Machine-Learning-Assisted Screening of Interface Passivation Materials for Perovskite Solar Cells

Abstract

Interface passivation using an ammonium salt can effectively improve the power conversion efficiency (PCE) of perovskite solar cells (PSCs). Despite significant PCE improvement achieved in previous studies, the selection criteria for ammonium salts are not fully understood. Here we apply a machine-learning (ML) method to investigate the relationship between the molecular features of ammonium salts and the PCE improvement of PSCs. We establish an ML model using an experimental data set of 19 salts to predict the PCE improvement after passivation. Three molecular features (hydrogen bond donor, hydrogen atom, and octane−water partition coefficient) are identified as the most important features of selecting an ammonium salt for passivation. The ML model is further used to screen ammonium salts from a pool of 112 salts in the PubChem database. FAMACs and FAMA-based PSCs fabricated with a model-recommended salt (2-phenylpropane-1aminium iodide) achieve PCEs of 22.36% and 24.47%, respectively.

Trap State Passivation for Stabilizing Perovskite Solar Cells via Multifunctional Molecules

“…(b) Flowchart for the machine-learning-assisted screening concept. Reprinted with permission from ref . Copyright 2023 American Chemical Society.…”

“…(c) Comparison of the PCE enhancement ratio between literature and prediction with the similar device architecture. Reprinted with permission from ref . Copyright 2023 American Chemical Society.…”

“…Organic ammonium salts with an extra anchoring group could be more effective because of their dual role of 2D layer formation and defect passivation with the anchoring group. Recently, machine learning (ML) techniques have been applied to explore the structure–property relation of the ammonium salts with defect passivation and efficiency enhancement of PSCs . The method has been applied to a pool of 112 ammonium salts in the PubChem database, which recommended 2-phenylpropane-1-aminium iodide as the most effective passivation molecule.…”

“…Recently, machine learning (ML) techniques have been applied to explore the structure−property relation of the ammonium salts with defect passivation and efficiency enhancement of PSCs. 30 The method has been applied to a pool of 112 ammonium salts in the PubChem database, which recommended 2-phenylpropane-1-aminium iodide as the most effective passivation molecule. A schematic illustration of the ML-assisted screening concept is shown in Figure 2b.…”

Perovskite Surface Passivation Using Thiophene-Based Small Molecules for Efficient and Stable Solar Cells

“…Note that we did not make any modification to the SnO 2 electron-transport layer or the SnO 2 /perovskite interface, which has a dominated influence on the hysteresis for the device with the n−i−p structure. 45,46 In the next step, the enhancement of carrier transport across the interface of the perovskite/electron transport layer will be designed to further improve the conversion efficiency and suppress the hysteresis of PSCs.…”