Search Menu
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information
Search Scholarly Publications

Title: Active learning of uniformly accurate interatomic potentials for materials simulation

Abstract

An active learning procedure called deep potential generator (DP-GEN) is proposed for the construction of accurate and transferable machine learning-based models of the potential energy surface (PES) for the molecular modeling of materials. This procedure consists of three main components: exploration, generation of accurate reference data, and training. Application to the sample systems of Al, Mg, and Al-Mg alloys demonstrates that DP-GEN can produce uniformly accurate PES models with a minimal number of reference data.

Authors:
 [1];  [2];  [3];  [4];  [5]
+ Show Author Affiliations
  1. Princeton Univ., NJ (United States). Program in Applied and Computational Mathematics
  2. Inst. of Applied Physics and Computational Mathematics (IAPCM), Beijing (China); CAEP Software Center for High Performance Numerical Simulation, Beijing (China)
  3. Inst. of Applied Physics and Computational Mathematics (IAPCM), Beijing (China). Lab. of Computational Physics
  4. 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
  5. Princeton Univ., NJ (United States). Dept. of Mathematics and program in Applied and Computational Mathematics
Publication Date:
Research Org.:
Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States). National Energy Research Scientific Computing Center (NERSC)
Sponsoring Org.:
USDOE
OSTI Identifier:
1542459
Alternate Identifier(s):
OSTI ID: 1496508
Grant/Contract Number:  
SC0019394
Resource Type:
Accepted Manuscript
Journal Name:
Physical Review Materials
Additional Journal Information:
Journal Volume: 3; Journal Issue: 2; Journal ID: ISSN 2475-9953
Publisher:
American Physical Society (APS)
Country of Publication:
United States
Language:
English
Subject:
36 MATERIALS SCIENCE

Citation Formats

Zhang, Linfeng, Lin, De-Ye, Wang, Han, Car, Roberto, and E, Weinan. Active learning of uniformly accurate interatomic potentials for materials simulation. United States: N. p., 2019. Web. doi:10.1103/PhysRevMaterials.3.023804.
Copy to clipboard
Zhang, Linfeng, Lin, De-Ye, Wang, Han, Car, Roberto, & E, Weinan. Active learning of uniformly accurate interatomic potentials for materials simulation. United States. https://doi.org/10.1103/PhysRevMaterials.3.023804
Copy to clipboard
Zhang, Linfeng, Lin, De-Ye, Wang, Han, Car, Roberto, and E, Weinan. Mon . "Active learning of uniformly accurate interatomic potentials for materials simulation". United States. https://doi.org/10.1103/PhysRevMaterials.3.023804. https://www.osti.gov/servlets/purl/1542459.
Copy to clipboard
@article{osti_1542459,
title = {Active learning of uniformly accurate interatomic potentials for materials simulation},
author = {Zhang, Linfeng and Lin, De-Ye and Wang, Han and Car, Roberto and E, Weinan},
abstractNote = {An active learning procedure called deep potential generator (DP-GEN) is proposed for the construction of accurate and transferable machine learning-based models of the potential energy surface (PES) for the molecular modeling of materials. This procedure consists of three main components: exploration, generation of accurate reference data, and training. Application to the sample systems of Al, Mg, and Al-Mg alloys demonstrates that DP-GEN can produce uniformly accurate PES models with a minimal number of reference data.},
doi = {10.1103/PhysRevMaterials.3.023804},
journal = {Physical Review Materials},
number = 2,
volume = 3,
place = {United States},
year = {Mon Feb 25 00:00:00 EST 2019},
month = {Mon Feb 25 00:00:00 EST 2019}
}
Copy to clipboard
Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record
https://doi.org/10.1103/PhysRevMaterials.3.023804
Copyright Statement
Other availability
Search WorldCat Search WorldCat to find libraries that may hold this journal
Citation Metrics:
Cited by: 252 works
Citation information provided by
Web of Science
Save / Share:
Export Metadata
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.

Works referenced in this record:

Measurements of the vacancy formation enthalpy in aluminum using positron annihilation spectroscopy
journal, May 1978

Generalized Gradient Approximation Made Simple
journal, October 1996

  • Perdew, John P.; Burke, Kieron; Ernzerhof, Matthias
  • Physical Review Letters, Vol. 77, Issue 18, p. 3865-3868
  • DOI: 10.1103/PhysRevLett.77.3865

Climb kinetics of dislocation loops in aluminium
journal, December 1968

DeePCG: Constructing coarse-grained models via deep neural networks
journal, July 2018

  • Zhang, Linfeng; Han, Jiequn; Wang, Han
  • The Journal of Chemical Physics, Vol. 149, Issue 3
  • DOI: 10.1063/1.5027645

Silicon Liquid Structure and Crystal Nucleation from Ab Initio Deep Metadynamics
journal, December 2018

Deep learning
journal, May 2015

  • LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey
  • Nature, Vol. 521, Issue 7553
  • DOI: 10.1038/nature14539

ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost
journal, January 2017

  • Smith, J. S.; Isayev, O.; Roitberg, A. E.
  • Chemical Science, Vol. 8, Issue 4
  • DOI: 10.1039/C6SC05720A

Atomic Energies from a Convolutional Neural Network
journal, May 2018

  • Chen, Xin; Jørgensen, Mathias S.; Li, Jun
  • Journal of Chemical Theory and Computation, Vol. 14, Issue 7
  • DOI: 10.1021/acs.jctc.8b00149

Impurity effect of Mg on the generalized planar fault energy of Al
journal, April 2016

  • Zhao, Dongdong; Løvvik, Ole Martin; Marthinsen, Knut
  • Journal of Materials Science, Vol. 51, Issue 14
  • DOI: 10.1007/s10853-016-9834-6

ANI-1, A data set of 20 million calculated off-equilibrium conformations for organic molecules
journal, December 2017

  • Smith, Justin S.; Isayev, Olexandr; Roitberg, Adrian E.
  • Scientific Data, Vol. 4, Issue 1
  • DOI: 10.1038/sdata.2017.193

Fast Parallel Algorithms for Short-Range Molecular Dynamics
journal, March 1995

Less is more: Sampling chemical space with active learning
journal, June 2018

  • Smith, Justin S.; Nebgen, Ben; Lubbers, Nicholas
  • The Journal of Chemical Physics, Vol. 148, Issue 24
  • DOI: 10.1063/1.5023802

Dispersion Relations for Phonons in Aluminum at 80 and 300°K
journal, May 1966

Machine learning of molecular electronic properties in chemical compound space
journal, September 2013

All-Atom Empirical Potential for Molecular Modeling and Dynamics Studies of Proteins †
journal, April 1998

  • MacKerell, A. D.; Bashford, D.; Bellott, M.
  • The Journal of Physical Chemistry B, Vol. 102, Issue 18
  • DOI: 10.1021/jp973084f

The Formation Energy of Vacancies in Aluminium and Magnesium
journal, June 1976

  • Tzanetakis, P.; Hillairet, J.; Revel, G.
  • physica status solidi (b), Vol. 75, Issue 2
  • DOI: 10.1002/pssb.2220750205

DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
journal, July 2018

Fast and Accurate Uncertainty Estimation in Chemical Machine Learning
journal, November 2018

  • Musil, Félix; Willatt, Michael J.; Langovoy, Mikhail A.
  • Journal of Chemical Theory and Computation, Vol. 15, Issue 2
  • DOI: 10.1021/acs.jctc.8b00959

Low‐Temperature Elastic Moduli of Aluminum
journal, February 1964

  • Kamm, G. N.; Alers, G. A.
  • Journal of Applied Physics, Vol. 35, Issue 2
  • DOI: 10.1063/1.1713309

The Inorganic Crystal Structure Database (ICSD)—Present and Future
journal, January 2004

Modified embedded atom method potential for Al, Si, Mg, Cu, and Fe alloys
journal, June 2012

Modified embedded-atom potentials for cubic materials and impurities
journal, August 1992

Lattice Constants and Brillouin Zone Overlap in Dilute Magnesium Alloys
journal, January 1957

Deep Potential: A General Representation of a Many-Body Potential Energy Surface
journal, January 2018

  • Han, Jiequn; Zhang, Linfeng; Car, Roberto
  • Communications in Computational Physics, Vol. 23, Issue 3
  • DOI: 10.4208/cicp.OA-2017-0213

Climb kinetics of dislocation loops in aluminium
journal, July 1967

Melting curve of aluminum up to 300 GPa obtained through ab initio molecular dynamics simulations
journal, September 2009

On the Determination of Molecular Fields. I. From the Variation of the Viscosity of a Gas with Temperature
journal, October 1924

  • Jones, J. E.
  • Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 106, Issue 738
  • DOI: 10.1098/rspa.1924.0081

Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
journal, January 2012

Melting of aluminum, molybdenum, and the light actinides
journal, November 2004

A study of the structure of Lomer and 60° dislocations in aluminium using high-resolution transmission electron microscopy
journal, September 1989

Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set
journal, July 1996

Special points for Brillouin-zone integrations
journal, June 1976

  • Monkhorst, Hendrik J.; Pack, James D.
  • Physical Review B, Vol. 13, Issue 12, p. 5188-5192
  • DOI: 10.1103/PhysRevB.13.5188

Machine learning unifies the modeling of materials and molecules
journal, December 2017

  • Bartók, Albert P.; De, Sandip; Poelking, Carl
  • Science Advances, Vol. 3, Issue 12
  • DOI: 10.1126/sciadv.1701816

Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set
journal, October 1996

Positron trapping in solid and liquid metals
journal, December 1975

Embedded-atom method: Derivation and application to impurities, surfaces, and other defects in metals
journal, June 1984

ReaxFF:  A Reactive Force Field for Hydrocarbons
journal, October 2001

  • van Duin, Adri C. T.; Dasgupta, Siddharth; Lorant, Francois
  • The Journal of Physical Chemistry A, Vol. 105, Issue 41
  • DOI: 10.1021/jp004368u

Commentary: The Materials Project: A materials genome approach to accelerating materials innovation
journal, July 2013

  • Jain, Anubhav; Ong, Shyue Ping; Hautier, Geoffroy
  • APL Materials, Vol. 1, Issue 1
  • DOI: 10.1063/1.4812323

Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces
journal, April 2007

Metadynamics for training neural network model chemistries: A competitive assessment
journal, June 2018

  • Herr, John E.; Yao, Kun; McIntyre, Ryker
  • The Journal of Chemical Physics, Vol. 148, Issue 24
  • DOI: 10.1063/1.5020067

On the stacking fault energies of some close-packed hexagonal metals
journal, December 1969

Stratified construction of neural network based interatomic models for multicomponent materials
journal, January 2017

Reinforced dynamics for enhanced sampling in large atomic and molecular systems
journal, March 2018

  • Zhang, Linfeng; Wang, Han; E., Weinan
  • The Journal of Chemical Physics, Vol. 148, Issue 12
  • DOI: 10.1063/1.5019675

Elastic Constants of Magnesium from 4.2°K to 300°K
journal, August 1957

Active Learning
journal, June 2012

Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the Electrons
journal, April 2010

Machine Learning a General-Purpose Interatomic Potential for Silicon
journal, December 2018

Dislocation Climb and Determination of Stacking‐Fault Energies in Al and Al‐1% Mg
journal, May 1966

  • Kannan, V. C.; Thomas, G.
  • Journal of Applied Physics, Vol. 37, Issue 6
  • DOI: 10.1063/1.1708819

Surface energies of elemental crystals
journal, September 2016

  • Tran, Richard; Xu, Zihan; Radhakrishnan, Balachandran
  • Scientific Data, Vol. 3, Issue 1
  • DOI: 10.1038/sdata.2016.80

Machine Learning Force Fields: Construction, Validation, and Outlook
journal, December 2016

Machine learning of accurate energy-conserving molecular force fields
journal, May 2017

  • Chmiela, Stefan; Tkatchenko, Alexandre; Sauceda, Huziel E.
  • Science Advances, Vol. 3, Issue 5
  • DOI: 10.1126/sciadv.1603015

Deep Potential Molecular Dynamics: A Scalable Model with the Accuracy of Quantum Mechanics
journal, April 2018

Active learning of linearly parametrized interatomic potentials
journal, December 2017

Python Materials Genomics (pymatgen): A robust, open-source python library for materials analysis
journal, February 2013

Enthalpy, heat capacity, and heat of fusion of aluminum from 366.degree. to 1647.degree.K
journal, January 1967

  • McDonald, Richard Addison
  • Journal of Chemical & Engineering Data, Vol. 12, Issue 1
  • DOI: 10.1021/je60032a037

Mechanism of pore opening in the calcium-activated chloride channel TMEM16A
journal, February 2021

High-resolution X-ray luminescence extension imaging
journal, February 2021

Machine learning of accurate energy-conserving molecular force fields
text, January 2017

ANI-1, A data set of 20 million calculated off-equilibrium conformations for organic molecules
text, January 2017

  • S., Smith, Justin; Olexandr, Isayev,; E., Roitberg, Adrian
  • The University of North Carolina at Chapel Hill University Libraries
  • DOI: 10.17615/0m5q-hh31

ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost
text, January 2017

  • ,
  • The University of North Carolina at Chapel Hill University Libraries
  • DOI: 10.17615/bhbf-9r93

Machine Learning a General-Purpose Interatomic Potential for Silicon
text, January 2018

  • Bartók, Ap; Kermode, J.; Bernstein, N.
  • Apollo - University of Cambridge Repository
  • DOI: 10.17863/cam.34909

Machine learning unifies the modeling of materials and molecules.
text, January 2017

  • Bartók, Albert P.; De, Sandip; Poelking, Carl
  • Apollo - University of Cambridge Repository
  • DOI: 10.17863/cam.21944

Machine learning of molecular electronic properties in chemical compound space
text, January 2013

Active learning*
journal, January 2007

Deep Learning
text, January 2018

Fast and accurate modeling of molecular atomization energies with machine learning
text, January 2012

  • Rupp, Matthias; Tkatchenko, Alexandre; Müller, Klaus-Robert
  • American Physical Society
  • DOI: 10.5451/unibas-ep43360

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

Machine learning force fields: Construction, validation, and outlook
preprint, January 2016

Machine Learning of Accurate Energy-Conserving Molecular Force Fields
text, January 2016

Deep Potential: a general representation of a many-body potential energy surface
text, January 2017

Metadynamics for Training Neural Network Model Chemistries: a Competitive Assessment
text, January 2017

DeePCG: constructing coarse-grained models via deep neural networks
text, January 2018

Fast and Accurate Uncertainty Estimation in Chemical Machine Learning
preprint, January 2018

Machine learning of molecular electronic properties in chemical compound space
text, January 2013

    Sort by:
    [ × clear filter / sort ]

    Works referencing / citing this record:

    Design, Parameterization, and Implementation of Atomic Force Fields for Adsorption in Nanoporous Materials
    journal, September 2019

    • Dubbeldam, David; Walton, Krista S.; Vlugt, Thijs J. H.
    • Advanced Theory and Simulations, Vol. 2, Issue 11
    • DOI: 10.1002/adts.201900135

    De novo exploration and self-guided learning of potential-energy surfaces
    journal, October 2019

    • Bernstein, Noam; Csányi, Gábor; Deringer, Volker L.
    • npj Computational Materials, Vol. 5, Issue 1
    • DOI: 10.1038/s41524-019-0236-6

    Deep learning inter-atomic potential model for accurate irradiation damage simulations
    journal, June 2019

    • Wang, Hao; Guo, Xun; Zhang, Linfeng
    • Applied Physics Letters, Vol. 114, Issue 24
    • DOI: 10.1063/1.5098061

    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

    • Shimamura, Kohei; Fukushima, Shogo; Koura, Akihide
    • The Journal of Chemical Physics, Vol. 151, Issue 12
    • DOI: 10.1063/1.5116420

    Ring polymer molecular dynamics and active learning of moment tensor potential for gas-phase barrierless reactions: Application to S + H 2
    journal, December 2019

    • Novikov, Ivan S.; Shapeev, Alexander V.; Suleimanov, Yury V.
    • The Journal of Chemical Physics, Vol. 151, Issue 22
    • DOI: 10.1063/1.5127561

    Uniformly accurate machine learning-based hydrodynamic models for kinetic equations
    journal, October 2019

    • Han, Jiequn; Ma, Chao; Ma, Zheng
    • Proceedings of the National Academy of Sciences, Vol. 116, Issue 44
    • DOI: 10.1073/pnas.1909854116

    Accessing thermal conductivity of complex compounds by machine learning interatomic potentials
    journal, October 2019

    Development of a deep machine learning interatomic potential for metalloid-containing Pd-Si compounds
    journal, November 2019

    De novo exploration and self-guided learning of potential-energy surfaces
    text, January 2019

    • Bernstein, Noam; Csányi, Gábor; Deringer, Volker L.
    • Apollo - University of Cambridge Repository
    • DOI: 10.17863/cam.58436
      Sort by:
      [ × clear filter / sort ]

      Similar Records in DOE PAGES and OSTI.GOV collections: