Heat flux for semi-local machine-learning potentials
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.
Code (2)
Tasks
Computational EfficiencySimilar Papers 제목 키워드 기반
Stress and heat flux via automatic differentiation
Machine-learning potentials provide computationally efficient and accurate approximations of the Born-Oppenheimer potential energy surface. This potential determines many materials properties and simulation techniques us…
Direct data-driven forecast of local turbulent heat flux in Rayleigh-Bénard convection
A combined convolutional autoencoder-recurrent neural network machine learning model is presented to analyse and forecast the dynamics and low-order statistics of the local convective heat flux field in a two-dimensional…
Metabolic fluxes and value production
Metabolic fluxes in cells are governed by physical, physiological, and economic principles. Here I assume an optimal allocation of enzyme resources and postulate a general principle for metabolism: each enzyme must conve…
Enzyme economy and metabolic control
The metabolic state of a cell, comprising fluxes, metabolite concentrations and enzyme levels, is shaped by a compromise between metabolic benefit and enzyme cost. This hypothesis and its consequences can be studied by c…
How does ion temperature gradient turbulence depend on magnetic geometry? Insights from data and machine learning
Magnetic geometry has a significant effect on the level of turbulent transport in fusion plasmas. Here, we model and analyze this dependence using multiple machine learning methods and a dataset of > 200,000 nonlinear si…
Feature Importancefeature selection