Reinforcement Mechanisms in Core@Shell <scp>ZnO</scp> / <scp>PP</scp> Composites: Machine Learning‐Driven Filler Optimization and Interfacial Engineering Strategies for Enhanced Mechanical Performance

ABSTRACT This study presents a core‐shell engineering and machine learning strategy to optimize calcium carbonate/zinc oxide fillers (CaCO 3 @ZnO) for reinforcing polypropylene (PP) composites. By precisely controlling ZnO shell thickness, the core‐shell fillers achieved significant ZnO reduction while simultaneously enhancing both antibacterial and mechanical properties at ≤ 15 wt% loading, surpassing the limitations of conventional high‐zinc toughening approaches. Machine learning analysis (XGBoost/Random Forest) identified CaO's predominant contribution to mechanical performance, highlighting interfacial engineering as the critical reinforcement mechanism. A data‐driven multiscale model established quantitative correlations among core‐shell architecture, interfacial characteristics, and macroscopic properties.