Transition metal phosphates (TMPs) are extensively explored for electrochemical and catalytical applications due to their structural versatility and chemical stability. Within this material class, novel high-entropy metal phosphates (HEMPs)─containing multiple transition metals combined into a single-phase structure─are particularly promising, as their compositional complexity can significantly enhance functional properties. However, the discovery of suitable HEMP compositions is hindered by the vast compositional design space and complex or very specific synthesis conditions. Here, we present a data-driven strategy combining automated wet-chemical synthesis with a Sequential Learning App for Materials Discovery (SLAMD) framework (Random Forest regression model) to efficiently explore and optimize HEMP compositions. Using a limited set of initial experiments, we identified multimetal compositions in a single-phase crystalline solid. The model successfully predicted a novel Co0.3Ni0.3Fe0.2Cd0.1Mn0.1 phosphate octahydrate phase, validated experimentally, demonstrating the effectiveness of the machine learning approach. This work highlights the potential of integrating automated synthesis platforms with data-driven algorithms to accelerate the discovery of high-entropy materials, offering an efficient design pathway to advanced functional materials.
