Unraveling Correlations between Molecular Properties and Device Parameters of Organic Solar Cells Using Machine Learning

Understanding the relationships between molecular properties and device parameters is highly desired not only to improve the overall performance of an organic solar cell but also to fulfill the requirements of a device for a particular application such as solar-to-fuel energy conversion (high open-circuit voltage (V_OC)) or solar window applications (high short circuit current (J_SC)). In this work, a series of machine learning models are built for three important device characteristics (V_OC, J_SC, and fill factor) using 13 crucial molecular properties as descriptors, resulting in an impressive predictive performance (r = 0.7). These models may play a vital role in designing promising organic materials for a specific photovoltaic application with high V_OC/J_SC. The importance of descriptors for each device parameter is unraveled, which may assist in tuning them and improve understanding of the energy conversion process.