Y6 and its derivatives have greatly improved the power conversion efficiency (PCE) of organic photovoltaics (OPVs). Further developing high-performance Y6 derivative acceptor materials through the relationship between the chemical structures and properties of these materials will help accelerate the development of OPV. Here, machine learning and quantum chemistry are used to understand the structure-property relationships and develop new OPV acceptor materials. By encoding the molecules with an improved one-hot code, the trained machine learning model shows good predictive performance, and 22 new acceptors with predicted PCE values greater than 17% within the virtual chemical space are screened out. Trends associated with the discovered high-performing molecules suggest that Y6 derivatives with medium-length side chains have higher performance. Further quantum chemistry calculations reveal that the end acceptor units mainly affect the frontier molecular orbital energy levels and the electrostatic potential on molecular surface, which in turn influence the performance of OPV devices. A series of promising Y6 derivative candidates is screened out and a rational design guide for developing high-performance OPV acceptors is provided. The approach in this work can be extended to other material systems for rapid materials discovery and can provide a framework for designing novel and promising OPV materials.
Keywords: density functional theory (DFT); electrostatic potential (ESP); machine learning; non-fullerene acceptors; organic photovoltaics.
© 2022 The Authors. Advanced Science published by Wiley-VCH GmbH.