A Machine Learning Framework for Predicting Glass-Forming Ability in Ternary Alloy Systems

TL;DR

This paper demonstrates that ensemble machine learning models can accurately predict the glass-forming ability of ternary oxide glasses from compositional features, providing both high accuracy and physical insights.

Contribution

It introduces the first systematic application of ensemble ML models to predict GFA in ternary oxide glasses, linking predictive accuracy with physical interpretability.

Findings

Models achieved R^2 > 0.92 and MAE < 0.04.

Electronegativity variance and atomic size mismatch are key features.

Ensemble ML models offer insights for designing new glasses.

Abstract

Predicting the glass-forming ability (GFA) of chemical compositions remains a fundamental challenge in materials science, especially for oxide glasses with broad compositional diversity. Traditional empirical and thermodynamic approaches often fail to capture the complex, nonlinear factors governing vitrification. In this study, we applied two ensemble machine learning algorithms-Random Forest (RF) and Extreme Gradient Boosting (XGB)-to the glass_ternary_hipt dataset to predict the GFA of ternary oxide glasses directly from composition-derived descriptors. Both models achieved excellent predictive accuracy (R^2 > 0.92, MAE < 0.04), confirming that GFA is learnable from compositional features alone. Feature importance analysis revealed that electronegativity variance, atomic size mismatch, and valence electron descriptors are the most influential factors, while cohesive energy and ionic radius provided secondary contributions. These chemically interpretable features align with established theories of glass formation, thereby bridging predictive performance with physical understanding. The novelty of this work lies in systematically extending ML-based predictive modeling to ternary oxide glasses, a class less studied compared to metallic and binary systems. Our results demonstrate that ensemble learning not only enables accurate GFA prediction but also provides actionable insights for designing new glass compositions with enhanced stability.