Performance optimization and machine learning-guided parameter sensitivity analysis of lead-free KGeCl3 perovskite solar cells

Abstract

This study gives a realistic insight into the effectiveness of lead-free Ge-based perovskite solar cells (PSCs) using KGeCl₃ as the absorber layer in combination with four different electron transport layers (ETLs), including WS₂, ZnSe, PC₆₀BM, and SnS₂, with copper iron tin sulfide (CFTS) serving as the hole transport layer (HTL). Initially, key material parameters such as layer thickness, donor density (N_D), acceptor density (N_A), defect density (N_t), interface defect densities (IL1 & IL2), series resistance (R_s), shunt resistance (R_sh), operating temperature (K), and back contact work function (eV) are varied using a SCAPS-1D simulator to optimize device performance. Between the four cell configurations, the FTO/CFTS/KGeCl₃/WS₂/Au structure has achieved the highest performance with a power conversion efficiency (PCE) of 21.39%, short-circuit current density (J_SC) of 39.526 mA cm⁻², fill factor (FF) of 76.56%, and open-circuit voltage (V_OC) of 0.706 V at a simulated temperature of 300 K. Other configurations using ZnSe, PC₆₀BM, and SnS₂ as ETLs showed PCE values of 21.38%, 21.05%, and 20.43%, respectively. Furthermore, an integrated machine learning framework with four supervised learning methods, i.e., Random Forest, XGBoost, CatBoost, and Decision Tree, has been utilized to effectively evaluate the importance of material features. Out of the algorithms, CatBoost has the highest performance with R² and accuracy values of 0.984 and 99.344%, respectively.