Comprehensive review of advances in machine-learning-driven optimization and characterization of perovskite materials for photovoltaic devices

Abstract

Perovskite solar cells (PSCs) have developed rapidly, positioning them as potential candidates for next-generation renewable energy sources. However, conventional trial-and-error approaches and the vast compositional parameter space continue to pose challenges in the pursuit of exceptional performance and high stability of perovskite-based optoelectronics. The increasing demand for novel materials in optoelectronic devices and establishment of substantial databases has enabled data-driven machine-learning (ML) approaches to swiftly advance in the materials field. This review succinctly outlines the fundamental ML procedures, techniques, and recent breakthroughs, particularly in predicting the physical characteristics of perovskite materials. Moreover, it highlights research endeavors aimed at optimizing and screening materials to enhance the efficiency and stability of PSCs. Additionally, this review highlights recent efforts in using characterization data for ML, exploring their correlations with material properties and device performance, which are actively being researched, but they have yet to receive significant attention. Lastly, we provide future perspectives, such as leveraging Large Language Models (LLMs) and text-mining, to expedite the discovery of novel perovskite materials and expand their utilization across various optoelectronic fields.