A Combined Machine Learning and High-Energy X-ray Diffraction Approach to Understanding Liquid and Amorphous Metal Oxides
Abstract
Determining the structure-property relations of liquid and amorphous metal oxides is challenging, due to their variable short-range order and polyhedral connectivity. To predict chemically realistic structures, we have developed a Machine Learned, Gaussian Approximation Potential (GAP) for HfO2, with a focus on enhanced sampling of the training database and accurate density functional theory calculations. By using training datasets for the GAP model at the level of Density Functional Theory-Strongly Constrained and Appropriately Normed (DFT-SCAN) level of theory, our results show that the topology of both the low viscosity liquid and the amorphous form are dominated by edge-shared chains and small corner-shared rings of polyhedra. This topology is shown to be consistent with the structure of other liquid and amorphous transition metal oxides of variable ion size, such as TiO2 and ZrO2. Current limitations of the ML-GAP modeling method for obtaining glass structures and future perspectives are also discussed.
- Authors:
-
- Argonne National Lab. (ANL), Argonne, IL (United States)
- Univ. of Cambridge (United Kingdom)
- Materials Development, Inc., Arlington Heights, IL (United States)
- Publication Date:
- Research Org.:
- Argonne National Laboratory (ANL), Argonne, IL (United States)
- Sponsoring Org.:
- USDOE Exascale Computing Project (ECP); USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR); USDOE National Nuclear Security Administration (NNSA)
- OSTI Identifier:
- 1960006
- Grant/Contract Number:
- AC02-06CH11357
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Journal of the Physical Society of Japan
- Additional Journal Information:
- Journal Volume: 91; Journal Issue: 9; Journal ID: ISSN 0031-9015
- Publisher:
- Physical Society of Japan
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 36 MATERIALS SCIENCE; Density Functional Theory; X-ray Diffraction; Glass Structure; Machine Learning
Citation Formats
Sivaraman, Ganesh, Csanyi, Gabor, Vazquez-Mayagoitia, Alvaro, Foster, Ian T., Wilke, Stephen K., Weber, Richard, and Benmore, Chris J. A Combined Machine Learning and High-Energy X-ray Diffraction Approach to Understanding Liquid and Amorphous Metal Oxides. United States: N. p., 2022.
Web. doi:10.7566/jpsj.91.091009.
Sivaraman, Ganesh, Csanyi, Gabor, Vazquez-Mayagoitia, Alvaro, Foster, Ian T., Wilke, Stephen K., Weber, Richard, & Benmore, Chris J. A Combined Machine Learning and High-Energy X-ray Diffraction Approach to Understanding Liquid and Amorphous Metal Oxides. United States. https://doi.org/10.7566/jpsj.91.091009
Sivaraman, Ganesh, Csanyi, Gabor, Vazquez-Mayagoitia, Alvaro, Foster, Ian T., Wilke, Stephen K., Weber, Richard, and Benmore, Chris J. Thu .
"A Combined Machine Learning and High-Energy X-ray Diffraction Approach to Understanding Liquid and Amorphous Metal Oxides". United States. https://doi.org/10.7566/jpsj.91.091009. https://www.osti.gov/servlets/purl/1960006.
@article{osti_1960006,
title = {A Combined Machine Learning and High-Energy X-ray Diffraction Approach to Understanding Liquid and Amorphous Metal Oxides},
author = {Sivaraman, Ganesh and Csanyi, Gabor and Vazquez-Mayagoitia, Alvaro and Foster, Ian T. and Wilke, Stephen K. and Weber, Richard and Benmore, Chris J.},
abstractNote = {Determining the structure-property relations of liquid and amorphous metal oxides is challenging, due to their variable short-range order and polyhedral connectivity. To predict chemically realistic structures, we have developed a Machine Learned, Gaussian Approximation Potential (GAP) for HfO2, with a focus on enhanced sampling of the training database and accurate density functional theory calculations. By using training datasets for the GAP model at the level of Density Functional Theory-Strongly Constrained and Appropriately Normed (DFT-SCAN) level of theory, our results show that the topology of both the low viscosity liquid and the amorphous form are dominated by edge-shared chains and small corner-shared rings of polyhedra. This topology is shown to be consistent with the structure of other liquid and amorphous transition metal oxides of variable ion size, such as TiO2 and ZrO2. Current limitations of the ML-GAP modeling method for obtaining glass structures and future perspectives are also discussed.},
doi = {10.7566/jpsj.91.091009},
journal = {Journal of the Physical Society of Japan},
number = 9,
volume = 91,
place = {United States},
year = {Thu Sep 15 00:00:00 EDT 2022},
month = {Thu Sep 15 00:00:00 EDT 2022}
}
Works referenced in this record:
Heat transport in liquid water from first-principles and deep neural network simulations
journal, December 2021
- Tisi, Davide; Zhang, Linfeng; Bertossa, Riccardo
- Physical Review B, Vol. 104, Issue 22
Area detector corrections for high quality synchrotron X-ray structure factor measurements
journal, January 2012
- Skinner, Lawrie B.; Benmore, Chris J.; Parise, John B.
- Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 662, Issue 1
Silicon Liquid Structure and Crystal Nucleation from Ab Initio Deep Metadynamics
journal, December 2018
- Bonati, Luigi; Parrinello, Michele
- Physical Review Letters, Vol. 121, Issue 26
A Review of High-Energy X-Ray Diffraction from Glasses and Liquids
journal, January 2012
- Benmore, C. J.
- ISRN Materials Science, Vol. 2012
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
Reverse Monte Carlo modelling
journal, November 2001
- McGreevy, R. L.
- Journal of Physics: Condensed Matter, Vol. 13, Issue 46
First-principles study of the melting temperature of MgO
journal, May 2019
- Rang, Max; Kresse, Georg
- Physical Review B, Vol. 99, Issue 18
On the Role of Long-Range Electrostatics in Machine-Learned Interatomic Potentials for Complex Battery Materials
journal, November 2021
- Staacke, Carsten G.; Heenen, Hendrik H.; Scheurer, Christoph
- ACS Applied Energy Materials, Vol. 4, Issue 11
Aerodynamic levitator for in situ x-ray structure measurements on high temperature and molten nuclear fuel materials
journal, July 2016
- Weber, J. K. R.; Tamalonis, A.; Benmore, C. J.
- Review of Scientific Instruments, Vol. 87, Issue 7
On representing chemical environments
journal, May 2013
- Bartók, Albert P.; Kondor, Risi; Csányi, Gábor
- Physical Review B, Vol. 87, Issue 18
Viscosity of silica
journal, December 2002
- Doremus, Robert H.
- Journal of Applied Physics, Vol. 92, Issue 12
Efficient implementation of atom-density representations
journal, March 2021
- Musil, Félix; Veit, Max; Goscinski, Alexander
- The Journal of Chemical Physics, Vol. 154, Issue 11
Local structure of silicate glasses
journal, October 1981
- Greaves, G. N.; Fontaine, A.; Lagarde, P.
- Nature, Vol. 293, Issue 5834
Aerodynamic levitation, supercooled liquids and glass formation
journal, May 2017
- Benmore, C. J.; Weber, J. K. R.
- Advances in Physics: X, Vol. 2, Issue 3
Strategies for the construction of machine-learning potentials for accurate and efficient atomic-scale simulations
journal, July 2021
- Miksch, April M.; Morawietz, Tobias; Kästner, Johannes
- Machine Learning: Science and Technology, Vol. 2, Issue 3
Jacob’s ladder of density functional approximations for the exchange-correlation energy
conference, January 2001
- Perdew, John P.
- Density functional theory and its application to materials, AIP Conference Proceedings
Fast Parallel Algorithms for Short-Range Molecular Dynamics
journal, March 1995
- Plimpton, Steve
- Journal of Computational Physics, Vol. 117, Issue 1
Ring statistics analysis of topological networks: New approach and application to amorphous GeS2 and SiO2 systems
journal, June 2010
- Le Roux, Sébastien; Jund, Philippe
- Computational Materials Science, Vol. 49, Issue 1
Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials
journal, March 2015
- Thompson, A. P.; Swiler, L. P.; Trott, C. R.
- Journal of Computational Physics, Vol. 285
Promoting transparency and reproducibility in enhanced molecular simulations
journal, July 2019
- ,
- Nature Methods, Vol. 16, Issue 8, p. 670-673
Modeling the Phase-Change Memory Material, Ge 2 Sb 2 Te 5 , with a Machine-Learned Interatomic Potential
journal, September 2018
- Mocanu, Felix C.; Konstantinou, Konstantinos; Lee, Tae Hoon
- The Journal of Physical Chemistry B, Vol. 122, Issue 38
Structure of molten titanium dioxide
journal, September 2014
- Alderman, O. L. G.; Skinner, L. B.; Benmore, C. J.
- Physical Review B, Vol. 90, Issue 9
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
Ab initiomolecular dynamics for liquid metals
journal, January 1993
- Kresse, G.; Hafner, J.
- Physical Review B, Vol. 47, Issue 1, p. 558-561
PLUMED 2: New feathers for an old bird
journal, February 2014
- Tribello, Gareth A.; Bonomi, Massimiliano; Branduardi, Davide
- Computer Physics Communications, Vol. 185, Issue 2
Experimentally Driven Automated Machine-Learned Interatomic Potential for a Refractory Oxide
journal, April 2021
- Sivaraman, Ganesh; Gallington, Leighanne; Krishnamoorthy, Anand Narayanan
- Physical Review Letters, Vol. 126, Issue 15
The Structure of Liquid and Amorphous Hafnia
journal, November 2017
- Gallington, Leighanne; Ghadar, Yasaman; Skinner, Lawrie
- Materials, Vol. 10, Issue 11
Meta-generalized gradient approximation: Explanation of a realistic nonempirical density functional
journal, April 2004
- Perdew, John P.; Tao, Jianmin; Staroverov, Viktor N.
- The Journal of Chemical Physics, Vol. 120, Issue 15
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
Automated Development of Molten Salt Machine Learning Potentials: Application to LiCl
journal, April 2021
- Sivaraman, Ganesh; Guo, Jicheng; Ward, Logan
- The Journal of Physical Chemistry Letters, Vol. 12, Issue 17
Strongly Constrained and Appropriately Normed Semilocal Density Functional
journal, July 2015
- Sun, Jianwei; Ruzsinszky, Adrienn; Perdew, John P.
- Physical Review Letters, Vol. 115, Issue 3
Atomic and electronic structures of an extremely fragile liquid
journal, December 2014
- Kohara, Shinji; Akola, Jaakko; Patrikeev, Leonid
- Nature Communications, Vol. 5, Issue 1
Atomic-scale structure of amorphous TiO2 by electron, X-ray diffraction and reverse Monte Carlo simulations
journal, July 1998
- Petkov, V.; Holzhüter, G.; Tröge, U.
- Journal of Non-Crystalline Solids, Vol. 231, Issue 1-2
Partial structure factors from disordered materials diffraction data: An approach using empirical potential structure refinement
journal, September 2005
- Soper, A. K.
- Physical Review B, Vol. 72, Issue 10
Machine-learned interatomic potentials by active learning: amorphous and liquid hafnium dioxide
journal, July 2020
- Sivaraman, Ganesh; Krishnamoorthy, Anand Narayanan; Baur, Matthias
- npj Computational Materials, Vol. 6, Issue 1
Phase Transition for a Hard Sphere System
journal, November 1957
- Alder, B. J.; Wainwright, T. E.
- The Journal of Chemical Physics, Vol. 27, Issue 5
Viscosity of molten silicon and the factors affecting measurement
journal, March 2003
- Sato, Yuzuru; Kameda, Yuichi; Nagasawa, Toru
- Journal of Crystal Growth, Vol. 249, Issue 3-4
Gaussian approximation potentials: A brief tutorial introduction
journal, April 2015
- Bartók, Albert P.; Csányi, Gábor
- International Journal of Quantum Chemistry, Vol. 115, Issue 16
Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set
journal, July 1996
- Kresse, G.; Furthmüller, J.
- Computational Materials Science, Vol. 6, Issue 1, p. 15-50
Well-Tempered Metadynamics: A Smoothly Converging and Tunable Free-Energy Method
journal, January 2008
- Barducci, Alessandro; Bussi, Giovanni; Parrinello, Michele
- Physical Review Letters, Vol. 100, Issue 2
Similarity Between Amorphous and Crystalline Phases: The Case of TiO 2
journal, May 2018
- Mavračić, Juraj; Mocanu, Felix C.; Deringer, Volker L.
- The Journal of Physical Chemistry Letters, Vol. 9, Issue 11
Density and viscosity of liquid ZrO2 measured by aerodynamic levitation technique
journal, July 2019
- Kondo, Toshiki; Muta, Hiroaki; Kurosaki, Ken
- Heliyon, Vol. 5, Issue 7
Properties of amorphous and crystalline titanium dioxide from first principles
journal, April 2012
- Prasai, Binay; Cai, Bin; Underwood, M. Kylee
- Journal of Materials Science, Vol. 47, Issue 21
DFT Accurate Interatomic Potential for Molten NaCl from Machine Learning
journal, November 2020
- Tovey, Samuel; Narayanan Krishnamoorthy, Anand; Sivaraman, Ganesh
- The Journal of Physical Chemistry C, Vol. 124, Issue 47
Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set
journal, October 1996
- Kresse, G.; Furthmüller, J.
- Physical Review B, Vol. 54, Issue 16, p. 11169-11186
Machine learning potentials for extended systems: a perspective
journal, July 2021
- Behler, Jörg; Csányi, Gábor
- The European Physical Journal B, Vol. 94, Issue 7
In situ Study of the Crystallization from Amorphous to Cubic Zirconium Oxide: Rietveld and Reverse Monte Carlo Analyses
journal, June 2007
- Zhang, Feng; Chupas, Peter J.; Lui, Siu Lun Alan
- Chemistry of Materials, Vol. 19, Issue 13
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
General-Purpose Machine Learning Potentials Capturing Nonlocal Charge Transfer
journal, January 2021
- Ko, Tsz Wai; Finkler, Jonas A.; Goedecker, Stefan
- Accounts of Chemical Research, Vol. 54, Issue 4
Surface Tension and Viscosity Measurements of Liquid and Undercooled Alumina by Containerless Techniques
journal, July 2005
- Paradis, Paul-François; Ishikawa, Takehiko
- Japanese Journal of Applied Physics, Vol. 44, Issue 7R
Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the Electrons
journal, April 2010
- Bartók, Albert P.; Payne, Mike C.; Kondor, Risi
- Physical Review Letters, Vol. 104, Issue 13
Machine Learning Force Fields: Construction, Validation, and Outlook
journal, December 2016
- Botu, V.; Batra, R.; Chapman, J.
- The Journal of Physical Chemistry C, Vol. 121, Issue 1
The MLIP package: Moment Tensor Potentials with MPI and Active Learning
journal, November 2020
- Novikov, Ivan S.; Gubaev, Konstantin; Podryabinkin, Evgeny
- Machine Learning: Science and Technology
Ring Configurations in a Random Network Model of Vitreous Silica
journal, March 1967
- King, Shirley V.
- Nature, Vol. 213, Issue 5081
Escaping free-energy minima
journal, September 2002
- Laio, A.; Parrinello, M.
- Proceedings of the National Academy of Sciences, Vol. 99, Issue 20
Active learning of uniformly accurate interatomic potentials for materials simulation
journal, February 2019
- Zhang, Linfeng; Lin, De-Ye; Wang, Han
- Physical Review Materials, Vol. 3, Issue 2
Machine learning based interatomic potential for amorphous carbon
journal, March 2017
- Deringer, Volker L.; Csányi, Gábor
- Physical Review B, Vol. 95, Issue 9
Correlations in the Motion of Atoms in Liquid Argon
journal, October 1964
- Rahman, A.
- Physical Review, Vol. 136, Issue 2A
Formation of Glasses from Liquids and Biopolymers
journal, March 1995
- Angell, C. A.
- Science, Vol. 267, Issue 5206
Molecular dynamics simulation of silicate glasses
journal, January 1996
- Cormack, A. N.; Cao, Yuan
- Molecular Engineering, Vol. 6, Issue 1-2
Performance of the strongly constrained and appropriately normed density functional for solid-state materials
journal, June 2018
- Isaacs, Eric B.; Wolverton, Chris
- Physical Review Materials, Vol. 2, Issue 6