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

Title: Machine-learned interatomic potentials by active learning: amorphous and liquid hafnium dioxide

Abstract

We propose an active learning scheme for automatically sampling a minimum number of uncorrelated configurations for fitting the Gaussian Approximation Potential (GAP). Our active learning scheme consists of an unsupervised machine learning (ML) scheme coupled with a Bayesian optimization technique that evaluates the GAP model. We apply this scheme to a Hafnium dioxide (HfO2) dataset generated from a "melt-quench" ab initio molecular dynamics (AIMD) protocol. Our results show that the active learning scheme, with no prior knowledge of the dataset, is able to extract a configuration that reaches the required energy fit tolerance. Further, molecular dynamics (MD) simulations performed using this active learned GAP model on 6144 atom systems of amorphous and liquid state elucidate the structural properties of HfO2 with near ab initio precision and quench rates (i.e., 1.0 K/ps) not accessible via AIMD. The melt and amorphous X-ray structural factors generated from our simulation are in good agreement with experiment. In addition, the calculated diffusion constants are in good agreement with previous ab initio studies.

Authors:
ORCiD logo [1];  [2]; ORCiD logo [3];  [3];  [1];  [4];  [1]; ORCiD logo [1]
  1. Argonne National Lab. (ANL), Argonne, IL (United States)
  2. Univ. of Stuttgart (Germany); Helmholtz-Inst., Munster (Germany)
  3. Univ. of Stuttgart (Germany)
  4. Univ. of Cambridge (United Kingdom)
Publication Date:
Research Org.:
Argonne National Lab. (ANL), Argonne, IL (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Basic Energy Sciences (BES); USDOE Laboratory Directed Research and Development (LDRD) Program; German Funding Agency
OSTI Identifier:
1660445
Grant/Contract Number:  
AC02-06CH11357; EXC 2075 - 390740016
Resource Type:
Accepted Manuscript
Journal Name:
npj Computational Materials
Additional Journal Information:
Journal Volume: 6; Journal Issue: 1; Journal ID: ISSN 2057-3960
Publisher:
Nature Publishing Group
Country of Publication:
United States
Language:
English

Citation Formats

Sivaraman, Ganesh, Krishnamoorthy, Anand Narayanan, Baur, Matthias, Holm, Christian, Stan, Marius, Csányi, Gábor, Benmore, Chris, and Vázquez-Mayagoitia, Álvaro. Machine-learned interatomic potentials by active learning: amorphous and liquid hafnium dioxide. United States: N. p., 2020. Web. doi:10.1038/s41524-020-00367-7.
Sivaraman, Ganesh, Krishnamoorthy, Anand Narayanan, Baur, Matthias, Holm, Christian, Stan, Marius, Csányi, Gábor, Benmore, Chris, & Vázquez-Mayagoitia, Álvaro. Machine-learned interatomic potentials by active learning: amorphous and liquid hafnium dioxide. United States. doi:10.1038/s41524-020-00367-7.
Sivaraman, Ganesh, Krishnamoorthy, Anand Narayanan, Baur, Matthias, Holm, Christian, Stan, Marius, Csányi, Gábor, Benmore, Chris, and Vázquez-Mayagoitia, Álvaro. Thu . "Machine-learned interatomic potentials by active learning: amorphous and liquid hafnium dioxide". United States. doi:10.1038/s41524-020-00367-7. https://www.osti.gov/servlets/purl/1660445.
@article{osti_1660445,
title = {Machine-learned interatomic potentials by active learning: amorphous and liquid hafnium dioxide},
author = {Sivaraman, Ganesh and Krishnamoorthy, Anand Narayanan and Baur, Matthias and Holm, Christian and Stan, Marius and Csányi, Gábor and Benmore, Chris and Vázquez-Mayagoitia, Álvaro},
abstractNote = {We propose an active learning scheme for automatically sampling a minimum number of uncorrelated configurations for fitting the Gaussian Approximation Potential (GAP). Our active learning scheme consists of an unsupervised machine learning (ML) scheme coupled with a Bayesian optimization technique that evaluates the GAP model. We apply this scheme to a Hafnium dioxide (HfO2) dataset generated from a "melt-quench" ab initio molecular dynamics (AIMD) protocol. Our results show that the active learning scheme, with no prior knowledge of the dataset, is able to extract a configuration that reaches the required energy fit tolerance. Further, molecular dynamics (MD) simulations performed using this active learned GAP model on 6144 atom systems of amorphous and liquid state elucidate the structural properties of HfO2 with near ab initio precision and quench rates (i.e., 1.0 K/ps) not accessible via AIMD. The melt and amorphous X-ray structural factors generated from our simulation are in good agreement with experiment. In addition, the calculated diffusion constants are in good agreement with previous ab initio studies.},
doi = {10.1038/s41524-020-00367-7},
journal = {npj Computational Materials},
number = 1,
volume = 6,
place = {United States},
year = {2020},
month = {7}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Save / Share:

Works referenced in this record:

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

Hafnia and hafnia-toughened ceramics
journal, January 1992

  • Wang, J.; Li, H. P.; Stevens, R.
  • Journal of Materials Science, Vol. 27, Issue 20
  • DOI: 10.1007/BF00541601

Reverse Monte Carlo Simulation: A New Technique for the Determination of Disordered Structures
journal, December 1988


New opportunities for materials informatics: Resources and data mining techniques for uncovering hidden relationships
journal, April 2016

  • Jain, Anubhav; Hautier, Geoffroy; Ong, Shyue Ping
  • Journal of Materials Research, Vol. 31, Issue 8
  • DOI: 10.1557/jmr.2016.80

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

Structure, thermodynamics, and crystallization of amorphous hafnia
journal, September 2015

  • Luo, Xuhui; Demkov, Alexander A.
  • Journal of Applied Physics, Vol. 118, Issue 12
  • DOI: 10.1063/1.4931157

Molecular dynamics simulation of amorphous HfO 2 for resistive RAM applications
journal, July 2014

  • Broglia, G.; Ori, G.; Larcher, L.
  • Modelling and Simulation in Materials Science and Engineering, Vol. 22, Issue 6
  • DOI: 10.1088/0965-0393/22/6/065006

On representing chemical environments
journal, May 2013


From ultrasoft pseudopotentials to the projector augmented-wave method
journal, January 1999


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


Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials
journal, March 2015


Thermodynamic limit for synthesis of metastable inorganic materials
journal, April 2018

  • Aykol, Muratahan; Dwaraknath, Shyam S.; Sun, Wenhao
  • Science Advances, Vol. 4, Issue 4
  • DOI: 10.1126/sciadv.aaq0148

Accelerated Hierarchical Density Based Clustering
conference, November 2017

  • McInnes, Leland; Healy, John
  • 2017 IEEE International Conference on Data Mining Workshops (ICDMW)
  • DOI: 10.1109/ICDMW.2017.12

Molecular Dynamics with On-the-Fly Machine Learning of Quantum-Mechanical Forces
journal, March 2015


SchNet – A deep learning architecture for molecules and materials
journal, June 2018

  • Schütt, K. T.; Sauceda, H. E.; Kindermans, P. -J.
  • The Journal of Chemical Physics, Vol. 148, Issue 24
  • DOI: 10.1063/1.5019779

Moment Tensor Potentials: A Class of Systematically Improvable Interatomic Potentials
journal, January 2016

  • Shapeev, Alexander V.
  • Multiscale Modeling & Simulation, Vol. 14, Issue 3
  • DOI: 10.1137/15M1054183

Perspective: Machine learning potentials for atomistic simulations
journal, November 2016

  • Behler, Jörg
  • The Journal of Chemical Physics, Vol. 145, Issue 17
  • DOI: 10.1063/1.4966192

Accelerating high-throughput searches for new alloys with active learning of interatomic potentials
journal, January 2019


The Structure of Liquid and Amorphous Hafnia
journal, November 2017

  • Gallington, Leighanne; Ghadar, Yasaman; Skinner, Lawrie
  • Materials, Vol. 10, Issue 11
  • DOI: 10.3390/ma10111290

A unified formulation of the constant temperature molecular dynamics methods
journal, July 1984

  • Nosé, Shuichi
  • The Journal of Chemical Physics, Vol. 81, Issue 1
  • DOI: 10.1063/1.447334

sGDML: Constructing accurate and data efficient molecular force fields using machine learning
journal, July 2019

  • Chmiela, Stefan; Sauceda, Huziel E.; Poltavsky, Igor
  • Computer Physics Communications, Vol. 240
  • DOI: 10.1016/j.cpc.2019.02.007

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

MDTraj: A Modern Open Library for the Analysis of Molecular Dynamics Trajectories
journal, October 2015

  • McGibbon, Robert T.; Beauchamp, Kyle A.; Harrigan, Matthew P.
  • Biophysical Journal, Vol. 109, Issue 8
  • DOI: 10.1016/j.bpj.2015.08.015

Transport Coefficients from Dissipation in a Canonical Ensemble
journal, July 1960


Self-Consistent Equations Including Exchange and Correlation Effects
journal, November 1965


Two faces of active learning
journal, April 2011


Hierarchical sampling for active learning
conference, January 2008

  • Dasgupta, Sanjoy; Hsu, Daniel
  • Proceedings of the 25th international conference on Machine learning - ICML '08
  • DOI: 10.1145/1390156.1390183

Determination of surface diffusion coefficients by Monte Carlo methods: Comparison of fluctuation and Kubo–Green methods
journal, May 1994

  • Uebing, Christian; Gomer, Robert
  • The Journal of Chemical Physics, Vol. 100, Issue 10
  • DOI: 10.1063/1.466819

Data-Driven Learning of Total and Local Energies in Elemental Boron
journal, April 2018


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


How van der Waals interactions determine the unique properties of water
journal, July 2016

  • Morawietz, Tobias; Singraber, Andreas; Dellago, Christoph
  • Proceedings of the National Academy of Sciences, Vol. 113, Issue 30
  • DOI: 10.1073/pnas.1602375113

RMC_POT: A computer code for reverse monte carlo modeling the structure of disordered systems containing molecules of arbitrary complexity
journal, July 2012

  • Gereben, Orsolya; Pusztai, László
  • Journal of Computational Chemistry, Vol. 33, Issue 29
  • DOI: 10.1002/jcc.23058

Design and synthesis of the superionic conductor Na10SnP2S12
journal, March 2016

  • Richards, William D.; Tsujimura, Tomoyuki; Miara, Lincoln J.
  • Nature Communications, Vol. 7, Issue 1
  • DOI: 10.1038/ncomms11009

Taking the Human Out of the Loop: A Review of Bayesian Optimization
journal, January 2016


Gate Oxides Beyond SiO 2
journal, November 2008

  • Schlom, Darrell G.; Guha, Supratik; Datta, Suman
  • MRS Bulletin, Vol. 33, Issue 11
  • DOI: 10.1557/mrs2008.221

Inhomogeneous Electron Gas
journal, November 1964


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


High-k (k=30) amorphous hafnium oxide films from high rate room temperature deposition
journal, June 2011

  • Li, Flora M.; Bayer, Bernhard C.; Hofmann, Stephan
  • Applied Physics Letters, Vol. 98, Issue 25
  • DOI: 10.1063/1.3601487

Validation of molecular dynamics simulation
journal, April 1998

  • van Gunsteren, Wilfred F.; Mark, Alan E.
  • The Journal of Chemical Physics, Vol. 108, Issue 15
  • DOI: 10.1063/1.476021

Polymorphic transitions in single crystals: A new molecular dynamics method
journal, December 1981

  • Parrinello, M.; Rahman, A.
  • Journal of Applied Physics, Vol. 52, Issue 12
  • DOI: 10.1063/1.328693

Realistic Atomistic Structure of Amorphous Silicon from Machine-Learning-Driven Molecular Dynamics
journal, May 2018

  • Deringer, Volker L.; Bernstein, Noam; Bartók, Albert P.
  • The Journal of Physical Chemistry Letters, Vol. 9, Issue 11
  • DOI: 10.1021/acs.jpclett.8b00902

Temperature effects on the ionic conductivity in concentrated alkaline electrolyte solutions
journal, January 2020

  • Shao, Yunqi; Hellström, Matti; Yllö, Are
  • Physical Chemistry Chemical Physics, Vol. 22, Issue 19
  • DOI: 10.1039/C9CP06479F

What are the true clusters?
journal, October 2015


Canonical dynamics: Equilibrium phase-space distributions
journal, March 1985


PACKMOL: A package for building initial configurations for molecular dynamics simulations
journal, October 2009

  • Martínez, L.; Andrade, R.; Birgin, E. G.
  • Journal of Computational Chemistry, Vol. 30, Issue 13
  • DOI: 10.1002/jcc.21224

hdbscan: Hierarchical density based clustering
journal, March 2017

  • McInnes, Leland; Healy, John; Astels, Steve
  • The Journal of Open Source Software, Vol. 2, Issue 11
  • DOI: 10.21105/joss.00205

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


Rapid estimation of elastic constants by molecular dynamics simulation under constant stress
journal, April 2004


Constant pressure molecular dynamics algorithms
journal, September 1994

  • Martyna, Glenn J.; Tobias, Douglas J.; Klein, Michael L.
  • The Journal of Chemical Physics, Vol. 101, Issue 5
  • DOI: 10.1063/1.467468

Active learning of uniformly accurate interatomic potentials for materials simulation
journal, February 2019


Machine learning based interatomic potential for amorphous carbon
journal, March 2017


Perspective on density functional theory
journal, April 2012

  • Burke, Kieron
  • The Journal of Chemical Physics, Vol. 136, Issue 15
  • DOI: 10.1063/1.4704546

Performance and Cost Assessment of Machine Learning Interatomic Potentials
journal, October 2019

  • Zuo, Yunxing; Chen, Chi; Li, Xiangguo
  • The Journal of Physical Chemistry A, Vol. 124, Issue 4
  • DOI: 10.1021/acs.jpca.9b08723

Uncovering Large-Scale Conformational Change in Molecular Dynamics without Prior Knowledge
journal, November 2016

  • Melvin, Ryan L.; Godwin, Ryan C.; Xiao, Jiajie
  • Journal of Chemical Theory and Computation, Vol. 12, Issue 12
  • DOI: 10.1021/acs.jctc.6b00757