Estimating thermal conductivity of α-Ag2Se using ANN potential with Chebyshev descriptor

Shimamura, Kohei; Takeshita, Yusuke; Fukushima, Satoshi; Koura, Akihide; Shimojo, Fuyuki

doi:10.1016/j.cplett.2021.138748

Cited by 11 publications

(7 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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].…”

Section: Heat Transport Applicationsmentioning

confidence: 99%

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

et al. 2021

View full text Add to dashboard Cite

We develop a neuroevolution-potential (NEP) framework for generating neural network-based machinelearning potentials. They are trained using an evolutionary strategy for performing large-scale molecular dynamics (MD) simulations. A descriptor of the atomic environment is constructed based on Chebyshev and Legendre polynomials. The method is implemented in graphic processing units within the open-source GPUMD package, which can attain a computational speed over 10 7 atom-step per second using one Nvidia Tesla V100. Furthermore, per-atom heat current is available in NEP, which paves the way for efficient and accurate MD simulations of heat transport in materials with strong phonon anharmonicity or spatial disorder, which usually cannot be accurately treated either with traditional empirical potentials or with perturbative methods.

show abstract

Section: Heat Transport Applicationsmentioning

confidence: 99%

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

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The formulas for ε i and W i for the EIP of Ag 2 Se are shown in Section I of the Supplementary Materials (SM). W i for the ANN potential with the Chebyshev descriptor is defined as [31] W…”

Section: Heat Flux Formulamentioning

confidence: 99%

“…( II.6) was that its contribution to the TC was dominant compared to that of the kinetic part in our previous studies regarding silver chalcogenides. [30,31] The effect of the regularization term on training is controlled by the magnitude of its coefficient p J . In this study, in addition to p j = 0.0, we mainly set p J = 10 -4 , 10 -3 , 10 -2 , or 10 -1 to construct ANN potentials and compare their results.…”

Section: Regularization Term Of Heat Fluxmentioning

confidence: 99%

See 1 more Smart Citation

Construction of Machine-Learning Interatomic Potential Under Heat Flux Regularization and Its Application to Power Spectrum Analysis for Silver Chalcogenides

Shimamura¹,

Koura²,

Shimojo³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

We propose a data-driven approach for constructing machine-learning interatomic potentials (MLIPs) trained under a regularization with the aim of avoiding nonphysical heat flux. Specifically, we introduce a regularization term for the heat flux into the cost function of MLIPs to be minimized. Since the treatment of heat flux using MLIPs with regularization can be decomposed into elemental contributions or conducted in frequency space, this approach is expected to be useful for investigating the origin of thermal conductivity obtained from the Green-Kubo formula. However, the strength of regularization needs to be appropriately set because it may reduce not only the nonphysical part but also the intrinsic heat flux one. To this end, we investigated the conditions for constructing MLIPs that can reproduce the power spectra of heat flux associated with the empirical interatomic potential of Ag 2 Se, which consists of pairwise functions and do not contain a nonphysical heat flux. The appropriate strength could be estimated from the variation of the magnitude of regularization term as well as root mean square errors for total potential energy, atomic force, and virial stress with respect to the strengths, without reference spectrum data. As an application example, we explored the differences in power spectra between superionic and nonsuperionic conducting phases based on the heat flux regularization to MLIPs trained with the first-principles calculation data of Ag 2 S. Furthermore, our results demonstrate that training with the regularization improves the robustness of MLIPs as well as the reduction of the nonphysical heat flux.

show abstract

“…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 [58][59][60][61], diamond and amorphous silicon [62][63][64], multilayer graphene [65], monolayer silicene [66], CoSb 3 [67], monolayer MoS 2 and MoSe 2 and their alloys [68], C 3 N [69], α-Ag 2 Se [70,71], β-Ga 2 O 3 [72], Tl 3 VSe 4 [56], PbTe [56], and SnSe [73]. 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 [74][75][76][77][78][79].…”

Section: Heat Transport Applicationsmentioning

confidence: 99%

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

Fan,

Zeng,

Zhang

et al. 2021

Preprint

View full text Add to dashboard Cite

We develop a neuroevolution-potential (NEP) framework for generating neural network based machine-learning potentials. They are trained using an evolutionary strategy for performing largescale molecular dynamics (MD) simulations. A descriptor of the atomic environment is constructed based on Chebyshev and Legendre polynomials. The method is implemented in graphic processing units within the open-source gpumd package, which can attain a computational speed over 10 7 atom-step per second using one Nvidia Tesla V100. Furthermore, per-atom heat current is available in NEP, which paves the way for efficient and accurate MD simulations of heat transport in materials with strong phonon anharmonicity or spatial disorder, which usually cannot be accurately treated either with traditional empirical potentials or with perturbative methods.

show abstract

Estimating thermal conductivity of α-Ag2Se using ANN potential with Chebyshev descriptor

Cited by 11 publications

References 40 publications

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

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

Construction of Machine-Learning Interatomic Potential Under Heat Flux Regularization and Its Application to Power Spectrum Analysis for Silver Chalcogenides

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

Contact Info

Product

Resources

About