Maximizing performance in Cs₂CuBiCl₆ perovskite cells through machine learning-driven absorber layer parameter analysis

Abstract

Conventional perovskite materials offer reasonable power conversion efficiency (PCE) but are plagued by stability issues. To address this, researchers have explored alternative materials, such as MA and FA-based lead or lead-free perovskites, known for their improved PCE and stability. In this study, we focused on a cesium (Cs)-based cell, Cs₂CuBiCl₆, which not only exhibits acceptable PCE but also demonstrates superior stability compared to traditional perovskite materials. To optimize the Cs₂CuBiCl₆-based cell, we conducted simulations varying parameters like thickness, bulk defect density (BDD), and doping. The optimized PCE for the Cs₂CuBiCl₆-based cell reached 10.30 %. We generated 1000 datasets through simulations, which serve as input for machine learning (ML) algorithms, including random forest (RF) and XGboost (XGB). The XGB model outperformed the RF model, achieving a higher R-squared value (R2: 99.97 %) and a lower mean squared error (MSE: 0.0014).