Exploring KGeCl3 3 material for perovskite solar cell absorber layer through different machine learning models

The existing designs of perovskite based solar cells frequently encounter issues with poor photovoltaic (PV) performance and stability issues. In this study, to address above issues, we investigate a novel solar cell device featuring layers of tin dioxide (SnO2), 2 ), fullerene (C60), 60 ), potassium germanide chloride (KGeCl3), 3 ), and Me4PACz. SnO2, 2 , serving as the electron transport layer (ETL), offers high electron mobility and compatibility with solution processing techniques. Further, different machine learning (ML) algorithms have been utilized for the prediction of accurate PCE prediction in order to simplify computations and improve accuracy. The complex interactions between these parameters and their combined impact on device stability and efficiency are shown through systematic experimentation with SCAPS 1d and 1000 datasets have been generated. Impressive PV parameters are obtained by optimization: VOC: OC : 1.13 V, JSC: SC : 23.47 mA/cm2, 2 , FF: 73.34 %, and PCE: 19.62 %. Ensemble machine learning techniques, such as XGBoost (XGB), perform better than individual models, exhibiting increased accuracy and resilience across a range of machine learning performance metrics. When compared to individual SVR, RF and stacked SVR & RF the MSE value produced by the XGB (0.150) algorithm is significantly lower. However, out of all the ML algorithms in this study, the R2 2 value found in XGB (99.60 %) is the best. The boosting strategy used by XGB is notable for how well it handles complicated datasets and enhances PCE prediction in solar cells. After finding the best suited models (RF & XGB), mean and standard deviation have also been calculated for the different ML performance matrices like MSE, R2 2 and CVS for 10 iterations. The development of innovative perovskite base PSCs without the need for tedious and lengthy simulations may be facilitated by this approach.