Simulating lattice thermal conductivity in semiconducting materials using high-dimensional neural network potential

Abstract

We demonstrate that a high-dimensional neural network potential (HDNNP) can predict the lattice thermal conductivity of semiconducting materials with an accuracy comparable to that of density functional theory (DFT) calculation. After a training procedure based on the force, the root mean square error between the forces predicted by the HDNNP and DFT is less than 40 meV/Å. As typical examples, we present the results for Si and GaN bulk crystals. The deviation from the thermal conductivity calculated using DFT is within 1% at 200 to 500 K for Si and within 5.4% at 200 to 1000 K for GaN.

References in corpus (8)

• Phonons and related properties of extended systems from density-functional perturbation theory
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Distribution of phonon lifetime in Brillouin zone
• The hiphive package for the extraction of high-order force constants by machine learning
• Efficient and Accurate Machine-Learning Interpolation of Atomic Energies in Compositions with Many Species
• Ab initio Green-Kubo Approach for the Thermal Conductivity of Solids
• Lattice thermal conductivities of two SiO${}_2$ polymorphs by first-principles calculation and phonon Boltzmann transport equation
• Phonon transport unveils the prevalent point defects in GaN

Cited by in corpus (4)

• Neuroevolution machine learning potentials: Combining high accuracy and low cost in atomistic simulations and application to heat transport
• Combining phonon accuracy with high transferability in Gaussian approximation potential models
• Phase stability of Au-Li binary systems studied using neural network potential
• Thermal conductivity of CaF${}_2$ at high pressure