Application of machine learning in perovskite materials and devices: A review

Abstract

Metal-halide hybrid perovskite materials are excellent candidates for solar cells and photoelectric devices. In recent years, machine learning (ML) techniques have developed rapidly in many fields and provided ideas for material discovery and design. ML can be applied to discover new materials quickly and effectively, with significant savings in resources and time compared with traditional experiments and density functional theory (DFT) calculations. In this review, we present the application of ML in perovskites and briefly review the recent works in the field of ML-assisted perovskite design. Firstly, the advantages of perovskites in solar cells and the merits of ML applied to perovskites are discussed. Secondly, the workflow of ML in perovskite design and some basic ML algorithms are introduced. Thirdly, the applications of ML in predicting various properties of perovskite materials and devices are reviewed. Finally, we propose some prospects for the future development of this field. The rapid development of ML technology will largely promote the process of materials science, and ML will become an increasingly popular method for predicting the target properties of materials and devices.