This study compares the microstructure and properties of pure Cu and Cu-5 wt.% Al2O3 composites fabricated by spark plasma sintering under strictly identical processing conditions at 800-1000°C. Pure Cu samples achieved near-full densification and exhibited a bimodal grain structure dominated by coarse grains with increasing sintering temperature. In contrast, the composite samples showed lower density and non-monotonic densification behavior, with a minimum relative density at 900°C and significantly refined equiaxed grains due to strong grain-boundary pinning by nano Al2O3 particles. The higher fractions of high-angle boundaries and pronounced orientation disruption were observed in the composite samples, while high-resolution analysis confirmed the presence of grain-boundary Al2O3-rich regions that restricted Cu grain coalescence and continuity of grain boundary migration. X-ray diffraction results confirmed the absence of reaction phases in both materials. Hardness peaked at 900°C for both samples, and the composite samples showed consistently lower hardness due to retained porosity. The apparent electrical conductivity of the composite displays a non-linear temperature dependence, reflecting the competing influences of densification, microstructural recovery, and the insulating nature of Al2O3.

High-entropy alloys (HEAs) exhibit complex phase formation behavior, challenging conventional predictive methods. This study presents a machine learning (ML) framework for phase prediction in HEAs, using a curated dataset of 648 experimentally characterized compositions and features derived from thermodynamic and electronic descriptors. Three classifiers—random forest, gradient boosting, and CatBoost—were trained and validated through cross-validation and testing. Gradient boosting achieved the highest accuracy, and valence electron concentration (VEC), atomic size mismatch (δ), and enthalpy of mixing (ΔHmix) were identified as the most influential features. The model predictions were experimentally verified using a non-equiatomic Al30Cu17.5Fe17.5Cr17.5Mn17.5 alloy and the equiatomic Cantor alloy (CoCrFeMnNi), both of which showed strong agreement with predicted phase structures. The results demonstrate that combining physically informed feature engineering with ML enables accurate and generalizable phase prediction, supporting accelerated HEA design.