Physically Consistent Machine Learning for Melting Temperature Prediction of Refractory High-Entropy Alloys
This work addresses the need for rapid alloy screening in high-temperature applications, though it is incremental as it applies an existing machine learning method with feature engineering to a specific domain.
The researchers tackled the problem of predicting melting temperatures for refractory high-entropy alloys by developing a gradient-boosted decision tree model, achieving a coefficient of determination of 0.948 and about 5% relative error on a validation set.
Predicting the melting temperature (Tm) of multi-component and high-entropy alloys (HEAs) is critical for high-temperature applications but computationally expensive using traditional CALPHAD or DFT methods. In this work, we develop a gradient-boosted decision tree (XGBoost) model to predict Tm for complex alloys based on elemental properties. To ensure physical consistency, we address the issue of data leakage by excluding temperature-dependent thermodynamic descriptors (such as Gibbs free energy of mixing) and instead rely on physically motivated elemental features. The optimized model achieves a coefficient of determination (R2) of 0.948 and a Mean Squared Error (MSE) of 9928 which is about 5% relative error for HEAs on a validation set of approximately 1300 compositions. Crucially, we validate the model using the Valence Electron Concentration (VEC) rule. Without explicit constraints during training, the model successfully captures the known stability transition between BCC and FCC phases at a VEC of approximately 6.87. These results demonstrate that data-driven models, when properly feature-engineered, can capture fundamental metallurgical principles for rapid alloy screening.