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

Title: Graph dynamical networks for unsupervised learning of atomic scale dynamics in materials

Abstract

Understanding the dynamical processes that govern the performance of functional materials is essential for the design of next generation materials to tackle global energy and environmental challenges. Many of these processes involve the dynamics of individual atoms or small molecules in condensed phases, e.g. lithium ions in electrolytes, water molecules in membranes, molten atoms at interfaces, etc., which are difficult to understand due to the complexity of local environments. In this work, we develop graph dynamical networks, an unsupervised learning approach for understanding atomic scale dynamics in arbitrary phases and environments from molecular dynamics simulations. We show that important dynamical information, which would be difficult to obtain otherwise, can be learned for various multi-component amorphous material systems. With the large amounts of molecular dynamics data generated every day in nearly every aspect of materials design, this approach provides a broadly applicable, automated tool to understand atomic scale dynamics in material systems.

Authors:
 [1];  [1]; ORCiD logo [1];  [1]; ORCiD logo [1]
  1. Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)
Publication Date:
Research Org.:
Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States). National Energy Research Scientific Computing Center (NERSC)
Sponsoring Org.:
USDOE Office of Science (SC), Basic Energy Sciences (BES) (SC-22). Scientific User Facilities Division
OSTI Identifier:
1577554
Grant/Contract Number:  
AC02-05CH11231; ACI-1053575
Resource Type:
Accepted Manuscript
Journal Name:
Nature Communications
Additional Journal Information:
Journal Volume: 10; Journal Issue: 1; Journal ID: ISSN 2041-1723
Publisher:
Nature Publishing Group
Country of Publication:
United States
Language:
English
Subject:
36 MATERIALS SCIENCE; Science & Technology - Other Topics

Citation Formats

Xie, Tian, France-Lanord, Arthur, Wang, Yanming, Shao-Horn, Yang, and Grossman, Jeffrey C. Graph dynamical networks for unsupervised learning of atomic scale dynamics in materials. United States: N. p., 2019. Web. doi:10.1038/s41467-019-10663-6.
Xie, Tian, France-Lanord, Arthur, Wang, Yanming, Shao-Horn, Yang, & Grossman, Jeffrey C. Graph dynamical networks for unsupervised learning of atomic scale dynamics in materials. United States. doi:10.1038/s41467-019-10663-6.
Xie, Tian, France-Lanord, Arthur, Wang, Yanming, Shao-Horn, Yang, and Grossman, Jeffrey C. Mon . "Graph dynamical networks for unsupervised learning of atomic scale dynamics in materials". United States. doi:10.1038/s41467-019-10663-6. https://www.osti.gov/servlets/purl/1577554.
@article{osti_1577554,
title = {Graph dynamical networks for unsupervised learning of atomic scale dynamics in materials},
author = {Xie, Tian and France-Lanord, Arthur and Wang, Yanming and Shao-Horn, Yang and Grossman, Jeffrey C.},
abstractNote = {Understanding the dynamical processes that govern the performance of functional materials is essential for the design of next generation materials to tackle global energy and environmental challenges. Many of these processes involve the dynamics of individual atoms or small molecules in condensed phases, e.g. lithium ions in electrolytes, water molecules in membranes, molten atoms at interfaces, etc., which are difficult to understand due to the complexity of local environments. In this work, we develop graph dynamical networks, an unsupervised learning approach for understanding atomic scale dynamics in arbitrary phases and environments from molecular dynamics simulations. We show that important dynamical information, which would be difficult to obtain otherwise, can be learned for various multi-component amorphous material systems. With the large amounts of molecular dynamics data generated every day in nearly every aspect of materials design, this approach provides a broadly applicable, automated tool to understand atomic scale dynamics in material systems.},
doi = {10.1038/s41467-019-10663-6},
journal = {Nature Communications},
number = 1,
volume = 10,
place = {United States},
year = {2019},
month = {6}
}

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

Citation Metrics:
Cited by: 3 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Learning atoms for materials discovery
journal, June 2018

  • Zhou, Quan; Tang, Peizhe; Liu, Shenxiu
  • Proceedings of the National Academy of Sciences, Vol. 115, Issue 28
  • DOI: 10.1073/pnas.1801181115

Understanding the Lithium Transport within a Rouse-Based Model for a PEO/LiTFSI Polymer Electrolyte
journal, February 2010

  • Diddens, Diddo; Heuer, Andreas; Borodin, Oleg
  • Macromolecules, Vol. 43, Issue 4
  • DOI: 10.1021/ma901893h

Transfer Learning from Markov Models Leads to Efficient Sampling of Related Systems
journal, September 2017

  • Sultan, Mohammad M.; Pande, Vijay S.
  • The Journal of Physical Chemistry B, Vol. 122, Issue 21
  • DOI: 10.1021/acs.jpcb.7b06896

Hamiltonian Systems and Transformation in Hilbert Space
journal, May 1931

  • Koopman, B. O.
  • Proceedings of the National Academy of Sciences, Vol. 17, Issue 5
  • DOI: 10.1073/pnas.17.5.315

Jump relaxation in solid electrolytes
journal, January 1993


VAMPnets for deep learning of molecular kinetics
journal, January 2018


Markov state model of the two-state behaviour of water
journal, October 2016

  • Hamm, Peter
  • The Journal of Chemical Physics, Vol. 145, Issue 13
  • DOI: 10.1063/1.4963305

On representing chemical environments
journal, May 2013


Graph Theory Meets Ab Initio Molecular Dynamics: Atomic Structures and Transformations at the Nanoscale
journal, August 2011


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


Building Markov state models with solvent dynamics
journal, January 2013


Collective hydrogen-bond rearrangement dynamics in liquid water
journal, December 2018

  • Schulz, R.; von Hansen, Y.; Daldrop, J. O.
  • The Journal of Chemical Physics, Vol. 149, Issue 24
  • DOI: 10.1063/1.5054267

Gas Adsorption Sites in a Large-Pore Metal-Organic Framework
journal, August 2005

  • Rowsell, Jesse L. C.; Spencer, Elinor C.; Eckert, Juergen
  • Science, Vol. 309, Issue 5739, p. 1350-1354
  • DOI: 10.1126/science.1113247

Polymer Electrolytes
journal, July 2013


Mechanism of Ion Transport in Amorphous Poly(ethylene oxide)/LiTFSI from Molecular Dynamics Simulations
journal, February 2006

  • Borodin, Oleg; Smith, Grant D.
  • Macromolecules, Vol. 39, Issue 4
  • DOI: 10.1021/ma052277v

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

Extended dynamic mode decomposition with dictionary learning: A data-driven adaptive spectral decomposition of the Koopman operator
journal, October 2017

  • Li, Qianxiao; Dietrich, Felix; Bollt, Erik M.
  • Chaos: An Interdisciplinary Journal of Nonlinear Science, Vol. 27, Issue 10
  • DOI: 10.1063/1.4993854

Markov State Models: From an Art to a Science
journal, February 2018

  • Husic, Brooke E.; Pande, Vijay S.
  • Journal of the American Chemical Society, Vol. 140, Issue 7
  • DOI: 10.1021/jacs.7b12191

Negative Transference Numbers in Poly(ethylene oxide)-Based Electrolytes
journal, January 2017

  • Pesko, Danielle M.; Timachova, Ksenia; Bhattacharya, Rajashree
  • Journal of The Electrochemical Society, Vol. 164, Issue 11
  • DOI: 10.1149/2.0581711jes

Nonaqueous Liquid Electrolytes for Lithium-Based Rechargeable Batteries
journal, October 2004


Deep learning for universal linear embeddings of nonlinear dynamics
journal, November 2018


Markov Chain Models for the Stochastic Modeling of Pitting Corrosion
journal, January 2013

  • Valor, A.; Caleyo, F.; Alfonso, L.
  • Mathematical Problems in Engineering, Vol. 2013
  • DOI: 10.1155/2013/108386

Selective gas adsorption and separation in metal–organic frameworks
journal, January 2009

  • Li, Jian-Rong; Kuppler, Ryan J.; Zhou, Hong-Cai
  • Chemical Society Reviews, Vol. 38, Issue 5, p. 1477-1504
  • DOI: 10.1039/b802426j

Designing Carbon Nanotube Membranes for Efficient Water Desalination
journal, February 2008

  • Corry, Ben
  • The Journal of Physical Chemistry B, Vol. 112, Issue 5
  • DOI: 10.1021/jp709845u

Review of the proton exchange membranes for fuel cell applications
journal, September 2010

  • Peighambardoust, S. J.; Rowshanzamir, S.; Amjadi, M.
  • International Journal of Hydrogen Energy, Vol. 35, Issue 17
  • DOI: 10.1016/j.ijhydene.2010.05.017

Structural Properties of Defects in Glassy Liquids
journal, April 2016

  • Cubuk, Ekin D.; Schoenholz, Samuel S.; Kaxiras, Efthimios
  • The Journal of Physical Chemistry B, Vol. 120, Issue 26
  • DOI: 10.1021/acs.jpcb.6b02144

Water Desalination across Nanoporous Graphene
journal, June 2012

  • Cohen-Tanugi, David; Grossman, Jeffrey C.
  • Nano Letters, Vol. 12, Issue 7, p. 3602-3608
  • DOI: 10.1021/nl3012853

Everything you wanted to know about Markov State Models but were afraid to ask
journal, September 2010


Relaxation in polymer electrolytes on the nanosecond timescale
journal, May 2000

  • Mao, Guomin; Perea, Ricardo Fernandez; Howells, W. Spencer
  • Nature, Vol. 405, Issue 6783
  • DOI: 10.1038/35012032

Molecular graph convolutions: moving beyond fingerprints
journal, August 2016

  • Kearnes, Steven; McCloskey, Kevin; Berndl, Marc
  • Journal of Computer-Aided Molecular Design, Vol. 30, Issue 8
  • DOI: 10.1007/s10822-016-9938-8

Li + Transport in Poly(Ethylene Oxide) Based Electrolytes: Neutron Scattering, Dielectric Spectroscopy, and Molecular Dynamics Simulations
journal, July 2013


Markov state models of biomolecular conformational dynamics
journal, April 2014


Review and Analysis of Molecular Simulations of Methane, Hydrogen, and Acetylene Storage in Metal–Organic Frameworks
journal, September 2011

  • Getman, Rachel B.; Bae, Youn-Sang; Wilmer, Christopher E.
  • Chemical Reviews, Vol. 112, Issue 2, p. 703-723
  • DOI: 10.1021/cr200217c

Atomistic mechanisms of orientation and temperature dependence in gold-catalyzed silicon growth
journal, August 2017

  • Wang, Yanming; Santana, Adriano; Cai, Wei
  • Journal of Applied Physics, Vol. 122, Issue 8
  • DOI: 10.1063/1.4991362

Design principles for solid-state lithium superionic conductors
journal, August 2015

  • Wang, Yan; Richards, William Davidson; Ong, Shyue Ping
  • Nature Materials, Vol. 14, Issue 10
  • DOI: 10.1038/nmat4369

Coarse Master Equation from Bayesian Analysis of Replica Molecular Dynamics Simulations
journal, April 2005

  • Sriraman, Saravanapriyan; Kevrekidis, Ioannis G.; Hummer, Gerhard
  • The Journal of Physical Chemistry B, Vol. 109, Issue 14
  • DOI: 10.1021/jp046448u

Membrane Desalination: Where Are We, and What Can We Learn from Fundamentals?
journal, June 2016


Reweighted autoencoded variational Bayes for enhanced sampling (RAVE)
journal, August 2018

  • Ribeiro, João Marcelo Lamim; Bravo, Pablo; Wang, Yihang
  • The Journal of Chemical Physics, Vol. 149, Issue 7
  • DOI: 10.1063/1.5025487

Correlations from Ion Pairing and the Nernst-Einstein Equation
journal, April 2019


Liquid–liquid phase transition in supercooled silicon
journal, October 2003

  • Sastry, Srikanth; Austen Angell, C.
  • Nature Materials, Vol. 2, Issue 11
  • DOI: 10.1038/nmat994

Insights into Phases of Liquid Water from Study of Its Unusual Glass-Forming Properties
journal, February 2008


Time-lagged autoencoders: Deep learning of slow collective variables for molecular kinetics
journal, June 2018

  • Wehmeyer, Christoph; Noé, Frank
  • The Journal of Chemical Physics, Vol. 148, Issue 24
  • DOI: 10.1063/1.5011399

Challenges in the development of advanced Li-ion batteries: a review
journal, January 2011

  • Etacheri, Vinodkumar; Marom, Rotem; Elazari, Ran
  • Energy & Environmental Science, Vol. 4, Issue 9
  • DOI: 10.1039/c1ee01598b

Acidic Properties and Structure–Activity Correlations of Solid Acid Catalysts Revealed by Solid-State NMR Spectroscopy
journal, March 2016


Designing Polymer Electrolytes for Safe and High Capacity Rechargeable Lithium Batteries
journal, March 2017


Markov chain model of electrochemical alloy deposition
journal, November 2005


Hierarchical visualization of materials space with graph convolutional neural networks
journal, November 2018

  • Xie, Tian; Grossman, Jeffrey C.
  • The Journal of Chemical Physics, Vol. 149, Issue 17
  • DOI: 10.1063/1.5047803

Analysis of Fluid Flows via Spectral Properties of the Koopman Operator
journal, January 2013


Quantum-chemical insights from deep tensor neural networks
journal, January 2017

  • Schütt, Kristof T.; Arbabzadah, Farhad; Chmiela, Stefan
  • Nature Communications, Vol. 8, Issue 1
  • DOI: 10.1038/ncomms13890

Coarse Master Equations for Peptide Folding Dynamics
journal, May 2008

  • Buchete, Nicolae-Viorel; Hummer, Gerhard
  • The Journal of Physical Chemistry B, Vol. 112, Issue 19
  • DOI: 10.1021/jp0761665

Unsupervised landmark analysis for jump detection in molecular dynamics simulations
journal, May 2019


Polymer Electrolytes for Lithium-Ion Batteries
journal, April 1998


Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
journal, April 2018


Master Equation Methods in Gas Phase Chemical Kinetics
journal, September 2006

  • Miller, James A.; Klippenstein, Stephen J.
  • The Journal of Physical Chemistry A, Vol. 110, Issue 36
  • DOI: 10.1021/jp062693x

Low Data Drug Discovery with One-Shot Learning
journal, April 2017


Vibrational Spectroscopy and Dynamics of Water
journal, April 2016


Inorganic Solid-State Electrolytes for Lithium Batteries: Mechanisms and Properties Governing Ion Conduction
journal, December 2015


Unravelling Li-Ion Transport from Picoseconds to Seconds: Bulk versus Interfaces in an Argyrodite Li 6 PS 5 Cl–Li 2 S All-Solid-State Li-Ion Battery
journal, August 2016

  • Yu, Chuang; Ganapathy, Swapna; de Klerk, Niek J. J.
  • Journal of the American Chemical Society, Vol. 138, Issue 35
  • DOI: 10.1021/jacs.6b05066

    Works referencing / citing this record:

    Dynamic graphical models of molecular kinetics
    journal, July 2019

    • Olsson, Simon; Noé, Frank
    • Proceedings of the National Academy of Sciences, Vol. 116, Issue 30
    • DOI: 10.1073/pnas.1901692116