Machine-learning-assisted discovery of mechanosynthesized lead-free metal halide perovskites for the oxidative photocatalytic cleavage of alkenes

Abstract

Lead-free metal halide perovskites can potentially be air- and water-stable photocatalysts for organic synthesis, but there have been limited studies on them for this application. Separately, machine learning (ML), a critical subfield of artificial intelligence, has played a pivotal role in identifying correlations and formulating predictions based on extensive datasets. Herein, we describe an iterative workflow by incorporating high-throughput experimental data with ML to discover new lead-free metal halide perovskite photocatalysts for the aerobic oxidation of styrene. Through six rounds of ML optimization guided by SHapley Additive exPlanations (SHAP) analysis, we identified BA2CsAg0.95Na0.05BiBr7 as a photocatalyst that afforded an 80% yield of benzoic acid under our standard conditions, which is a 13-fold improvement compared to the 6% that we started with when using Cs2AgBiBr6 as the initial photocatalyst benchmark. We demonstrated that BA2CsAg0.95Na0.05BiBr7 could tolerate various functional groups with 22 styrene derivatives, highlighting the generality of the photocatalytic properties. Radical scavenging studies and density functional theory calculations revealed that formation of the reactive oxygen species superoxide and singlet oxygen in the presence of BA2CsAg0.95Na0.05BiBr7 were critical for the photocatalysis.