Predicting Debye Temperature and Thermal Conductivity of Transition Metals Using Machine Learning Ensemble Models

The Debye temperature () and lattice thermal conductivity () of transition metals are fundamental to their applications in thermal management, high-temperature alloys, and energy-related technologies, as well as to understanding their lattice dynamics and heat-transport behavior. However, reliable and accurate prediction of these properties remains challenging due to anharmonic lattice effects, complex structure-property relationships, and the limited availability of experimental data. This study aims to predict the  and  of transition metals from a dataset of nearly 1000 individual records, which include their physical and chemical properties, with the goal of designing advanced materials. To achieve the goal, this study employed several machine learning-based models: Fine Tree (FT), Medium Tree (MT), Coarse Tree (CT), Optimizable Tree (OT), Bagged Tree (BGT), Boosted Tree (BST), and Optimizable Ensemble (OE), which were investigated on the transition metals dataset. Among the implemented models, the OE showed excellent predictive performance, achieving R² values of 95.82% and 88.69% in validation, as well as R² values of 97.51% and 94.33% in tests for the  and , respectively. Furthermore, the RReliefF algorithm is employed to reveal the significance of input features to the respective target properties ( or ). Moreover, a significant correlation between  and  was identified, and partial dependence plots were also employed to interpret feature influence and validate model predictions. These findings demonstrate the effectiveness of machine learning models in predicting thermophysical properties of transition metals.