AI-driven robot enables synthesis-property relation prediction for metal halide perovskites in humid atmosphere

Materials Acceleration Platforms (MAPs) – also known as self-driving laboratories, present a new paradigm for materials science and promise an order of magnitude accelerated materials discovery and optimization compared to the traditional trial and error approach. Metal halide perovskites (MHPs) are an emerging class of materials for optoelectronic applications but are plagued by irreproducible optoelectronic quality, in particular for films fabricated in humid atmosphere. This challenge is widely observed across various inorganic material synthesis processes. Automating decision-making hinges on the challenge to reduce data to machine-readable metrics that accurately represent the material quality. Here we develop a machine learning (ML)-guided closed-loop platform (AutoBot) with a multimodal data fusion approach combining results from three characterization techniques to predict synthesis - property relations for the optical quality of MHP thin films in relative humidities (RHs) ranging from 5 - 55%. The efficiency of this approach is confirmed by the fast-dropping learning rate to 2% after experimentally sampling less than 1% of the possible 5,000+ combinations. The validation of predicted synthesis - property relations was done by in situ photoluminescence characterization and revealed an avenue for controlling the MHP crystallization by fine-tuning the synthesis, MACl additive, and RH. Doing so decreases the energetic barrier to form heterogeneously nucleating photo-active MHP. By adjusting the antisolvent drop time, comparable MHP film quality can be obtained in a relative humidity window between 5 - 25% lifting the need for stringent atmosphere control. Our MAP enables an accelerated screening and understanding of the synthesis design space, facilitating rational synthesis recipe choice and higher reproducibility for a wide range of materials.