Understanding Causalities in Organic Photovoltaics Device Degradation in a Machine‐Learning‐Driven High‐Throughput Platform

• Published in: Advanced materials (Weinheim) Vol. 36; no. 20; pp. e2300259 - n/a
• Main Authors: Liu, Chao, Lüer, Larry, Corre, Vincent M. Le, Forberich, Karen, Weitz, Paul, Heumüller, Thomas, Du, Xiaoyan, Wortmann, Jonas, Zhang, Jiyun, Wagner, Jerrit, Ying, Lei, Hauch, Jens, Li, Ning, Brabec, Christoph J.
• Format: Journal Article
• Language: English
• Published: Germany Wiley Subscription Services, Inc 01.05.2024
• Subjects: Cost analysis; device stability; Diffusion layers; Energy conversion efficiency; Gaussian process; Gaussian process regression (GPR) prediction; linear Pearson correlations; Machine learning; Microstructure; Morphology; organic solar cells; Photovoltaic cells; Process parameters; Solar cells; Stability; Thickness; organic solar cells; device stability; machine learning; linear Pearson correlations; Gaussian process regression (GPR) prediction
• ISSN: 0935-9648; 1521-4095
• DOI: 10.1002/adma.202300259

Organic solar cells (OSCs) now approach power conversion efficiencies of 20%. However, in order to enter mass markets, problems in upscaling and operational lifetime have to be solved, both concerning the connection between processing conditions and active layer morphology. Morphological studies supporting the development of structure–process–property relations are time‐consuming, complex, and expensive to undergo and for which statistics, needed to assess significance, are difficult to be collected. This work demonstrates that causal relationships between processing conditions, morphology, and stability can be obtained in a high‐throughput method by combining low‐cost automated experiments with data‐driven analysis methods. An automatic spectral modeling feeds parametrized absorption data into a feature selection technique that is combined with Gaussian process regression to quantify deterministic relationships linking morphological features and processing conditions with device functionality. The effect of the active layer thickness and the morphological order is further modeled by drift–diffusion simulations and returns valuable insight into the underlying mechanisms for improving device stability by tuning the microstructure morphology with versatile approaches. Predicting microstructural features as a function of processing parameters is decisive know‐how for the large‐scale production of OSCs. A machine‐learning‐driven high‐throughput workflow for solution‐processed organic solar cells is presented, identifying causal relationships between process conditions and active layer morphology, and between morphology and stability. Using only inexpensive and fast optical probes, quantitative structure–property relationships are obtained that improve the understanding and control of electrical performance degradation.