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

Abstract

We develop a neuroevolution-potential (NEP) framework for generating neural network based machine-learning 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.

arXiv comment18 pages, 10 figures, 2 tables, code and data available

References in corpus (43)

• Quantum ESPRESSO: a modular and open-source software project for quantum simulations of materials
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
• Machine Learning Force Fields
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• Optimization Algorithm for the Generation of ONCV Pseudopotentials
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• DScribe: Library of Descriptors for Machine Learning in Materials Science
• Machine learning a general purpose interatomic potential for silicon
• The hiphive package for the extraction of high-order force constants by machine learning
• Machine-learning interatomic potentials for materials science
• Efficient and Accurate Machine-Learning Interpolation of Atomic Energies in Compositions with Many Species
• Force and heat current formulas for many-body potentials in molecular dynamics simulation with applications to thermal conductivity calculations
• Efficient molecular dynamics simulations with many-body potentials on graphics processing units
• WACSF - Weighted Atom-Centered Symmetry Functions as Descriptors in Machine Learning Potentials
• Embedded Atom Neural Network Potentials: Efficient and Accurate Machine Learning with a Physically Inspired Representation
• An Accurate and Transferable Machine Learning Potential for Carbon
• Homogeneous nonequilibrium molecular dynamics method for heat transport and spectral decomposition with many-body potentials
• First-Principles Prediction of Phononic Thermal Conductivity of Silicene: a Comparison with Graphene
• Unexpected phonon-transport properties of stanene among 2D group-IV materials from \textit{ab initio}
• Accelerating first-principles estimation of thermal conductivity by machine-learning interatomic potentials: A MTP/ShengBTE solution
• Unexpectedly Large Tunability of Lattice Thermal Conductivity of Monolayer Silicene via Mechanical Strain
• Thermal conductivity decomposition in two-dimensional materials: Application to graphene
• Atom-Density Representations for Machine Learning
• Optimizing many-body atomic descriptors for enhanced computational performance of machine learning based interatomic potentials
• Tensile Strains Give Rise to Strong Size Effects for Thermal Conductivities of Silicene, Germanene and Stanene
• Gaussian Moments as Physically Inspired Molecular Descriptors for Accurate and Scalable Machine Learning Potentials
• Equivalence of the equilibrium and the nonequilibrium molecular dynamics methods for thermal conductivity calculations: From bulk to nanowire silicon
• Spectral Decomposition of Thermal Conductivity: Comparing Velocity Decomposition Methods in Homogeneous Molecular Dynamics Simulations
• Accelerated molecular dynamics force evaluation on graphics processing units for thermal conductivity calculations
• Hybrid neural network potential for multilayer graphene
• Machine-learning based interatomic potential for phonon transport in perfect crystalline Si and crystalline Si with vacancies
• Machine learning force fields based on local parametrization of dispersion interactions: Application to the phase diagram of C${}_{60}$
• Bimodal grain-size scaling of thermal transport in polycrystalline graphene from large-scale molecular dynamics simulations
• Combining phonon accuracy with high transferability in Gaussian approximation potential models
• Transferability of neural network potentials for varying stoichiometry: phonons and thermal conductivity of Mn${}_x$Ge${}_y$ compounds
• PyXtal FF: a Python Library for Automated Force Field Generation
• Thermal transport properties of single-layer black phosphorous from extensive molecular dynamics simulations
• Simulating lattice thermal conductivity in semiconducting materials using high-dimensional neural network potential
• A minimal Tersoff potential for diamond silicon with improved descriptions of elastic and phonon transport properties

Cited by in corpus (13)

• GPUMD: A package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations
• 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
• Anisotropic and high thermal conductivity in monolayer quasi-hexagonal fullerene: A comparative study against bulk phase fullerene
• Simple machine-learned interatomic potentials for complex alloys
• Phase transitions in inorganic halide perovskites from machine learning potentials
• Limits of the phonon quasi-particle picture at the cubic-to-tetragonal phase transition in halide perovskites
• E(n)-Equivariant Cartesian Tensor Passing Potential
• Ab initio Green-Kubo simulations of heat transport in solids: Method and implementation
• Variable thermal transport in black, blue, and violet phosphorene from extensive atomistic simulations with a neuroevolution potential
• Heat transport across graphene/hexagonal-BN tilted grain boundaries from phase-field crystal model and molecular dynamics simulations
• Stability and distortion of fcc-LaH${}_{10}$ with path-integral molecular dynamics
• Machine learning based modeling of disordered elemental semiconductors: understanding the atomic structure of a-Si and a-C