Synthesis and Machine Learning Prediction of High Entropy Multi-Principal Element Nanoparticles

The vast compositional space of multi-principal element nanoparticles (MPENs), along with their unique properties and diverse applications, has garnered significant attention from the research community. MPENs exhibit unique properties, high configurational entropy, multi-element synergy, and long-range atomic ordering, featuring distinct sublattices of semi-metallic or metallic components. This review reports the recent approaches described in the literature, highlighting their commonalities and differences, and classifies them into general strategies. This report discusses in detail the synthesis approaches of single-phase MPENs. To integrate experimental validation with computational preselection, machine learning (ML) offers the opportunity to establish relationships between lattice structures, properties, and phase formations and how collect and analysis of experimental data. Additionally, challenges such as ML-guided uncertainty quantification and materials design are explored.