Machine-learning-based interatomic potential for phonon transport in perfect crystalline Si and crystalline Si with vacancies

Abstract

We report that single interatomic potential, developed using Gaussian regression of density functional theory calculation data, has high accuracy and flexibility to describe phonon transport with ab initio accuracy in two different atomistic configurations: perfect crystalline Si and crystalline Si with vacancies. The high accuracy of second-and third-order force constants from the Gaussian approximation potential (GAP) are demonstrated with phonon dispersion, Grüneisen parameter, three-phonon scattering rate, phonon-vacancy scattering rate, and thermal conductivity, all of which are very close to the results from density functional theory calculation. We also show that the widely used empirical potentials (Stillinger-Weber and Tersoff) produce much larger errors compared to the GAP. The computational cost of GAP is higher than the two empirical potentials, but five orders of magnitude lower than the density functional theory calculation. Our work shows that GAP can provide a new opportunity for studying phonon transport in partially disordered crystalline phases with the high predictive power of ab initio calculation but at a feasible computational cost.

Neuroevolution machine learning potentials: Combining high accuracy and low cost in atomistic simulations and application to heat transport

“…MD simulations with ML potentials have been applied to study heat transport properties of a number of materials, including, e.g., GeTe and MnGe compounds [61][62][63][64], diamond and amorphous silicon [65][66][67], multilayer graphene [68], monolayer silicene [69], CoSb 3 [70], monolayer MoS 2 and MoSe 2 and their alloys [71], C 3 N [72], α-Ag 2 Se [73,74], β-Ga 2 O 3 [75], Tl 3 VSe 4 [59], PbTe [59], and SnSe [76]. There are also works that exclusively used the Boaltzmann transport equation (BTE) approach to calculate thermal conductivity based on force constants determined from ML potentials [77][78][79][80][81][82]. In this section, we use 2D silicene and bulk PbTe as the examples to demonstrate the applicability of NEP in heat transport calculations.…”

Machine-learning interatomic potentials for materials science

“…The approach exploits the ML potentials' high accuracy and computational efficiency (compared to DFT) while keeping the simulation in the interpolation regime. One recent example is developing a GAP Si potential specifically designed for phonon properties and thermal conductivity calculations, including the effect of vacancies [136]. Similarly, a deep NN potential was constructed to calculate the vacancy formation free energy in Al as a function of temperature [137].…”

Taking materials dynamics to new extremes using machine learning interatomic potentials

“…The evaluation of the performance of the learned potential in MD simulations depends on the interested properties. For example, stable structure prediction at given temperature and pressures is important for phase-diagram prediction [25,77,78] , while dislocation core structure, generalized stacking fault energy prediction is important for mechanical properties [46,102] ; accurate phonon spectra are indispensable for the prediction of thermal conductivity [112] .…”