Correcting force error-induced underestimation of lattice thermal conductivity in machine learning molecular dynamics

Abstract

Machine learned potentials (MLPs) have been widely employed in molecular dynamics (MD) simulations to study thermal transport. However, literature results indicate that MLPs generally underestimate the lattice thermal conductivity (LTC) of typical solids. Here, we quantitatively analyze this underestimation in the context of the neuroevolution potential (NEP), which is a representative MLP that balances efficiency and accuracy. Taking crystalline silicon, GaAs, graphene, and PbTe as examples, we reveal that the fitting errors in the machine-learned forces against the reference ones are responsible for the underestimated LTC as they constitute external perturbations to the interatomic forces. Since the force errors of a NEP model and the random forces in the Langevin thermostat both follow a Gaussian distribution, we propose an approach to correcting the LTC by intentionally introducing different levels of force noises via the Langevin thermostat and then extrapolating to the limit of zero force error. Excellent agreement with experiments is obtained by using this correction for all the prototypical materials over a wide range of temperatures. Based on spectral analyses, we find that the LTC underestimation mainly arises from increased phonon scatterings in the low-frequency region caused by the random force errors.

References in corpus (10)

• Canonical sampling through velocity-rescaling
• GPUMD: A package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations
• Accurate sampling using Langevin dynamics
• Thermal conductivity of suspended pristine graphene measured by Raman spectroscopy
• Improving the accuracy of the neuroevolution machine learning potential for multi-component systems
• Quantum-corrected thickness-dependent thermal conductivity in amorphous silicon predicted by machine-learning molecular dynamics simulations
• Sub-micrometer phonon mean free paths in metal-organic frameworks revealed by machine-learning molecular dynamics simulations
• Accurate prediction of heat conductivity of water by a neuroevolution potential
• Mechanisms of temperature-dependent thermal transport in amorphous silica from machine-learning molecular dynamics
• Reduced thermal conductivity of epitaxial GaAs on Si due to symmetry-breaking biaxial strain

Cited by in corpus (9)

• Molecular dynamics simulations of heat transport using machine-learned potentials: A mini review and tutorial on GPUMD with neuroevolution potentials
• Insight into the effect of force error on the thermal conductivity from machine-learned potentials
• Accurate estimation of interfacial thermal conductance between silicon and diamond enabled by a machine learning interatomic potential
• Ultrahigh interfacial thermal conductance for cooling gallium oxide electronics using cubic boron arsenide
• Consistency between the Green-Kubo formula and Lorentz model for predicting the infrared dielectric function of polar materials
• Anisotropic and isotropic elasticity and thermal transport in monolayer C${}_{24}$ networks from machine-learning molecular dynamics
• Accelerating the Discovery of Materials with Expected Thermal Conductivity via a Synergistic Strategy of DFT and Interpretable Deep Learning
• Thermal conductivities of monolayer graphene oxide from machine learning molecular dynamics simulations
• Interface phonon modes governing the ideal limit of thermal transport across diamond/cubic boron nitride interfaces