Molecular dynamics simulations of heat transport using machine-learned potentials: A mini review and tutorial on GPUMD with neuroevolution potentials

Abstract

Molecular dynamics (MD) simulations play an important role in understanding and engineering heat transport properties of complex materials. An essential requirement for reliably predicting heat transport properties is the use of accurate and efficient interatomic potentials. Recently, machine-learned potentials (MLPs) have shown great promise in providing the required accuracy for a broad range of materials. In this mini review and tutorial, we delve into the fundamentals of heat transport, explore pertinent MD simulation methods, and survey the applications of MLPs in MD simulations of heat transport. Furthermore, we provide a step-by-step tutorial on developing MLPs for highly efficient and predictive heat transport simulations, utilizing the neuroevolution potentials (NEPs) as implemented in the GPUMD package. Our aim with this mini review and tutorial is to empower researchers with valuable insights into cutting-edge methodologies that can significantly enhance the accuracy and efficiency of MD simulations for heat transport studies.

arXiv comment25 pages, 9 figures. This paper is part of the special topic, Machine Learning for Thermal Transport

References in corpus (55)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
• Phononics: Manipulating heat flow with electronic analogs and beyond
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• Unified theory of thermal transport in crystals and disordered solids
• Phase transitions of hybrid perovskites simulated by machine-learning force fields trained on-the-fly with Bayesian inference
• GPUMD: A package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations
• Role of anharmonic phonon scattering in the spectrally decomposed thermal conductance at planar interfaces
• 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
• Homogeneous nonequilibrium molecular dynamics method for heat transport and spectral decomposition with many-body potentials
• Frequency-dependent phonon mean free path in carbon nanotubes from non-equilibrium molecular dynamics
• Modeling heat transport in crystals and glasses from a unified lattice-dynamical approach
• Influence of Boundaries and Thermostatting on Nonequilibrium Molecular Dynamics Simulations of Heat Conduction in Solids
• Thermal conductivity decomposition in two-dimensional materials: Application to graphene
• Optimizing many-body atomic descriptors for enhanced computational performance of machine learning based interatomic potentials
• Improving the accuracy of the neuroevolution machine learning potential for multi-component systems
• Ab initio Green-Kubo Approach for the Thermal Conductivity of Solids
• Microscopic theory and quantum simulation of atomic heat transport
• Equivalence of the equilibrium and the nonequilibrium molecular dynamics methods for thermal conductivity calculations: From bulk to nanowire silicon
• Strategies for the Construction of Machine-Learning Potentials for Accurate and Efficient Atomic-Scale Simulations
• Spectral Decomposition of Thermal Conductivity: Comparing Velocity Decomposition Methods in Homogeneous Molecular Dynamics Simulations
• Quantum-corrected thickness-dependent thermal conductivity in amorphous silicon predicted by machine-learning molecular dynamics simulations
• Tutorial: How to Train a Neural Network Potential
• Accelerated molecular dynamics force evaluation on graphics processing units for thermal conductivity calculations
• Machine learned Force-Fields for an ab-initio Quality Description of Metal-Organic Frameworks
• Hybrid neural network potential for multilayer graphene
• Anisotropic and high thermal conductivity in monolayer quasi-hexagonal fullerene: A comparative study against bulk phase fullerene
• Heat transport in liquid water from first-principles and deep-neural-network simulations
• Structural, electronic, thermal and mechanical properties of C60-based fullerene two-dimensional networks explored by first-principles and machine learning
• Simple machine-learned interatomic potentials for complex alloys
• 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
• Tuning the lattice thermal conductivity in van-der-Waals structures through rotational (dis)ordering
• Correcting force error-induced underestimation of lattice thermal conductivity in machine learning molecular dynamics
• Transferability of neural network potentials for varying stoichiometry: phonons and thermal conductivity of Mn${}_x$Ge${}_y$ compounds
• Thermophysical properties of FLiBe using moment tensor potentials
• Thermal transport properties of single-layer black phosphorous from extensive molecular dynamics simulations
• Temperature- and vacancy-concentration-dependence of heat transport in Li${}_3$ClO from multi-method numerical simulations
• Computing the heat conductivity of fluids from density fluctuations
• Ab initio Green-Kubo simulations of heat transport in solids: Method and implementation
• Finite-size effects on current correlation functions
• Tutorial: Concepts and numerical techniques for modeling individual phonon transmission at interfaces
• Heat flux for semi-local machine-learning potentials
• Thermal Transport by Electrons and Ions in Warm Dense Aluminum: A Combined Density Functional Theory and Deep Potential Study
• Combining linear-scaling quantum transport and machine-learning molecular dynamics to study thermal and electronic transports in complex materials
• Variable thermal transport in black, blue, and violet phosphorene from extensive atomistic simulations with a neuroevolution potential
• Combining the D3 dispersion correction with the neuroevolution machine-learned potential
• Dissimilar thermal transport properties in $\kappa$-Ga${}_2$O${}_3$ and $\beta$-Ga${}_2$O${}_3$ revealed by machine-learning homogeneous nonequilibrium molecular dynamics simulations
• Stress and heat flux via automatic differentiation
• Exactly equivalent thermal conductivity in finite systems from equilibrium and nonequilibrium molecular dynamics simulations
• Hexagonal boron-carbon fullerene heterostructures; Stable two-dimensional semiconductors with remarkable stiffness, low thermal conductivity and flat bands
• Construction of Machine-Learning Interatomic Potential Under Heat Flux Regularization and Its Application to Power Spectrum Analysis for Silver Chalcogenides

Cited by in corpus (19)

• Advances in modeling complex materials: The rise of neuroevolution potentials
• Highly efficient path-integral molecular dynamics simulations with GPUMD using neuroevolution potentials: Case studies on thermal properties of materials
• Insight into the effect of force error on the thermal conductivity from machine-learned potentials
• PYSED: A tool for extracting kinetic-energy-weighted phonon dispersion and lifetime from molecular dynamics simulations
• Accurate estimation of interfacial thermal conductance between silicon and diamond enabled by a machine learning interatomic potential
• Probing the ideal limit of interfacial thermal conductance in two-dimensional van der Waals heterostructures
• Phonon coherence and minimum thermal conductivity in disordered superlattice
• Thermal conductivity of Li${}_3$PS${}_4$ solid electrolytes with ab initio accuracy
• Revisit Many-body Interaction Heat Current and Thermal Conductivity Calculation in Moment Tensor Potential/LAMMPS Interface
• Copper delocalization leads to ultralow thermal conductivity in chalcohalide CuBiSeCl2
• Exploring the energy landscape of aluminas through machine learning interatomic potential
• Ultrahigh interfacial thermal conductance for cooling gallium oxide electronics using cubic boron arsenide
• Anisotropic and isotropic elasticity and thermal transport in monolayer C${}_{24}$ networks from machine-learning molecular dynamics
• Role of octahedral tilting induced acoustic softening on limiting thermal transport in SrSnO3
• Thermal conductivities of monolayer graphene oxide from machine learning molecular dynamics simulations
• Benchmarking Chemically Scalable Machine-Learning Interatomic Potentials for Large-Scale Simulations of Multicomponent Alloys
• Revealing Phonon Bridge Effect for Amorphous vs Crystalline Metal-Silicide Layers at Si/Ti Interfaces by a Machine Learning Potential
• A review of simulation, measurement techniques, and development in chip thermal design
• Interface phonon modes governing the ideal limit of thermal transport across diamond/cubic boron nitride interfaces