09. Heat and Mass Transfer

Micro/nanoscale heat conduction is crucial for a broad range of applications such as thermal management of electronic devices, thermal insulation, and thermoelectrics. Understanding and designing of thermal transport properties in solid materials largely depends on atomistic simulations, which however suffer either low computational efficiency or accuracy. In recent years, machine learning is emerging as a powerful tool to investigate heat transfer, particularly for complex systems. The applications of machine learning in exploring thermal transport properties of solids mainly include constructing interatomic potentials and directly predicting thermophysical properties of materials. In this work, we will introduce our recent progess in investigating complex thermal issues using machine learning. On one hand, we have developed machine learning interatomic potentials that can accurately describe phonon transport in defective crystals. The machine learning interatomic potentials achieve a DFT-level accuracy combined with orders of magnitude reduced computational cost. On the other hand, we have developed machine learning models to accurately predict the thermal resistance of various interfaces. These results demonstrate the great potential of using machine learning algorithms to understand and predict thermal transport properties in complex systems.