Zhenlong Li, Haoyang Li, Pascal Kaienburg, Moritz Riede, University of Oxford, Oxford, United Kingdom
We have successfully characterized our fabrication equipment to intentionally generate controlled inhomogeneities in thin-film thickness and composition. Leveraging these controllable inhomogeneities, we applied regression analysis to develop a reliable model that simulates the spatial distribution of evaporated organic semiconductors within the vacuum chamber. As shown in Figure 1, we further established systematic workflows for characterization and data acquisition, enabling high-throughput optimization of thin-film thickness and composition in organic solar cells and investigation of their correlations with device performance, including open-circuit voltage (Voc), short-circuit current (Jsc), fill factor (FF), and overall power conversion efficiency (PCE). Building on this methodology, we employed a machine learning model to predict the physical properties of evaporated organic semiconductor films. To demonstrate the approach, we optimized the total thickness and component ratio of a zinc phthalocyanine (ZnPc):C_₆₀ bulk heterojunction (BHJ) in a typical vacuum-deposited organic solar cell and achieved accurate predictions of the optical constants of the ZnPc:C_₆₀ BHJ.