Capture the high-efficiency non-fullerene ternary organic solar cells formula by machine-learning-assisted energy-level alignment optimization.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 34553173.
- Also identified by DOI 10.1016/j.patter.2021.100333 and PMC identifier 8441578.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
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 (<i>V</i> <sub>OC</sub>) but significantly improve short-circuit current density (<i>J</i> <sub>SC</sub>), and, to a certain extent, the <i>V</i> <sub>OC</sub> 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.