Data-Driven Fine Element Tuning of Halide Double Perovskite for Enhanced Photoluminescence

Element tuning of targeted materials and obtaining the optimal synthesis recipe are major goals for many material scientists. However, this is often limited by conventional trial-and-error procedures, which are time-consuming and labor-intensive. In this work, fine element tuning of halide double perovskite Cs2NaxAg1-xInyBi1-yCl6 is conducted by performing a data-driven investigation combining high-throughput experiments with machine learning (ML). A positive correlation between the more accessible R value in emission RGB values (the intensities of the red/green/blue primary colors) and photoluminescence intensity is revealed, and over a thousand R values of the Cs2NaxAg1-xInyBi1-yCl6 crystals synthesized with different additives and element compositions are collected. More importantly, the volume ratios of Na+/Ag+ (VNa: VAg) and Bi3+/In3+ (VBi: VIn) with the corresponding R values are correlated through ML, and the synergistic regulation of the two ion pairs is revealed. A possible correlation between R and XRD is also proposed. Finally, different emission intensities of LED beads coated with Cs2NaxAg1-xInyBi1-yCl6 synthesized using parameters obtained from ML are demonstrated, and an emission enhancement of approximate to 50 times is observed between the brightest and dimmest LEDs. This work illustrates that data-driven investigation helps guide material synthesis and will significantly reduce the workload for developing novel materials, especially for complex compositions. Machine learning (ML) and high-throughput experiments are integrated as a data-driven approach for the fine element tuning of the halide double perovskites (HDP). The ML model correlating the synthesis parameters of HDP with the corresponding photoluminescence (PL) strength is obtained for guiding the synthesis of target HDP with enhanced PL.image