Machine Learning-Enabled Optical Architecture Design of Perovskite Solar Cells
Zong-Zheng Li, Chaorong Guo, Wenlei Lv, Peng Huang, Yongyou Zhang
Abstract
Perovskite solar cells, emerging as a cutting-edge solar energy technology, have demonstrated a power conversion efficiency (PCE) of >26%, which is below the theoretical limit of 33%. This study, employing a combination of neural network models and high-throughput simulation calculations, taking the single-junction FAPbI 3 cell as an illustrative example, indicates that a pyramid structure, in comparison of a planar one, can increase the highest J sc to 27.4 mA/cm 2 and the PCE to 28.4%. Both J sc and PCE surpass the currently reported experimental results. The optimized periodicity and tilt angle of the pyramid structure align with the textured structure of crystalline silicon solar cells. These results underscore the substantial development potential of neural network inverse design based on high-throughput calculations in the field of optoelectronic devices and provide theoretical guidance for the design of monolithic perovskite–silicon tandem solar cells.