Advancing Thermal Conductivity Prediction of Metallic Materials by Integrating Molecular Dynamics Simulation with Machine Learning

Molecular dynamics (MD) simulation has an intrinsic limitation when calculating thermal conductivity of metals. That is, only phonon (lattice) thermal conductivity can be derived from trajectory of atoms, which is obtained by solving the Newton ' s equations of motion numerically. Therefore, significant contribution of electrons in metals remains unaccounted for. In this study, a Light Gradient Boosting Machine (Light GBM) regression model is employed to predict thermal conductivity of metal s using heat flux calculated by MD sim ulation, electrical con ductivity and others as input vari ables. The Lig htGBM model successfully predic ts the complex non-linear Gre en-Kubo relation for thermal con ductivity calculation even though the underlying physical mechanisms are not entirely clear. The model predic ts vari ous temperature dependences of thermal con ductivity of metal s accurately. Furthermore, the model trained with known compositions of Al-Cu alloys is proved to estimate the thermal con ductivity of alloys with unknown compositions. The model also demon strates a cer tain leve l of predic tive ability for alloys with different compositions and temperature s. This stud y demon strates the poten tial of a dat a-driven approach as an efficient met hod for uncovering complex relationships bet ween inc omplete dat a from MD sim ulations and true material s properties, especially in cases where the underlying physics is elusive.