[1] Nat. Commun. 12, 2422 (2021).
