Abstract
Appropriate energy-level alignment in non-fullerene ternary organic solar cells (OSCs) can enhance the power conversion efficiencies (PCEs), due to the simultaneous improvement in charge generation/transportation and reduction in voltage loss. Seven machine-learning (ML) algorithms were used to build the regression and classification models based on energy-level parameters to predict PCE and capture high-performance material combinations, and random forest showed the best predictive capability. Furthermore, two sets of verification experiments were designed to compare the experimental and predicted results. The outcome elucidated that a deep lowest unoccupied molecular orbital (LUMO) of the non-fullerene acceptors can slightly reduce the open-circuit voltage (V OC) but significantly improve short-circuit current density (J SC), and, to a certain extent, the V OC could be optimized by the slightly up-shifted LUMO of the third component in non-fullerene ternary OSCs. Consequently, random forest can provide an effective global optimization scheme and capture multi-component combinations for high-efficiency ternary OSCs.