A Data-Driven Platform for Two-Dimensional Hybrid Lead-Halide Perovskites

Theexceptional properties of two-dimensional hybrid organic-inorganiclead-halide perovskites (2D HOIPs) have led to a rapid increase inthe number of low-dimensional materials for optoelectronic engineeringand solar energy conversion. The flexibility and controllability of2D HOIPs create a vast structural space, which presents an urgentissue to effectively explore 2D HOIPs with better performance forpractical applications. However, the traditional RP-DJ classificationmethod falls short in describing the influence of structure on theelectronic properties of 2D HOIPs. To overcome this limitation, weemployed inorganic structure factors (SF) as a classification descriptor,which considers the influence of inorganic layer distortion of 2DHOIPs. And we investigated the relationship between SF, other physicochemicalfeatures, and band gaps of 2D HOIPs. By using this structural descriptoras a feature for a machine learning model, a database of 304920 2DHOIPs and their structural and electronic properties was generated.A large number of previously neglected 2D HOIPs were discovered. Withthe establishment of this database, experimental data and machinelearning methods were combined to develop a 2D HOIPs exploration platform.This platform integrates searching, download, analysis, and onlineprediction, providing a useful tool for the further discovery of 2DHOIPs.