skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Deep Potential Molecular Dynamics: A Scalable Model with the Accuracy of Quantum Mechanics

Journal Article · · Physical Review Letters
 [1];  [1];  [2];  [3];  [4]
  1. Princeton Univ., NJ (United States). Program in Applied and Computational Mathematics
  2. Inst. of Applied Physics and Computational Mathematics, Beijing (China); CAEP Software Center for High Performance Numerical Simulation, Beijing (China)
  3. Princeton Univ., NJ (United States). Dept. of Chemistry. Dept. of Physics. Program in Applied and Computational Mathematics. Princeton Inst. for the Science and Technology of Materials
  4. Princeton Univ., NJ (United States). Dept. of Mathematics. Program in Applied and Computational Mathematics; Peking Univ., Beijing (China). Beijing Inst. of Big Data Research. Center for Data Science. Beijing International Center for Mathematical Research
+ Show Author Affiliations

We introduce a scheme for molecular simulations, the deep potential molecular dynamics (DPMD) method, based on a many-body potential and interatomic forces generated by a carefully crafted deep neural network trained with ab initio data. The neural network model preserves all the natural symmetries in the problem. It is first-principles based in the sense that there are no ad hoc components aside from the network model. We show that the proposed scheme provides an efficient and accurate protocol in a variety of systems, including bulk materials and molecules. In all these cases, DPMD gives results that are essentially indistinguishable from the original data, at a cost that scales linearly with system size.

Research Organization:
Princeton Univ., NJ (United States)
Sponsoring Organization:
USDOE Office of Science (SC), Basic Energy Sciences (BES); USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)
Grant/Contract Number:
SC0008626; SC0009248
OSTI ID:
1541298
Alternate ID(s):
OSTI ID: 1431394
Journal Information:
Physical Review Letters, Vol. 120, Issue 14; ISSN 0031-9007
Publisher:
American Physical Society (APS)Copyright Statement
Country of Publication:
United States
Language:
English
Citation Metrics:
Cited by: 713 works
Citation information provided by
Web of Science

References (43)

Generalized Gradient Approximation Made Simple journal October 1996
Accurate determination of crystal structures based on averaged local bond order parameters journal September 2008
Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning journal January 2012
A universal strategy for the creation of machine learning-based atomistic force fields journal September 2017
Development and Testing of the OPLS All-Atom Force Field on Conformational Energetics and Properties of Organic Liquids journal January 1996
Nosé–Hoover chains: The canonical ensemble via continuous dynamics journal August 1992
ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost journal January 2017
How van der Waals interactions determine the unique properties of water journal July 2016
Embedded-atom method: Derivation and application to impurities, surfaces, and other defects in metals journal June 1984
Toward reliable density functional methods without adjustable parameters: The PBE0 model journal April 1999
ReaxFF:  A Reactive Force Field for Hydrocarbons journal October 2001
Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces journal April 2007
Comparison of simple potential functions for simulating liquid water journal July 1983
Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials journal March 2015
Accurate Molecular Van Der Waals Interactions from Ground-State Electron Density and Free-Atom Reference Data journal February 2009
i-PI: A Python interface for ab initio path integral molecular dynamics simulations journal March 2014
GROMACS 4.5: a high-throughput and highly parallel open source molecular simulation toolkit journal February 2013
DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics journal July 2018
CHARMM general force field: A force field for drug-like molecules compatible with the CHARMM all-atom additive biological force fields journal January 2009
Quantum Monte Carlo journal February 1986
Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the Electrons journal April 2010
Perspective: Machine learning potentials for atomistic simulations journal November 2016
Quantum-chemical insights from deep tensor neural networks journal January 2017
Development and testing of a general amber force field journal January 2004
Coupled‐cluster methods with noniterative triple excitations for restricted open‐shell Hartree–Fock and other general single determinant reference functions. Energies and analytical gradients journal June 1993
Accelerating the convergence of path integral dynamics with a generalized Langevin equation journal February 2011
Machine learning of accurate energy-conserving molecular force fields journal May 2017
Crystal Structure and Pair Potentials: A Molecular-Dynamics Study journal October 1980
Advanced capabilities for materials modelling with Quantum ESPRESSO journal October 2017
Self-Consistent Equations Including Exchange and Correlation Effects journal November 1965
A second-generation reactive empirical bond order (REBO) potential energy expression for hydrocarbons journal January 2002
Machine learning of accurate energy-conserving molecular force fields text January 2017
Advanced capabilities for materials modelling with Quantum ESPRESSO text January 2017
Fast and accurate modeling of molecular atomization energies with machine learning text January 2012
ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost text January 2017
Accurate determination of crystal structures based on averaged local bond order parameters text January 2008
Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons text January 2009
Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning text January 2011
i-PI: A Python interface for ab initio path integral molecular dynamics simulations text January 2014
Quantum-Chemical Insights from Deep Tensor Neural Networks text January 2016
Machine Learning of Accurate Energy-Conserving Molecular Force Fields text January 2016
Advanced capabilities for materials modelling with Quantum ESPRESSO text January 2017
DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics text January 2017

Cited By (54)

A Critical Review of Machine Learning of Energy Materials journal January 2020
Role of Water in the Reaction Mechanism and endo / exo Selectivity of 1,3‐Dipolar Cycloadditions Elucidated by Quantum Chemistry and Machine Learning journal May 2019
Simulating Diffusion Properties of Solid‐State Electrolytes via a Neural Network Potential: Performance and Training Scheme journal December 2019
Towards exact molecular dynamics simulations with machine-learned force fields journal September 2018
Graph dynamical networks for unsupervised learning of atomic scale dynamics in materials journal June 2019
Recent advances and applications of machine learning in solid-state materials science journal August 2019
Fast, accurate, and transferable many-body interatomic potentials by symbolic regression journal November 2019
A fast neural network approach for direct covariant forces prediction in complex multi-element extended systems journal September 2019
DeePCG: Constructing coarse-grained models via deep neural networks journal July 2018
Adaptive coupling of a deep neural network potential to a classical force field journal October 2018
Analysis of trajectory similarity and configuration similarity in on-the-fly surface-hopping simulation on multi-channel nonadiabatic photoisomerization dynamics journal December 2018
Molecular force fields with gradient-domain machine learning: Construction and application to dynamics of small molecules with coupled cluster forces journal March 2019
A universal density matrix functional from molecular orbital-based machine learning: Transferability across organic molecules journal April 2019
Atom-density representations for machine learning journal April 2019
Deep learning inter-atomic potential model for accurate irradiation damage simulations journal June 2019
Evaluation of experimental alkali metal ion–ligand noncovalent bond strengths with DLPNO-CCSD(T) method journal July 2019
Compressing physics with an autoencoder: Creating an atomic species representation to improve machine learning models in the chemical sciences journal August 2019
Guidelines for creating artificial neural network empirical interatomic potential from first-principles molecular dynamics data under specific conditions and its application to α-Ag 2 Se journal September 2019
Machine learning for interatomic potential models journal February 2020
FCHL revisited: Faster and more accurate quantum machine learning journal January 2020
Incorporating long-range physics in atomic-scale machine learning journal November 2019
Uniformly accurate machine learning-based hydrodynamic models for kinetic equations journal October 2019
Isotope effects in liquid water via deep potential molecular dynamics journal October 2019
Machine learning and molecular design of self-assembling -conjugated oligopeptides journal April 2018
From DFT to machine learning: recent approaches to materials science–a review journal May 2019
Development of a deep machine learning interatomic potential for metalloid-containing Pd-Si compounds journal November 2019
Constructing convex energy landscapes for atomistic structure optimization journal December 2019
Machine-learning-based interatomic potential for phonon transport in perfect crystalline Si and crystalline Si with vacancies journal July 2019
Atomic energy mapping of neural network potential journal September 2019
Electronic structure at coarse-grained resolutions from supervised machine learning journal March 2019
A unified picture of the covalent bond within quantum-accurate force fields: From organic molecules to metallic complexes’ reactivity journal May 2019
High-repetition-rate femtosecond mid-infrared pulses generated by nonlinear optical modulation of continuous-wave QCLs and ICLs journal January 2019
De novo exploration and self-guided learning of potential-energy surfaces text January 2019
Molecular Modeling Investigations of Sorption and Diffusion of Small Molecules in Glassy Polymers journal August 2019
Enumeration of de novo inorganic complexes for chemical discovery and machine learning journal January 2020
Learning from the density to correct total energy and forces in first principle simulations journal October 2019
Machine Learning a General-Purpose Interatomic Potential for Silicon text January 2018
DeePCG: constructing coarse-grained models via deep neural networks text January 2018
Adaptive coupling of a deep neural network potential to a classical force field text January 2018
Analysis of Trajectory Similarity and Configuration Similarity in On-the-Fly Surface-Hopping Simulation on Multi-Channel Nonadiabatic Photoisomerization Dynamics text January 2018
Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation text January 2018
Learning from the Density to Correct Total Energy and Forces in First Principle Simulations text January 2018
Molecular Force Fields with Gradient-Domain Machine Learning: Construction and Application to Dynamics of Small Molecules with Coupled Cluster Forces text January 2019
Graph Dynamical Networks for Unsupervised Learning of Atomic Scale Dynamics in Materials text January 2019
Atomic energy mapping of neural network potential text January 2019
Deep learning inter-atomic potential model for accurate irradiation damage simulations text January 2019
Isotope Effects in Liquid Water via Deep Potential Molecular Dynamics text January 2019
Uniformly Accurate Machine Learning Based Hydrodynamic Models for Kinetic Equations text January 2019
Machine-learning interatomic potential for radiation damage and defects in tungsten text January 2019
FCHL revisited: faster and more accurate quantum machine learning text January 2019
Incorporating long-range physics in atomic-scale machine learning text January 2019
Nonadiabatic Excited-State Dynamics with Machine Learning journal September 2018
Reinforced dynamics for enhanced sampling in large atomic and molecular systems journal March 2018
N-body Networks: a Covariant Hierarchical Neural Network Architecture for Learning Atomic Potentials preprint January 2018

Similar Records

DeePCG: Constructing coarse-grained models via deep neural networks
Journal Article · Mon Jul 16 00:00:00 EDT 2018 · Journal of Chemical Physics · OSTI ID:1541298
+2 more
Adaptive coupling of a deep neural network potential to a classical force field
Journal Article · Wed Oct 17 00:00:00 EDT 2018 · Journal of Chemical Physics · OSTI ID:1541298
Isotope effects in molecular structures and electronic properties of liquid water via deep potential molecular dynamics based on the SCAN functional
Journal Article · Mon Dec 21 00:00:00 EST 2020 · Physical Review. B · OSTI ID:1541298
+3 more

Related Subjects

74 ATOMIC AND MOLECULAR PHYSICS