Heat flux for semi-local machine-learning potentials
This work addresses the need for efficient and accurate heat transport simulations in materials science, representing an incremental improvement by extending existing methods to a new class of potentials.
The paper tackled the challenge of accurately simulating heat transport in materials by adapting the Green-Kubo method for semi-local machine-learning potentials, resulting in a validated calculation of thermal conductivity for zirconium dioxide across temperatures.
The Green-Kubo (GK) method is a rigorous framework for heat transport simulations in materials. However, it requires an accurate description of the potential-energy surface and carefully converged statistics. Machine-learning potentials can achieve the accuracy of first-principles simulations while allowing to reach well beyond their simulation time and length scales at a fraction of the cost. In this paper, we explain how to apply the GK approach to the recent class of message-passing machine-learning potentials, which iteratively consider semi-local interactions beyond the initial interaction cutoff. We derive an adapted heat flux formulation that can be implemented using automatic differentiation without compromising computational efficiency. The approach is demonstrated and validated by calculating the thermal conductivity of zirconium dioxide across temperatures.