Mass-customization of organic photovoltaics and data production for machine learning models precisely predicting device behavior

Abstract

High-throughput experimentation (HTE) combined with machine learning (ML) has emerged as a powerful tool to accelerate material discovery and optimize fabrication processes. However, in photovoltaics field, only a few studies have successfully applied this approach using industrially relevant techniques, roll-to-roll (R2R) process. We developed universal and extendable data structure for ML training that accommodates upcoming materials while retaining compatibility with existing dataset. Using MicroFactory platform, which enables mass-customization of organic photovoltaics (OPVs), we fabricated and characterized over 26,000 unique cells within four days. To guide selection of ML model for precisely predicting device behavior, photovoltaic parameter and J–V prediction models to forecast device parameters and J–V curves were developed, respectively. Random forest model proved most effective, achieving a PCE of 11.8% (0.025 cm²)—the highest record for fully R2R-fabricated OPVs. By integrating accumulated datasets with smaller new-component datasets, we enhanced model performance for PM6:Y6:IT-4F and PM6:D18:L8-BO systems, showing that models trained on binary systems can predict ternary performance and enabling the development of generalized ML models for future high-performance materials.