Chemical Robotics Enabled Exploration of Stability in Multicomponent Lead Halide Perovskites via Machine Learning

Metal halide perovskites have attracted immense interest as a promising material for a variety of optoelectronic and sensing applications. However, issues regarding long-term stability have emerged as the key bottleneck for commercialization. Here, we develop an automated experimental workflow based on combinatorial synthesis and rapid throughput characterization to explore long-term stability of these materials in ambient conditions. We apply it to four model perovskite systems: MA x FA y Cs1–x–y PbBr3, MA x FA y Cs1–x–y PbI3, Cs x FA y MA1–x–y Pb­(Br x+y I1–x–y )3, and Cs x MA y FA1–x–y Pb­(I x+y Br1–x–y )3. Non-negative matrix factorization and Gaussian process regression are used to interpolate the photoluminescent behavior of the phase diagram. This interpolative regression analysis helps to distinguish mixtures that form solid solutions from those that segregate into multiple materials, pointing out the most stable regions of the phase diagram. We find stability dependence on composition to be nonuniform within the composition space, suggesting the presence of potential preferential compositional regions. This proposed workflow is universal and can be applied to other solution-processable materials.