DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Learning from Imperfections: Predicting Structure and Thermodynamics from Atomic Imaging of Fluctuations

Abstract

In materials characterization, traditionally a single experimental sample is used to derive information about a single point in the composition space, while the imperfections, impurities, and stochastic details of material structure are deemed irrelevant or complicating factors in the analysis. Here we demonstrate that atomic-scale studies of a single nominal composition can provide information about microstructures and thermodynamic response over a finite area of chemical space. Using the principles of statistical inference, we develop a framework for incorporating structural fluctuations into statistical mechanical models and use it to solve the inverse problem of deriving effective interatomic interactions responsible for elemental segregation in a La5/8Ca3/8MnO3 thin film. Here, the results are further analyzed by a variational autoencoder to detect anomalous behavior in the composition phase diagram. This study provides a framework for creating generative models from a combination of multiple experimental data and provides direct insight into the driving forces for cation segregation in manganites.

Authors:
ORCiD logo [1]; ORCiD logo [2]; ORCiD logo [1]; ORCiD logo [3]; ORCiD logo [2]; ORCiD logo [2]; ORCiD logo [2]
  1. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States); Univ. of Tennessee, Knoxville, TN (United States)
  2. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
  3. CICECO - Aveiro Institute of Materials, Aveiro (Portugal)
Publication Date:
Research Org.:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Basic Energy Sciences (BES)
OSTI Identifier:
1505330
Grant/Contract Number:  
AC05-00OR22725
Resource Type:
Accepted Manuscript
Journal Name:
ACS Nano
Additional Journal Information:
Journal Volume: 13; Journal Issue: 1; Journal ID: ISSN 1936-0851
Publisher:
American Chemical Society (ACS)
Country of Publication:
United States
Language:
English
Subject:
36 MATERIALS SCIENCE; generative model; manganite; scanning tunneling microscopy; segregation; statistical inference; thin film

Citation Formats

Vlcek, Lukas, Ziatdinov, Maxim, Maksov, Artem, Tselev, Alexander, Baddorf, Arthur P., Kalinin, Sergei V., and Vasudevan, Rama K. Learning from Imperfections: Predicting Structure and Thermodynamics from Atomic Imaging of Fluctuations. United States: N. p., 2018. Web. doi:10.1021/acsnano.8b07980.
Vlcek, Lukas, Ziatdinov, Maxim, Maksov, Artem, Tselev, Alexander, Baddorf, Arthur P., Kalinin, Sergei V., & Vasudevan, Rama K. Learning from Imperfections: Predicting Structure and Thermodynamics from Atomic Imaging of Fluctuations. United States. https://doi.org/10.1021/acsnano.8b07980
Vlcek, Lukas, Ziatdinov, Maxim, Maksov, Artem, Tselev, Alexander, Baddorf, Arthur P., Kalinin, Sergei V., and Vasudevan, Rama K. Tue . "Learning from Imperfections: Predicting Structure and Thermodynamics from Atomic Imaging of Fluctuations". United States. https://doi.org/10.1021/acsnano.8b07980. https://www.osti.gov/servlets/purl/1505330.
@article{osti_1505330,
title = {Learning from Imperfections: Predicting Structure and Thermodynamics from Atomic Imaging of Fluctuations},
author = {Vlcek, Lukas and Ziatdinov, Maxim and Maksov, Artem and Tselev, Alexander and Baddorf, Arthur P. and Kalinin, Sergei V. and Vasudevan, Rama K.},
abstractNote = {In materials characterization, traditionally a single experimental sample is used to derive information about a single point in the composition space, while the imperfections, impurities, and stochastic details of material structure are deemed irrelevant or complicating factors in the analysis. Here we demonstrate that atomic-scale studies of a single nominal composition can provide information about microstructures and thermodynamic response over a finite area of chemical space. Using the principles of statistical inference, we develop a framework for incorporating structural fluctuations into statistical mechanical models and use it to solve the inverse problem of deriving effective interatomic interactions responsible for elemental segregation in a La5/8Ca3/8MnO3 thin film. Here, the results are further analyzed by a variational autoencoder to detect anomalous behavior in the composition phase diagram. This study provides a framework for creating generative models from a combination of multiple experimental data and provides direct insight into the driving forces for cation segregation in manganites.},
doi = {10.1021/acsnano.8b07980},
journal = {ACS Nano},
number = 1,
volume = 13,
place = {United States},
year = {2018},
month = {12}
}

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:

Fulfilling the promise of the materials genome initiative with high-throughput experimental methodologies
journal, March 2017

  • Green, M. L.; Choi, C. L.; Hattrick-Simpers, J. R.
  • Applied Physics Reviews, Vol. 4, Issue 1
  • DOI: 10.1063/1.4977487

Informatics Infrastructure for the Materials Genome Initiative
journal, July 2016


Phase development and electrical property analysis of pulsed laser deposited Pb(Mg1/3Nb2/3)O3–PbTiO3 (70/30) epitaxial thin films
journal, November 1998

  • Maria, J. -P.; Hackenberger, W.; Trolier-McKinstry, S.
  • Journal of Applied Physics, Vol. 84, Issue 9
  • DOI: 10.1063/1.368809

Relaxor ferroelectrics
journal, December 1987


Atomic-scale images of charge ordering in a mixed-valence manganite
journal, April 2002

  • Renner, Ch.; Aeppli, G.; Kim, B. -G.
  • Nature, Vol. 416, Issue 6880
  • DOI: 10.1038/416518a

Metastable Filamentary Vortex Flow in Thin Film Superconductors
journal, April 1996

  • Grønbech-Jensen, Niels; Bishop, A. R.; Domínguez, Daniel
  • Physical Review Letters, Vol. 76, Issue 16
  • DOI: 10.1103/PhysRevLett.76.2985

A computational high-throughput search for new ternary superalloys
journal, January 2017


Perspective: Composition–structure–property mapping in high-throughput experiments: Turning data into knowledge
journal, May 2016

  • Hattrick-Simpers, Jason R.; Gregoire, John M.; Kusne, A. Gilad
  • APL Materials, Vol. 4, Issue 5
  • DOI: 10.1063/1.4950995

On-the-fly machine-learning for high-throughput experiments: search for rare-earth-free permanent magnets
journal, September 2014

  • Kusne, Aaron Gilad; Gao, Tieren; Mehta, Apurva
  • Scientific Reports, Vol. 4, Issue 1
  • DOI: 10.1038/srep06367

The high-throughput highway to computational materials design
journal, February 2013

  • Curtarolo, Stefano; Hart, Gus L. W.; Nardelli, Marco Buongiorno
  • Nature Materials, Vol. 12, Issue 3
  • DOI: 10.1038/nmat3568

A high-throughput infrastructure for density functional theory calculations
journal, June 2011


AFLOWLIB.ORG: A distributed materials properties repository from high-throughput ab initio calculations
journal, June 2012


A polymer dataset for accelerated property prediction and design
journal, March 2016

  • Huan, Tran Doan; Mannodi-Kanakkithodi, Arun; Kim, Chiho
  • Scientific Data, Vol. 3, Issue 1
  • DOI: 10.1038/sdata.2016.12

Finding Density Functionals with Machine Learning
journal, June 2012


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


How to represent crystal structures for machine learning: Towards fast prediction of electronic properties
journal, May 2014


Statistical inference and adaptive design for materials discovery
journal, June 2017

  • Lookman, Turab; Balachandran, Prasanna V.; Xue, Dezhen
  • Current Opinion in Solid State and Materials Science, Vol. 21, Issue 3
  • DOI: 10.1016/j.cossms.2016.10.002

Perspective: Codesign for materials science: An optimal learning approach
journal, April 2016

  • Lookman, Turab; Alexander, Francis J.; Bishop, Alan R.
  • APL Materials, Vol. 4, Issue 5
  • DOI: 10.1063/1.4944627

Verification of the Crooks fluctuation theorem and recovery of RNA folding free energies
journal, September 2005


Experimental Free Energy Surface Reconstruction from Single-Molecule Force Spectroscopy using Jarzynski’s Equality
journal, August 2007


Equilibrium free energies from non-equilibrium trajectories with relaxation fluctuation spectroscopy
journal, May 2018

  • Ross, David; Strychalski, Elizabeth A.; Jarzynski, Christopher
  • Nature Physics, Vol. 14, Issue 8
  • DOI: 10.1038/s41567-018-0153-5

Surfaces of the perovskite manganites La 1 x Ca x MnO 3
journal, May 1999


XPS investigation of Mn valence in lanthanum manganite thin films under variation of oxygen content
journal, April 2006


Cationic and charge segregation in La2/3Ca1/3MnO3 thin films grown on (001) and (110) SrTiO3
journal, September 2008

  • Estradé, S.; Arbiol, J.; Peiró, F.
  • Applied Physics Letters, Vol. 93, Issue 11
  • DOI: 10.1063/1.2981574

Cation Size Mismatch and Charge Interactions Drive Dopant Segregation at the Surfaces of Manganite Perovskites
journal, May 2013

  • Lee, Wonyoung; Han, Jeong Woo; Chen, Yan
  • Journal of the American Chemical Society, Vol. 135, Issue 21
  • DOI: 10.1021/ja3125349

Evaluating bag-of-visual-words representations in scene classification
conference, January 2007

  • Yang, Jun; Jiang, Yu-Gang; Hauptmann, Alexander G.
  • Proceedings of the international workshop on Workshop on multimedia information retrieval - MIR '07
  • DOI: 10.1145/1290082.1290111

Statistical distance and Hilbert space
journal, January 1981


Knowledge Extraction from Atomically Resolved Images
journal, October 2017


Rigorous force field optimization principles based on statistical distance minimization
journal, October 2015

  • Vlcek, Lukas; Chialvo, Ariel A.
  • The Journal of Chemical Physics, Vol. 143, Issue 14
  • DOI: 10.1063/1.4932360

Learning phase transitions from dynamics
journal, August 2018


Surface reconstructions and modified surface states in L a 1 x C a x Mn O 3
journal, October 2018


Surface Control of Epitaxial Manganite Films via Oxygen Pressure
journal, February 2015

  • Tselev, Alexander; Vasudevan, Rama K.; Gianfrancesco, Anthony G.
  • ACS Nano, Vol. 9, Issue 4
  • DOI: 10.1021/acsnano.5b00743

Growth Mode Transition in Complex Oxide Heteroepitaxy: Atomically Resolved Studies
journal, April 2016

  • Tselev, Alexander; Vasudevan, Rama K.; Gianfrancesco, Anthony G.
  • Crystal Growth & Design, Vol. 16, Issue 5
  • DOI: 10.1021/acs.cgd.5b01826

Feature extraction via similarity search: application to atom finding and denoising in electron and scanning probe microscopy imaging
journal, March 2018

  • Somnath, Suhas; Smith, Christopher R.; Kalinin, Sergei V.
  • Advanced Structural and Chemical Imaging, Vol. 4, Issue 1
  • DOI: 10.1186/s40679-018-0052-y

Tunable Metallicity of the La 5 / 8 Ca 3 / 8 MnO 3 ( 001 ) Surface by an Oxygen Overlayer
journal, February 2009


Machine learning and data science in soft materials engineering
journal, December 2017


Statistical distance and the geometry of quantum states
journal, May 1994


Consistent Integration of Experimental and Ab Initio Data into Effective Physical Models
journal, October 2017

  • Vlcek, Lukas; Vasudevan, Rama K.; Jesse, Stephen
  • Journal of Chemical Theory and Computation, Vol. 13, Issue 11
  • DOI: 10.1021/acs.jctc.7b00114

Revised effective ionic radii and systematic studies of interatomic distances in halides and chalcogenides
journal, September 1976


Short-range order in two-dimensional binary alloys
journal, January 2003


Fast oxygen diffusion in A-site ordered perovskites
journal, January 2007


A -Site Ordering versus Electronic Inhomogeneity in Colossally Magnetoresistive Manganite Films
journal, September 2006


Sr Segregation in Perovskite Oxides: Why It Happens and How It Exists
journal, August 2018


Effects of annealing on structure and composition of LSMO thin films
journal, November 2015


Statistically optimal analysis of samples from multiple equilibrium states
journal, September 2008

  • Shirts, Michael R.; Chodera, John D.
  • The Journal of Chemical Physics, Vol. 129, Issue 12
  • DOI: 10.1063/1.2978177

Phase diagram studies in the quasi binary systems LaMnO 3 –SrMnO 3 and LaMnO 3 –CaMnO 3
journal, May 2000

  • Majewski, Peter; Epple, Lars; Rozumek, Michael
  • Journal of Materials Research, Vol. 15, Issue 5
  • DOI: 10.1557/JMR.2000.0164

New tool in the box
journal, February 2017


Machine learning phases of matter
journal, February 2017

  • Carrasquilla, Juan; Melko, Roger G.
  • Nature Physics, Vol. 13, Issue 5
  • DOI: 10.1038/nphys4035

Discovering phases, phase transitions, and crossovers through unsupervised machine learning: A critical examination
journal, June 2017


Chemically induced Jahn–Teller ordering on manganite surfaces
journal, July 2014

  • Gai, Zheng; Lin, Wenzhi; Burton, J. D.
  • Nature Communications, Vol. 5, Issue 1
  • DOI: 10.1038/ncomms5528

CMR manganites: physics, thin films and devices
journal, April 2003


The physics of manganites: Structure and transport
journal, August 2001


In situ study of activation and de-activation of LSM fuel cell cathodes – Electrochemistry and surface analysis of thin-film electrodes
journal, October 2012


Development of lanthanum strontium manganite perovskite cathode materials of solid oxide fuel cells: a review
journal, November 2008


Very large magnetoresistance and coherent switching in half-metallic manganite tunnel junctions
journal, June 2000


Works referencing / citing this record: