DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics

Abstract

Recent developments in many-body potential energy representation via deep learning have brought new hopes to addressing the accuracy-versus-efficiency dilemma in molecular simulations. Here we describe DeePMD-kit, a package written in Python/C++ that has been designed to minimize the effort required to build deep learning based representation of potential energy and force field and to perform molecular dynamics. Potential applications of DeePMD-kit span from finite molecules to extended systems and from metallic systems to chemically bonded systems. DeePMD-kit is interfaced with TensorFlow, one of the most popular deep learning frameworks, making the training process highly automatic and efficient. On the other end, DeePMD-kit is interfaced with high-performance classical molecular dynamics and quantum (path-integral) molecular dynamics packages, i.e., LAMMPS and the i-PI, respectively. Thus, upon training, the potential energy and force field models can be used to perform efficient molecular simulations for different purposes. As an example of the many potential applications of the package, we use DeePMD-kit to learn the interatomic potential energy and forces of a water model using data obtained from density functional theory. We demonstrate that the resulted molecular dynamics model reproduces accurately the structural information contained in the original model.

References in corpus (7)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• How van der Waals interactions determine the unique properties of water
• Deep Potential: a general representation of a many-body potential energy surface
• The TensorMol-0.1 Model Chemistry: a Neural Network Augmented with Long-Range Physics

Cited by in corpus (233)

• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• Machine Learning Force Fields
• Recent Advances and Applications of Deep Learning Methods in Materials Science
• DP-GEN: A concurrent learning platform for the generation of reliable deep learning based potential energy models
• Data-driven materials science: status, challenges and perspectives
• DeePMD-kit v2: A software package for Deep Potential models
• Neuroevolution machine learning potentials: Combining high accuracy and low cost in atomistic simulations and application to heat transport
• Physics-inspired structural representations for molecules and materials
• Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation
• GPUMD: A package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations
• Machine learning for electronically excited states of molecules
• The Phase Diagram of a Deep Potential Water Model
• Neural Network Based in Silico Simulation of Combustion Reactions
• 86 PFLOPS Deep Potential Molecular Dynamics simulation of 100 million atoms with ab initio accuracy
• A deep potential model with long-range electrostatic interactions
• Combining SchNet and SHARC: The SchNarc machine learning approach for excited-state dynamics
• Deep Potentials for Materials Science
• A practical guide to machine learning interatomic potentials -- Status and future
• DeePCG: constructing coarse-grained models via deep neural networks
• Silicon liquid structure and crystal nucleation from ab-initio deep Metadynamics
• End-to-end Symmetry Preserving Inter-atomic Potential Energy Model for Finite and Extended Systems
• Deep neural network for the dielectric response of insulators
• Raman Spectrum and Polarizability of Liquid Water from Deep Neural Networks
• Improving the accuracy of the neuroevolution machine learning potential for multi-component systems
• Experimental Observation of Localized Interfacial Phonon Modes
• Neural Network Potentials for Chemistry: Concepts, Applications and Prospects
• Deep Potential generation scheme and simulation protocol for the Li10GeP2S12-type superionic conductors
• Advances of Machine Learning in Materials Science: Ideas and Techniques
• Molecular dynamics simulations of heat transport using machine-learned potentials: A mini review and tutorial on GPUMD with neuroevolution potentials
• Phase equilibrium of water with hexagonal and cubic ice using the SCAN functional
• Homogeneous ice nucleation in an ab initio machine learning model of water
• DeePMD-kit v3: A Multiple-Backend Framework for Machine Learning Potentials
• Deep Learning of Accurate Force Field of Ferroelectric HfO${}_2$
• Liquid-liquid transition in water from first principles
• Physics-informed radial basis network (PIRBN): A local approximating neural network for solving nonlinear PDEs
• Polarization-driven band topology evolution in twisted MoTe${}_2$ and WSe${}_2$
• Deep learning inter-atomic potential model for accurate irradiation damage simulations
• PiNN: A Python Library for Building Atomic Neural Networks of Molecules and Materials
• Machine learned Force-Fields for an ab-initio Quality Description of Metal-Organic Frameworks
• Isotope Effects in Liquid Water via Deep Potential Molecular Dynamics
• Heat transport in liquid water from first-principles and deep-neural-network simulations
• MLatom 3: Platform for machine learning-enhanced computational chemistry simulations and workflows
• Data-driven Material Models for Atomistic Simulation
• i-PI 3.0: a flexible and efficient framework for advanced atomistic simulations
• Accurate Deep Potential model for the Al-Cu-Mg alloy in the full concentration space
• Machine learning and excited-state molecular dynamics
• The Evolution of Machine Learning Potentials for Molecules, Reactions and Materials
• Viscosity in water from first-principles and deep-neural-network simulations
• Graph Neural Networks Accelerated Molecular Dynamics
• Unraveling the Crystallization Kinetics of the Ge${}_2$Sb${}_2$Te${}_5$ Phase Change Compound with a Machine-Learned Interatomic Potential
• Liquid-Liquid Critical Point in Phosphorus
• PANNA: Properties from Artificial Neural Network Architectures
• Bayesian Force Fields from Active Learning for Simulation of Inter-Dimensional Transformation of Stanene
• Discrepancies and Error Evaluation Metrics for Machine Learning Interatomic Potentials
• Unconventional mechanical and thermal behaviors of MOF CALF-20
• Atomistic modelling of all dislocations and twins in HCP and BCC Ti
• Data-Driven Prediction of Complex Crystal Structures of Dense Lithium
• Predicted superconductivity and superionic state in the electride Li${}_5$N under high pressure
• Development of Interatomic Potential for Al-Tb Alloy by Deep Neural Network Learning Method
• Efficient implementation of atom-density representations
• Phonons in magic-angle twisted bilayer graphene
• Scalable Hybrid Deep Neural Networks/Polarizable Potentials Biomolecular Simulations including long-range effects
• Universal Machine Learning Kohn-Sham Hamiltonian for Materials
• Correcting force error-induced underestimation of lattice thermal conductivity in machine learning molecular dynamics
• Extending the limit of molecular dynamics with ab initio accuracy to 10 billion atoms
• Towards Linearly Scaling and Chemically Accurate Global Machine Learning Force Fields for Large Molecules
• A Tungsten Deep Neural-Network Potential for Simulating Mechanical Property Degradation Under Fusion Service Environment
• Universal interatomic potential for perovskite oxides
• Machine Learning - Driven Materials Discovery: Unlocking Next-Generation Functional Materials - A review
• A first-principles machine-learning force field for heterogeneous ice nucleation on microcline feldspar
• Thermophysical properties of FLiBe using moment tensor potentials
• Understanding the Anomalous Diffusion of Water in Aqueous Electrolytes Using Machine Learned Potentials
• Temperature- and vacancy-concentration-dependence of heat transport in Li${}_3$ClO from multi-method numerical simulations
• Pushing the limit of molecular dynamics with ab initio accuracy to 100 million atoms with machine learning
• Prediction of a supersolid phase in high-pressure deuterium
• ArcaNN: automated enhanced sampling generation of training sets for chemically reactive machine learning interatomic potentials
• Unconventional ferroelectric domain switching dynamics in CuInP2S6 from first principles
• Advances in modeling complex materials: The rise of neuroevolution potentials
• The Neural Network Approach to Inverse Problems in Differential Equations
• Machine-learning interatomic potential for molecular dynamics simulation of ferroelectric KNbO3 perovskite
• BubbleNet: Inferring micro-bubble dynamics with semi-physics-informed deep learning
• A Deep Potential model for liquid-vapor equilibrium and cavitation rates of water
• Ultralow lattice thermal transport and considerable wave-like phonon tunneling in chalcogenide perovskite BaZrS${}_3$
• ænet-PyTorch: a GPU-supported implementation for machine learning atomic potentials training
• Insight into the effect of force error on the thermal conductivity from machine-learned potentials
• Detecting dynamic domains and local fluctuations in complex molecular systems via timelapse neighbors shuffling
• An Extendible, Graph-Neural-Network-Based Approach for Accurate Force Field Development of Large Flexible Organic Molecules
• XLB: A differentiable massively parallel lattice Boltzmann library in Python
• Towards fully ab initio simulation of atmospheric aerosol nucleation
• Revealing the molecular structures of a-Al2O3(0001)-water interface by machine learning based computational vibrational spectroscopy
• Neural network representation of electronic structure from $ab$ $initio$ molecular dynamics
• KLIFF: A framework to develop physics-based and machine learning interatomic potentials
• Complex Spin Hamiltonian Represented by Artificial Neural Network
• What dictates soft clay-like Lithium superionic conductor formation from rigid-salts mixture
• Thermal Transport by Electrons and Ions in Warm Dense Aluminum: A Combined Density Functional Theory and Deep Potential Study
• Integrating Machine Learning with Physics-Based Modeling
• TimeSOAP: Tracking high-dimensional fluctuations in complex molecular systems via time-variations of SOAP spectra
• A deep machine learning potential for atomistic simulation of Fe-Si-O systems under Earth's outer core conditions
• Tunable ferroelectric topological defects on 2D topological surfaces: strain engineering skyrmion-like polar structures in 2D materials
• Innate Dynamics and Identity Crisis of a Metal Surface Unveiled by Machine Learning of Atomic Environments
• Theoretical evidence of H-He demixing under Jupiter and Saturn conditions
• Enhancing the Accuracy of Density Functional Tight Binding Models Through ChIMES Many-body Interaction Potentials
• Origin of negative thermal expansion and pressure induced amorphization in zirconium tungstate from machine-learning potential
• Full-scale ab initio simulations of laser-driven atomistic dynamics
• Finite-temperature properties of antiferroelectric perovskite $\mathrm{PbZr}{\mathrm{O}}_3$ from deep learning interatomic potential
• Modeling the High-Pressure Solid and Liquid Phases of Tin from Deep Potentials with ab initio Accuracy
• Lattice dynamics and elastic properties of alpha-U at high-temperature and high-pressure by machine learning potential simulations
• Visualizing the microscopic origins of topology in twisted molybdenum ditelluride
• Structure and polymerization of liquid sulfur across the $\lambda$-transition
• chemtrain: Learning Deep Potential Models via Automatic Differentiation and Statistical Physics
• Multiple lattice instabilities and complex ground state in Cs${}_2$AgBiBr${}_6$
• Spiers Memorial Lecture: How to do impactful research in artificial intelligence for chemistry and materials science
• Classical and Machine Learning Interatomic Potentials for BCC Vanadium
• Adaptive coupling of a deep neural network potential to a classical force field
• Intramolecular and water mediated tautomerism of solvated glycine
• Hydrogen diffusion in the lower mantle revealed by machine learning potentials
• DeePKS+ABACUS as a Bridge between Expensive Quantum Mechanical Models and Machine Learning Potentials
• Generator of Neural Network Potential for Molecular Dynamics: Constructing Robust and Accurate Potentials with Active Learning for Nanosecond-scale Simulations
• Enhancing ReaxFF for Molecular Dynamics Simulations of Lithium-Ion Batteries: An interactive reparameterization protocol
• The dynamic nature of high pressure ice VII
• Towards Large-Scale and Spatio-temporally Resolved Diagnosis of Electronic Density of States by Deep Learning
• Combining stochastic density functional theory with deep potential molecular dynamics to study warm dense matter
• The Symmetry-Preserving Mean Field Condition for Electrostatic Correlations in Bulk
• Exploring the formation of gold/silver nanoalloys with gas-phase synthesis and machine-learning assisted simulations
• Machine-Learned Atomic Cluster Expansion Potentials for Fast and Quantum-Accurate Thermal Simulations of Wurtzite AlN
• Anisotropic molecular coarse-graining by force and torque matching with neural networks
• Chirality-Dependent Kinetics of Single-Walled Carbon Nanotubes from Machine-Learning Force Fields
• Exploring Li-ion Transport Properties of Li${}_3$TiCl${}_6$: A Machine Learning Molecular Dynamics Study
• Propensity of water self-ions at air(oil)-water interfaces revealed by deep potential molecular dynamics with enhanced sampling
• Understanding High-Temperature Chemical Reactions on Metal Surfaces
• Validation Workflow for Machine Learning Interatomic Potentials for Complex Ceramics
• Deep Density: circumventing the Kohn-Sham equations via symmetry preserving neural networks
• Learning Thermodynamically Stable and Galilean Invariant Partial Differential Equations for Non-equilibrium Flows
• Some observations on high-dimensional partial differential equations with Barron data
• Transferable empirical pseudopotenials from machine learning
• A chemical bond-based machine learning model for dipole moment: Application to dielectric properties of liquid methanol and ethanol
• Evolution of flat bands in MoSe${}_2$/WSe${}_2$ moiré lattices: A study combining machine learning and band unfolding methods
• Thermal disorder and phonon softening in the ferroelectric phase transition of lead titanate
• Structure and mechanical properties of monolayer amorphous carbon and boron nitride
• Structural Signatures for Thermodynamic Stability in Vitreous Silica: Insight from Machine Learning and Molecular Dynamics Simulations
• Unraveling Antagonistic Collision-Controlled Reactivity in Energetic Molecular Perovskites with Deep Potential Molecular Dynamics
• Non-Equilibrium Nature of Fracture Determines the Crack Paths
• Differentiable Physics: A Position Piece
• Probing the state of hydrogen in $\delta$-AlOOH at mantle conditions with machine learning potential
• High-Throughput Condensed-Phase Hybrid Density Functional Theory for Large-Scale Finite-Gap Systems: The SeA Approach
• Enhancing the formation of ionic defects to study the ice Ih/XI transition with molecular dynamics simulations
• DPmoire: A tool for constructing accurate machine learning force fields in moiré systems
• Copper delocalization leads to ultralow thermal conductivity in chalcohalide CuBiSeCl2
• General Electronic Structure Calculation Method for Twisted Systems
• Materials Informatics: Emergence To Autonomous Discovery In The Age Of AI
• Size and Quality of Quantum Mechanical Data Sets for Training Neural Network Force Fields for Liquid Water
• Metatensor and metatomic: foundational libraries for interoperable atomistic machine learning
• Isotope effects in x-ray absorption spectra of liquid water
• IR Spectroscopy of Carboxylate-Passivated Semiconducting Nanocrystals: Simulation and Experiment
• Fitting to magnetic forces improves the reliability of magnetic Moment Tensor Potentials
• Machine learning at the atomic-scale
• Local structure, thermodynamics, and melting curve of boron phosphide at high pressures by deep learning-driven ab initio simulations
• Machine Learning Potentials for Alloys: A Detailed Workflow to Predict Phase Diagrams and Benchmark Accuracy
• Fast proper orthogonal descriptors for many-body interatomic potentials
• Efficient moment tensor machine-learning interatomic potential for accurate description of defects in Ni-Al Alloys
• A Heterogeneous Parallel Non-von Neumann Architecture System for Accurate and Efficient Machine Learning Molecular Dynamics
• KPROJ: A Program for Unfolding Electronic and Phononic Bands
• Benchmarking CHGNet Universal Machine Learning Interatomic Potential Against DFT and EXAFS: Case of Layered WS2 and MoS2
• Hydrogen diffusion in garnet: insights from atomistic simulations
• Efficient Generation of Stable Linear Machine-Learning Force Fields with Uncertainty-Aware Active Learning
• Elasticity and acoustic velocities of $\delta$-AlOOH at extreme conditions: a methodology assessment
• Using metadynamics to build neural network potentials for reactive events: the case of urea decomposition in water
• Fortnet, a software package for training Behler-Parrinello neural networks
• Aqueous Solution Chemistry In Silico and the Role of Data Driven Approaches
• Reconstructions and Dynamics of $\beta$-Lithium Thiophosphate Surfaces
• Apax: A Flexible and Performant Framework For The Development of Machine-Learned Interatomic Potentials
• Scaling Molecular Dynamics with ab initio Accuracy to 149 Nanoseconds per Day
• Physics-informed graph neural networks enhance scalability of variational nonequilibrium optimal control
• Deep Learning Inter-atomic Potential for Thermal and Phonon Behaviour of Silicon Carbide with Quantum Accuracy
• Learning intermolecular forces at liquid-vapor interfaces
• Melting curves of ice polymorphs in the vicinity of the liquid-liquid critical point
• Slowly Quenched, High Pressure Glassy B${}_2$O${}_3$ at DFT Accuracy
• A Planning-and-Exploring Approach to Extreme-Mechanics Force Fields
• Pressure-Induced Structural and Dielectric Changes in Liquid Water at Room Temperature
• Equivariant Tensor Network Potentials
• Evaluating the Transferability of Machine-Learned Force Fields for Material Property Modeling
• Deriving effective electrode-ion interactions from free-energy profiles at electrochemical interfaces
• Free energy profiles for chemical reactions in solution from high-dimensional neural network potentials: The case of the Strecker synthesis
• Water Isotope Separation using Deep Learning and a Catalytically Active Ultrathin Membrane
• Unifying O(3) Equivariant Neural Networks Design with Tensor-Network Formalism
• Structure and solidification of the (Fe0.75B0.15Si0.1)100-xTax (x=0-2) melts: experiment and machine learning
• Transferability of the chemical bond-based machine learning model for dipole moment: the GHz to THz dielectric properties of liquid propylene glycol and polypropylene glycol
• Low-rank matrix and tensor approximations for compression of machine-learning interatomic potentials
• Charge Orders in Fully Intercalated Bilayer TaSe${}_2$: Dependence on Interlayer Stacking and Intercalation Sites
• Strength of 2D Glasses Explored by Machine-Learning Force Fields
• Mechanisms and Stability of Li Dynamics in Amorphous Li-Ti-P-S-Based Mixed Ionic-Electronic Conductors: A Machine Learning Molecular Dynamics Study
• Viscosity, breakdown of Stokes-Einstein relation and dynamical heterogeneity in supercooled liquid Ge${}_2$Sb${}_2$Te${}_5$ from simulations with a neural network potential
• Data Fusion of Deep Learned Molecular Embeddings for Property Prediction
• Evaluation of Structural Properties and Defect Energetics in Al${}_x$Ga${}_{1-x}$N Alloys
• FastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUs
• Machine-Learned Bond-Order Potential for Exploring the Configuration Space of Carbon
• Self-healing mechanism of lithium in lithium metal batteries
• A general formalism for machine-learning models based on multipolar-spherical harmonics
• Mapping the Structure of Oxygen-Doped Wurtzite Aluminum Nitride Coatings From Ab Initio Random Structure Search and Experiments
• Machine-Learned Potentials for Solvation Modeling
• Considerations in the use of ML interaction potentials for free energy calculations
• Ab Initio bulk free energy surface of proper ferroelectrics
• Multiscale mechanics of thermal gradient coupled graphene fracture: A molecular dynamics study
• Edge Dynamics in Iron-Cluster Catalyzed Growth of Single-Walled Carbon Nanotubes Revealed by Molecular Dynamics Simulations based on a Neural Network Potential
• Atomistic understanding of hydrogen bubble-induced embrittlement in tungsten enabled by machine learning molecular dynamics
• The Scalability for Parallel Machine Learning Training Algorithm: Dataset Matters
• Role of octahedral tilting induced acoustic softening on limiting thermal transport in SrSnO3
• Visualizing Electronic Structure of Twisted Bilayer MoTe2 in Devices
• Decoding lithium's subtle phase stability with a machine learning force field
• On the Boroxol Ring Fraction in Melt-Quenched B${}_2$O${}_3$ Glass
• Accurate force field of two-dimensional ferroelectrics from deep learning
• Incorporating Gibbs free energy into interatomic potential fitting
• A unified machine-learning framework for ab initio multiscale modeling of liquids
• Boosting current-induced molecular dynamics with machine-learning potential
• Managing Expectations and Imbalanced Training Data in Reactive Force Field Development: an Application to Water Adsorption on Alumina
• Incorporating electronic information into Machine Learning potential energy surfaces via approaching the ground-state electronic energy as a function of atom-based electronic populations
• Neural Canonical Transformations for Quantum Anharmonic Solids of Lithium
• Using a monomer potential energy surface to perform approximate path integral molecular dynamics simulation of ab-initio water with near-zero added cost
• A charge-density machine-learning workflow for computing the infrared spectrum of molecules
• A Computational Method for Studying Vibrational Mode Dynamics
• Rethinking Thread Scheduling under Oversubscription: A User-Space Framework for Coordinating Multi-runtime and Multi-process Workloads
• The ground state of CuInP${}_2$S${}_6$ thin films: A study of the deep potential method
• A review of simulation, measurement techniques, and development in chip thermal design
• Machine learning potential as a guide for eutectic in ultra-refractory multicomponent ceramics
• Competing Hydrogenation Pathways to Metastable CaH${}_6$ Revealed by Machine-Learning-Potential Molecular Dynamics
• Revealing Phonon Bridge Effect for Amorphous vs Crystalline Metal-Silicide Layers at Si/Ti Interfaces by a Machine Learning Potential
• Elucidating the mechanism of reactive uptake of N${}_2$O${}_5$ in aqueous aerosol
• Interlayer coupling driven stabilization and superconductivity in bilayer CoTe${}_2$
• Robust chirality memory in carbon nanotubes growing under modulated and evolving environments
• Accelerating discovery of infrared nonlinear optical materials with large shift current via high-throughput screening
• Intrinsic structure of relaxor ferroelectrics from first principles
• REANN: A PyTorch-based End-to-End Multi-functional Deep Neural Network Package for Molecular, Reactive and Periodic Systems
• Aitomia: Your Intelligent Assistant for AI-Driven Atomistic and Quantum Chemical Simulations