Title: AENET–LAMMPS and AENET–TINKER: Interfaces for accurate and efficient molecular dynamics simulations with machine learning potentials

Journal Article · · Journal of Chemical Physics
DOI: https://doi.org/10.1063/5.0063880 · OSTI ID:1853506
ORCiD logo [1]; ORCiD logo [2]; ORCiD logo [3]; ORCiD logo [2]; ORCiD logo [4]
  1. Stanford University, CA (United States); Columbia Univ., New York, NY (United States)
  2. Stanford University, CA (United States)
  3. College of Industrial Technology, Amagasaki (Japan)
  4. Columbia University, New York, NY (United States); Utrecht University (Netherlands)
+ Show Author Affiliations

Machine-learning potentials (MLPs) trained on data from quantum-mechanics based first-principles methods can approach the accuracy of the reference method at a fraction of the computational cost. To facilitate efficient MLP-based molecular dynamics and Monte Carlo simulations, an integration of the MLPs with sampling software is needed. Here, we develop two interfaces that link the atomic energy network (ænet) MLP package with the popular sampling packages TINKER and LAMMPS. The three packages, ænet, TINKER, and LAMMPS, are free and open-source software that enable, in combination, accurate simulations of large and complex systems with low computational cost that scales linearly with the number of atoms. Scaling tests show that the parallel efficiency of the ænet–TINKER interface is nearly optimal but is limited to shared-memory systems. The ænet–LAMMPS interface achieves excellent parallel efficiency on highly parallel distributed memory systems and benefits from the highly optimized neighbor list implemented in LAMMPS. We demonstrate the utility of the two MLP interfaces for two relevant example applications: the investigation of diffusion phenomena in liquid water and the equilibration of nanostructured amorphous battery materials.

Research Organization:
Univ. of California, Merced, CA (United States)
Sponsoring Organization:
Camille Dreyfus Teacher–Scholar Awards; Columbia Center for Computational Electrochemistry (CCCE); German Research Foundation (DFG); National Institutes of Health (NIH); National Science Foundation (NSF); New York State Empire State Development; USDOE Office of Science (SC), Basic Energy Sciences (BES)
Grant/Contract Number:
SC0020203
OSTI ID:
1853506
Journal Information:
Journal of Chemical Physics, Journal Name: Journal of Chemical Physics Journal Issue: 7 Vol. 155; ISSN 0021-9606
Publisher:
American Institute of Physics (AIP)Copyright Statement
Country of Publication:
United States
Language:
English

References (83)

AENET-LAMMPS and AENET-TINKER: interfaces for accurate and efficient molecular dynamics simulations with machine learning potentials dataset January 2020
25th Anniversary Article: Understanding the Lithiation of Silicon and Other Alloying Anodes for Lithium-Ion Batteries journal August 2013
Approaching the Downsizing Limit of Silicon for Surface-Controlled Lithium Storage journal January 2015
Silicon-Based Nanomaterials for Lithium-Ion Batteries: A Review journal October 2013
Enabling High‐Energy Solid‐State Batteries with Stable Anode Interphase by the Use of Columnar Silicon Anodes journal July 2020
An efficient newton-like method for molecular mechanics energy minimization of large molecules journal October 1987
Neural network potentials for metals and oxides - First applications to copper clusters at zinc oxide journal November 2012
Adaptive machine learning framework to accelerate ab initio molecular dynamics journal December 2014
Fast Parallel Algorithms for Short-Range Molecular Dynamics journal March 1995
Neural Networks: Tricks of the Trade book January 2012
Efficient BackProp book January 2012
On the limited memory BFGS method for large scale optimization journal August 1989
Approximation by superpositions of a sigmoidal function journal December 1989
Computer-aided drug design: the next 20 years journal October 2007
Machine learning-accelerated quantum mechanics-based atomistic simulations for industrial applications journal October 2020
Chemical diffusion in intermediate phases in the lithium-silicon system journal May 1981
An implementation of artificial neural-network potentials for atomistic materials simulations: Performance for TiO2 journal March 2016
Considerations for choosing and using force fields and interatomic potentials in materials science and engineering journal December 2013
Amp: A modular approach to machine learning in atomistic simulations journal October 2016
Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials journal March 2015
Solid Electrolyte Interphase on Native Oxide-Terminated Silicon Anodes for Li-Ion Batteries journal March 2019
A review of conduction phenomena in Li-ion batteries journal December 2010
Li-ion diffusion in amorphous Si films prepared by RF magnetron sputtering: A comparison of using liquid and polymer electrolytes journal April 2010
Determination of the diffusion coefficient of lithium ions in nano-Si journal March 2009
XCrySDen—a new program for displaying crystalline structures and electron densities journal June 1999
Tinker-HP: Accelerating Molecular Dynamics Simulations of Large Complex Systems with Advanced Point Dipole Polarizable Force Fields Using GPUs and Multi-GPU Systems journal March 2021
Performance and Cost Assessment of Machine Learning Interatomic Potentials journal October 2019
Quantum Dynamics and Spectroscopy of Ab Initio Liquid Water: The Interplay of Nuclear and Electronic Quantum Effects journal March 2017
The Interplay of Structure and Dynamics in the Raman Spectrum of Liquid Water over the Full Frequency and Temperature Range journal February 2018
Hiding in the Crowd: Spectral Signatures of Overcoordinated Hydrogen-Bond Environments journal September 2019
Analysis of the Li Distribution in Si-Based Negative Electrodes for Lithium-Ion Batteries by Soft X-ray Emission Spectroscopy journal September 2020
Lithiation/Delithiation Properties of Lithium Silicide Electrodes in Ionic-Liquid Electrolytes journal January 2021
Computer Simulation of Proton Solvation and Transport in Aqueous and Biomolecular Systems journal February 2006
Aqueous Basic Solutions: Hydroxide Solvation, Structural Diffusion, and Comparison to the Hydrated Proton journal April 2010
Static and Dynamical Properties of Liquid Water from First Principles by a Novel Car−Parrinello-like Approach journal January 2009
System-Size Dependence of Diffusion Coefficients and Viscosities from Molecular Dynamics Simulations with Periodic Boundary Conditions journal October 2004
Potentiostatic Intermittent Titration Technique for Electrodes Governed by Diffusion and Interfacial Reaction journal December 2011
Computational predictions of energy materials using density functional theory journal January 2016
The high-throughput highway to computational materials design journal February 2013
Computational understanding of Li-ion batteries journal March 2016
Liquid water contains the building blocks of diverse ice phases journal November 2020
Best practices in machine learning for chemistry journal May 2021
Nuclear quantum effects enter the mainstream journal February 2018
Structure prediction drives materials discovery journal April 2019
Silicon nanowires for Li-based battery anodes: a review journal January 2013
ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost journal January 2017
Tinker-HP: a massively parallel molecular dynamics package for multiscale simulations of large complex systems with advanced point dipole polarizable force fields journal January 2018
General formulation of pressure and stress tensor for arbitrary many-body interaction potentials under periodic boundary conditions journal October 2009
A consistent and accurate ab initio parametrization of density functional dispersion correction (DFT-D) for the 94 elements H-Pu journal April 2010
Molecular dynamics simulation of a polymer chain in solution journal November 1993
Perspective on density functional theory journal April 2012
Construction of high-dimensional neural network potentials using environment-dependent atom pairs journal May 2012
An analysis of hydrated proton diffusion in ab initio molecular dynamics journal January 2015
Constructing first-principles phase diagrams of amorphous Li x Si using machine-learning-assisted sampling with an evolutionary algorithm journal June 2018
A reactive, scalable, and transferable model for molecular energies from a neural network approach based on local information journal June 2018
SchNet – A deep learning architecture for molecules and materials journal June 2018
Decoding the spectroscopic features and time scales of aqueous proton defects journal June 2018
Machine learning for interatomic potential models journal February 2020
Potential energy functions for atomic-level simulations of water and organic and biomolecular systems journal May 2005
Proton transfer through the water gossamer journal July 2013
The atomic simulation environment—a Python library for working with atoms journal June 2017
Machine learning for the modeling of interfaces in energy storage and conversion materials journal July 2019
Strategies for the construction of machine-learning potentials for accurate and efficient atomic-scale simulations journal July 2021
A family of variable-metric methods derived by variational means journal January 1970
Conditioning of quasi-Newton methods for function minimization journal September 1970
A new approach to variable metric algorithms journal March 1970
The Convergence of a Class of Double-rank Minimization Algorithms 1. General Considerations journal January 1970
Computer Simulation of Liquids book June 2017
Efficient and accurate machine-learning interpolation of atomic energies in compositions with many species journal July 2017
High-dimensional neural-network potentials for multicomponent systems: Applications to zinc oxide journal April 2011
Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the Electrons journal April 2010
Generalized Gradient Approximation Made Simple journal October 1996
Comment on “Generalized Gradient Approximation Made Simple” journal January 1998
Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces journal April 2007
Neural network atomic potential to investigate the dislocation dynamics in bcc iron journal April 2020
OpenMP: an industry standard API for shared-memory programming journal January 1998
Minimized lithium trapping by isovalent isomorphism for high initial Coulombic efficiency of silicon anodes journal November 2019
The Many Roles of Computation in Drug Discovery journal March 2004
Combining theory and experiment in electrocatalysis: Insights into materials design journal January 2017
Moment Tensor Potentials: A Class of Systematically Improvable Interatomic Potentials journal January 2016
In Situ XRD and Electrochemical Study of the Reaction of Lithium with Amorphous Silicon journal January 2004
AENET-LAMMPS and AENET-TINKER: interfaces for accurate and efficient molecular dynamics simulations with machine learning potentials dataset January 2020
An Overview of Molecular Modeling for Drug Discovery with Specific Illustrative Examples of Applications journal April 2019

Similar Records

Related Subjects

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY
71 CLASSICAL AND QUANTUM MECHANICS
GENERAL PHYSICS
Molecular dynamics
Monte Carlo methods
artificial neural networks
atomic energy
batteries
computer software
density functional theory
machine learning
nanoparticles
programing languages