Asset Details
Do you wish to reserve the book?
Machine Learning-Driven Exploration of Cesium-Based All-Inorganic Mixed-Halide Perovskite Solar Cells with a Double Absorber Layer Architecture
Hey, we have placed the reservation for you!
By the way, why not check out events that you can attend while you pick your title.
Oops! Something went wrong.
Looks like we were not able to place the reservation. Kindly try again later.
Are you sure you want to remove the book from the shelf?
Machine Learning-Driven Exploration of Cesium-Based All-Inorganic Mixed-Halide Perovskite Solar Cells with a Double Absorber Layer Architecture
Do you wish to request the book?
Machine Learning-Driven Exploration of Cesium-Based All-Inorganic Mixed-Halide Perovskite Solar Cells with a Double Absorber Layer Architecture
Please be aware that the book you have requested cannot be checked out. If you would like to checkout this book, you can reserve another copy
We have requested the book for you!
Your request is successful and it will be processed during the Library working hours. Please check the status of your request in My Requests.
Oops! Something went wrong.
Looks like we were not able to place your request. Kindly try again later.
Journal Article
Machine Learning-Driven Exploration of Cesium-Based All-Inorganic Mixed-Halide Perovskite Solar Cells with a Double Absorber Layer Architecture
2024
Overview
Over the past two decades, organic–inorganic hybrid perovskites have shown continuous improvement in photovoltaic performance. However, thermal instability and the presence of lead are still issues, and research efforts are aimed at combatting this. In addition, high power conversion efficiency remains the primary goal. Cesium-based inorganic perovskite compounds have emerged with more stable performance against varying environmental conditions. In this study, a low-lead cesium-based all-inorganic mixed-halide perovskite solar cell (IMH-PSC) was designed using the SCAPS-1D simulator. To enhance the photon absorption, a double-absorber-layer perovskite solar cell (DAL-PSC) architecture was considered for absorption of the high-/low-energy photons in the top/bottom perovskite layer (TPL/BPL), respectively. The IMH perovskites used in the DAL-PSC included CsPb0.625Zn0.375I2Br, CsPb0.625Zn0.375I2Cl, and CsPb0.625Zn0.375IBr2. After the performance of the DAL-IMH-PSC was analysed using SCAPS, machine learning models were trained and tested to predict the photovoltaic (PV) parameters and to determine the impact of input parameters such as absorber layer thickness and defect density on the PV performance of the DAL-IMH-PSC design. Using SCAPS-1D, a dataset of 29,400 combinations was extracted with varied input parameters: TPL thickness from 0.05 μm to 1 μm, BPL thickness from 0.05 μm to 0.5 μm, and TPL/BPL defect density from 1 × 1012 cm−3 to 1 × 1018 cm−3. The DAL-IMH-PSC layered as fluorine-doped tin oxide (FTO)/TiO2/CsPb0.625Zn0.375I2Cl/CsPb0.625Zn0.375IBr2/Spiro-MeOTAD/back electrode delivered the highest power conversion efficiency (PCE), at 30.36%. The random forest and extreme gradient boosting algorithms showed the best prediction performance. In addition, features of importance were identified with the help of SHAP (SHapley Additive exPlanations) plots, which showed the inverse dependence of bottom defect density on PCE.
