Phase-stability-guided explainable machine learning for mechanical-property prediction and experimentally supported candidate screening of high-entropy alloys

Abstract

High-entropy alloys (HEAs) provide a broad compositional space for developing structural materials with balanced phase stability and mechanical performance. However, reliable mechanical-property prediction remains challenging because alloy chemistry, phase constitution, processing state, and model uncertainty are strongly coupled. We developed a phase-stability-guided explainable machine learning framework using a curated database comprising 541 phase-labelled HEAs, 263 hardness-labelled records, and 214 yield-strength-labelled records. Hierarchical physical and processing descriptors were combined with leakage-controlled phase-probability features generated through composition-level nested cross-fitting. XGBoost and CatBoost models were used for property prediction, bootstrap ensembles for uncertainty quantification, and SHAP and accumulated local effects for model interpretation. A total of 300,000 virtual candidates were screened, followed by CALPHAD-assisted assessment and experimental validation of three representative alloys. The phase classifier achieved an overall accuracy of 0.923. The phase-guided property models achieved R² values of 0.881 for hardness and 0.856 for yield strength. The experimentally measured dominant phases, hardness values, and compressive yield strengths of three representative candidates were generally consistent with the model predictions, with moderate experimental deviations. The proposed framework integrates physical descriptors, probabilistic phase information, model explainability, and uncertainty-aware screening, providing an interpretable and experimentally supported strategy for prioritizing promising HEA compositions before broader experimental optimization.