A Machine Learning–Based Design Rule for Improved Open‐Circuit Voltage in Ternary Organic Solar Cells

Abstract

Organic solar cells (OSCs) based on ternary blends are among the most promising photovoltaic technologies. To further improve the power conversion efficiency (PCE), the materials selection criteria must be focused on achieving high open-circuit voltage (V oc ) through the alignment of the energy levels of the ternary blends. Hence, machine-learning approaches are in high demand for extracting the complex correlation between V oc and the energy levels of the ternary blends, which are crucial to facilitate device design. Herein, the datadriven strategies are used to generate a model based on the available experimental data, and the V oc is then predicted using available machine-learning methods (the Random Forest regression and the Support Vector regression). In addition, the Random Forest regression is developed to find the appropriate energy-level alignment of ternary OSCs and to reveal the relationship between V oc and electronic features. Finally, an analysis based on the ranking of variables in terms of importance by the Random Forest model is performed to identify the key feature governing the V oc and the performance of ternary OSCs. From the perspective of device design, the machine-learning approach provides sufficient insights to improve the V oc and advances the comprehensive understanding of ternary OSCs.

Unraveling the Mystery of Ternary Organic Solar Cells: A Review on the Influence of Third Component on Structure–Morphology–Performance Relationships

“…While the increase in complexity in computer simulations may incur a higher cost, recently the hope is to incorporate the benefits of artificial intelligence, particularly machine learning to better screen third components at a much‐reduced computational cost. In the context of TOSCs, the integration of machine learning is currently pioneered by Lee to correlate energy levels of the ternary blend to V oc via machine learning methods such as Random Forest regression and Support Vector regression, [ 206 ] and also to correlate to PCE. [ 207 ]…”

Slot-Die-Coated Ternary Organic Photovoltaics for Indoor Light Recycling

“…44 In contrast, OPVs with FBT:PC 61 BM active layers had PCEs of 8 and 14% under 1 sun and 1000 lux illumination, respectively, but with V oc values of 0.78 V or less. 44 Inspired by the result that PDI could significantly raise the V oc of PBDB-T:PC 61 BM-based OPVs when used as a third component, 43,45 we hypothesized that ternary blends of FBT:PC 61 BM:PDI could deliver OPVs with both high V oc and PCE and have utility as indoor light recycling devices.…”

Relationship between the VOC Tuning Effect and the Interface Activation Energy Due to the Third Component Concentration in Ternary Organic Solar Cells

“…24 This cathode has resulted to be reliable not only to fabricate relatively good devices but also to study charge recombination phenomena occurring in organic solar cells. 17 For more information about this alternative cathode, interface contact, performance, and so forth, see previous studies. 32,33 The FF is the parameter that limits the efficiency of the herein-reported devices in comparison with those reported in the literature; however, it does not play any role in our analysis, which is focused on V OC .…”