Machine learning–enabled identification of material phase transitions based on experimental data: Exploring collective dynamics in ferroelectric relaxors
Abstract
Exploration of phase transitions and construction of associated phase diagrams are of fundamental importance for condensed matter physics and materials science alike, and remain the focus of extensive research for both theoretical and experimental studies. For the latter, comprehensive studies involving scattering, thermodynamics, and modeling are typically required. We present a new approach to data mining multiple realizations of collective dynamics, measured through piezoelectric relaxation studies, to identify the onset of a structural phase transition in nanometer-scale volumes, that is, the probed volume of an atomic force microscope tip. Machine learning is used to analyze the multidimensional data sets describing relaxation to voltage and thermal stimuli, producing the temperature-bias phase diagram for a relaxor crystal without the need to measure (or know) the order parameter. The suitability of the approach to determine the phase diagram is shown with simulations based on a two-dimensional Ising model. Finally, these results indicate that machine learning approaches can be used to determine phase transitions in ferroelectrics, providing a general, statistically significant, and robust approach toward determining the presence of critical regimes and phase boundaries.
- Authors:
-
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States); Xi’an Jiaotong Univ., Shaanxi (China)
- Xi’an Jiaotong Univ., Shaanxi (China)
- Univ. of New South Wales, Sydney, NSW (Australia)
- Simon Fraser Univ., Burnaby, BC (Canada)
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
- Publication Date:
- Research Org.:
- Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC), Basic Energy Sciences (BES); Natural Science Foundation (NSF)
- OSTI Identifier:
- 1435239
- Grant/Contract Number:
- AC05-00OR22725; N00014-12-1-1045; N00014-16-1-6301; 203773; 51431007; 51321003
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Science Advances
- Additional Journal Information:
- Journal Volume: 4; Journal Issue: 3; Journal ID: ISSN 2375-2548
- Publisher:
- AAAS
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 36 MATERIALS SCIENCE; 75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND SUPERFLUIDITY
Citation Formats
Li, Linglong, Yang, Yaodong, Zhang, Dawei, Ye, Zuo-Guang, Jesse, Stephen, Kalinin, Sergei V., and Vasudevan, Rama K. Machine learning–enabled identification of material phase transitions based on experimental data: Exploring collective dynamics in ferroelectric relaxors. United States: N. p., 2018.
Web. doi:10.1126/sciadv.aap8672.
Li, Linglong, Yang, Yaodong, Zhang, Dawei, Ye, Zuo-Guang, Jesse, Stephen, Kalinin, Sergei V., & Vasudevan, Rama K. Machine learning–enabled identification of material phase transitions based on experimental data: Exploring collective dynamics in ferroelectric relaxors. United States. https://doi.org/10.1126/sciadv.aap8672
Li, Linglong, Yang, Yaodong, Zhang, Dawei, Ye, Zuo-Guang, Jesse, Stephen, Kalinin, Sergei V., and Vasudevan, Rama K. Fri .
"Machine learning–enabled identification of material phase transitions based on experimental data: Exploring collective dynamics in ferroelectric relaxors". United States. https://doi.org/10.1126/sciadv.aap8672. https://www.osti.gov/servlets/purl/1435239.
@article{osti_1435239,
title = {Machine learning–enabled identification of material phase transitions based on experimental data: Exploring collective dynamics in ferroelectric relaxors},
author = {Li, Linglong and Yang, Yaodong and Zhang, Dawei and Ye, Zuo-Guang and Jesse, Stephen and Kalinin, Sergei V. and Vasudevan, Rama K.},
abstractNote = {Exploration of phase transitions and construction of associated phase diagrams are of fundamental importance for condensed matter physics and materials science alike, and remain the focus of extensive research for both theoretical and experimental studies. For the latter, comprehensive studies involving scattering, thermodynamics, and modeling are typically required. We present a new approach to data mining multiple realizations of collective dynamics, measured through piezoelectric relaxation studies, to identify the onset of a structural phase transition in nanometer-scale volumes, that is, the probed volume of an atomic force microscope tip. Machine learning is used to analyze the multidimensional data sets describing relaxation to voltage and thermal stimuli, producing the temperature-bias phase diagram for a relaxor crystal without the need to measure (or know) the order parameter. The suitability of the approach to determine the phase diagram is shown with simulations based on a two-dimensional Ising model. Finally, these results indicate that machine learning approaches can be used to determine phase transitions in ferroelectrics, providing a general, statistically significant, and robust approach toward determining the presence of critical regimes and phase boundaries.},
doi = {10.1126/sciadv.aap8672},
journal = {Science Advances},
number = 3,
volume = 4,
place = {United States},
year = {Fri Mar 30 00:00:00 EDT 2018},
month = {Fri Mar 30 00:00:00 EDT 2018}
}
Web of Science
Works referenced in this record:
Finite-temperature properties of the relaxor from atomistic simulations
journal, June 2015
- Al-Barakaty, A.; Prosandeev, Sergey; Wang, Dawei
- Physical Review B, Vol. 91, Issue 21
Origin of morphotropic phase boundaries in ferroelectrics
journal, January 2008
- Ahart, Muhtar; Somayazulu, Maddury; Cohen, R. E.
- Nature, Vol. 451, Issue 7178
Recent progress in relaxor ferroelectrics with perovskite structure
journal, January 2006
- Bokov, A. A.; Ye, Z. -G.
- Journal of Materials Science, Vol. 41, Issue 1
Giant elastic tunability in strained BiFeO3 near an electrically induced phase transition
journal, November 2015
- Li, Q.; Cao, Y.; Yu, P.
- Nature Communications, Vol. 6, Issue 1
Principal component and spatial correlation analysis of spectroscopic-imaging data in scanning probe microscopy
journal, February 2009
- Jesse, Stephen; Kalinin, Sergei V.
- Nanotechnology, Vol. 20, Issue 8
Parameter Space Compression Underlies Emergent Theories and Predictive Models
journal, October 2013
- Machta, B. B.; Chachra, R.; Transtrum, M. K.
- Science, Vol. 342, Issue 6158
Dielectric and piezoelectric performance of PMN–PT single crystals with compositions around the MPB: influence of composition, poling field and crystal orientation
journal, December 2002
- Zhao, Xiangyong; Fang, Bijun; Cao, Hu
- Materials Science and Engineering: B, Vol. 96, Issue 3
Thermally activated avalanches: Jamming and the progression of needle domains
journal, March 2011
- Salje, E. K. H.; Ding, X.; Zhao, Z.
- Physical Review B, Vol. 83, Issue 10
Structural, dielectric and Raman scattering studies of (1− x )PbMg 1/3 Nb 2/3 O 3 – x PbTiO 3 single crystals (0 ≤ x ≤ 0.38)
journal, June 2006
- Słodczyk, A.; Kania, A.; Daniel, Ph.
- Phase Transitions, Vol. 79, Issue 6-7
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
Dynamics of a ferromagnetic domain wall: Avalanches, depinning transition, and the Barkhausen effect
journal, September 1998
- Zapperi, Stefano; Cizeau, Pierre; Durin, Gianfranco
- Physical Review B, Vol. 58, Issue 10
Assembly and phase transitions of colloidal crystals
journal, January 2016
- Li, Bo; Zhou, Di; Han, Yilong
- Nature Reviews Materials, Vol. 1, Issue 2
Nanoscale Mechanical Softening of Morphotropic BiFeO 3
journal, October 2014
- Heo, Yooun; Jang, Byong-Kweon; Kim, Seung Jin
- Advanced Materials, Vol. 26, Issue 45
Quantum Spin Hall Effect and Topological Phase Transition in HgTe Quantum Wells
journal, December 2006
- Bernevig, B. A.; Hughes, T. L.; Zhang, S.-C.
- Science, Vol. 314, Issue 5806, p. 1757-1761
Nanotwins and phases in high-strain Pb(Mg1/3Nb2/3)1−xTixO3 crystal
journal, April 2008
- Tu, C. -S.; Hsieh, C. -M.; Chien, R. R.
- Journal of Applied Physics, Vol. 103, Issue 7
Physical metallurgy of Ti–Ni-based shape memory alloys
journal, July 2005
- Otsuka, K.; Ren, X.
- Progress in Materials Science, Vol. 50, Issue 5
Strain-induced metal–insulator phase coexistence in perovskite manganites
journal, March 2004
- Ahn, K. H.; Lookman, T.; Bishop, A. R.
- Nature, Vol. 428, Issue 6981
Phase stability after an electric-field poling in crystals
journal, December 2004
- Tu, C. -S.; Chien, R. R.; Wang, F. -T.
- Physical Review B, Vol. 70, Issue 22
Electronic liquid-crystal phases of a doped Mott insulator
journal, June 1998
- Kivelson, S. A.; Fradkin, E.; Emery, V. J.
- Nature, Vol. 393, Issue 6685
Band Excitation in Scanning Probe Microscopy: Recognition and Functional Imaging
journal, April 2014
- Jesse, S.; Vasudevan, R. K.; Collins, L.
- Annual Review of Physical Chemistry, Vol. 65, Issue 1
Spectroscopic imaging in piezoresponse force microscopy: New opportunities for studying polarization dynamics in ferroelectrics and multiferroics
journal, July 2012
- Vasudevan, R. K.; Jesse, S.; Kim, Y.
- MRS Communications, Vol. 2, Issue 3
Subterahertz dielectric relaxation in lead-free Ba(Zr,Ti)O3 relaxor ferroelectrics
journal, April 2016
- Wang, D.; Bokov, A. A.; Ye, Z. -G.
- Nature Communications, Vol. 7, Issue 1
Acoustic Detection of Phase Transitions at the Nanoscale
journal, December 2015
- Vasudevan, Rama K.; Khassaf, Hamidreza; Cao, Ye
- Advanced Functional Materials, Vol. 26, Issue 4
The Higgs mode in disordered superconductors close to a quantum phase transition
journal, January 2015
- Sherman, Daniel; Pracht, Uwe S.; Gorshunov, Boris
- Nature Physics, Vol. 11, Issue 2
Detection of Phase Transition via Convolutional Neural Networks
journal, June 2017
- Tanaka, Akinori; Tomiya, Akio
- Journal of the Physical Society of Japan, Vol. 86, Issue 6
Imaging mechanism of piezoresponse force microscopy of ferroelectric surfaces
journal, March 2002
- Kalinin, Sergei V.; Bonnell, Dawn A.
- Physical Review B, Vol. 65, Issue 12
A structural approach to relaxation in glassy liquids
journal, February 2016
- Schoenholz, S. S.; Cubuk, E. D.; Sussman, D. M.
- Nature Physics, Vol. 12, Issue 5
High-temperature solution growth and characterization of the piezo-/ferroelectric (1−x)Pb(Mg1/3Nb2/3)O3–xPbTiO3 [PMNT] single crystals
journal, January 2000
- Dong, M.; Ye, Z. -G
- Journal of Crystal Growth, Vol. 209, Issue 1
Mechanical Switching of Nanoscale Multiferroic Phase Boundaries
journal, April 2015
- Li, Yong-Jun; Wang, Jian-Jun; Ye, Jian-Chao
- Advanced Functional Materials, Vol. 25, Issue 22
Learning phase transitions by confusion
journal, February 2017
- van Nieuwenburg, Evert P. L.; Liu, Ye-Hua; Huber, Sebastian D.
- Nature Physics, Vol. 13, Issue 5
Above-room-temperature ferroelectricity in a single-component molecular crystal
journal, February 2010
- Horiuchi, Sachio; Tokunaga, Yusuke; Giovannetti, Gianluca
- Nature, Vol. 463, Issue 7282, p. 789-792
Slush-like polar structures in single-crystal relaxors
journal, June 2017
- Takenaka, Hiroyuki; Grinberg, Ilya; Liu, Shi
- Nature, Vol. 546, Issue 7658
Experimental quantum Hamiltonian learning
journal, March 2017
- Wang, Jianwei; Paesani, Stefano; Santagati, Raffaele
- Nature Physics, Vol. 13, Issue 6
Large electric-field-induced strain in ferroelectric crystals by point-defect-mediated reversible domain switching
journal, January 2004
- Ren, Xiaobing
- Nature Materials, Vol. 3, Issue 2
Machine learning modeling of superconducting critical temperature
journal, June 2018
- Stanev, Valentin; Oses, Corey; Kusne, A. Gilad
- npj Computational Materials, Vol. 4, Issue 1
Detection of phase transition via convolutional neural network
text, January 2016
- Tanaka, Akinori; Tomiya, Akio
- arXiv
Learning phase transitions by confusion
text, January 2016
- van Nieuwenburg, Evert P. L.; Liu, Ye-Hua; Huber, Sebastian D.
- arXiv
Machine learning modeling of superconducting critical temperature
text, January 2017
- Stanev, Valentin; Oses, Corey; Kusne, A. Gilad
- arXiv
Quantum Spin Hall Effect and Topological Phase Transition in HgTe Quantum Wells
text, January 2006
- Bernevig, B. Andrei; Hughes, Taylor L.; Zhang, Shou-Cheng
- arXiv
Nanoscale Mechanical Softening of Morphotropic BiFeO 3
journal, October 2014
- Heo, Yooun; Jang, Byong-Kweon; Kim, Seung Jin
- Advanced Materials, Vol. 26, Issue 45
Origin of morphotropic phase boundaries in ferroelectrics
journal, January 2008
- Ahart, Muhtar; Somayazulu, Maddury; Cohen, R. E.
- Nature, Vol. 451, Issue 7178
Giant elastic tunability in strained BiFeO3 near an electrically induced phase transition
journal, November 2015
- Li, Q.; Cao, Y.; Yu, P.
- Nature Communications, Vol. 6, Issue 1
Large electric-field-induced strain in ferroelectric crystals by point-defect-mediated reversible domain switching
journal, January 2004
- Ren, Xiaobing
- Nature Materials, Vol. 3, Issue 2
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
Polarization response of crystals with structural and ferroelectric instabilities
journal, October 1993
- Balashova, E. V.; Tagantsev, A. K.
- Physical Review B, Vol. 48, Issue 14
Betaine arsenate as a system with two instabilities
journal, April 1995
- Balashova, E. V.; Lemanov, V. V.; Tagantsev, A. K.
- Physical Review B, Vol. 51, Issue 14
Band Excitation in Scanning Probe Microscopy: Recognition and Functional Imaging
journal, April 2014
- Jesse, S.; Vasudevan, R. K.; Collins, L.
- Annual Review of Physical Chemistry, Vol. 65, Issue 1
Parameter Space Compression Underlies Emergent Theories and Predictive Models
text, January 2013
- Machta, Benjamin B.; Chachra, Ricky; Transtrum, Mark K.
- arXiv
Detection of phase transition via convolutional neural network
text, January 2016
- Tanaka, Akinori; Tomiya, Akio
- arXiv
Dynamics of a ferromagnetic domain wall: avalanches, depinning transition and the Barkhausen effect
text, January 1998
- Zapperi, Stefano; Cizeau, Pierre; Durin, Gianfranco
- arXiv
Machine learning modeling of superconducting critical temperature
dataset, January 2022
- Stanev, Valentin; Oses, Corey; Kusne, A. Gilad
- Materials Data Facility
Works referencing / citing this record:
The Use of Deep Learning to Fast Evaluate Organic Photovoltaic Materials
journal, November 2018
- Sun, Wenbo; Li, Meng; Li, Yong
- Advanced Theory and Simulations, Vol. 2, Issue 1
Smart machine learning or discovering meaningful physical and chemical contributions through dimensional stacking
journal, August 2019
- Griffin, Lee A.; Gaponenko, Iaroslav; Zhang, Shujun
- npj Computational Materials, Vol. 5, Issue 1
An artificial intelligence atomic force microscope enabled by machine learning
journal, January 2018
- Huang, Boyuan; Li, Zhenghao; Li, Jiangyu
- Nanoscale, Vol. 10, Issue 45
Evaluation of the spectrum of a quantum system using machine learning based on incomplete information about the wavefunctions
journal, January 2020
- Burlak, Gennadiy
- Applied Physics Letters, Vol. 116, Issue 2
Machine learning for composite materials
journal, March 2019
- Chen, Chun-Teh; Gu, Grace X.
- MRS Communications, Vol. 9, Issue 02
Materials science in the artificial intelligence age: high-throughput library generation, machine learning, and a pathway from correlations to the underpinning physics
journal, July 2019
- Vasudevan, Rama K.; Choudhary, Kamal; Mehta, Apurva
- MRS Communications, Vol. 9, Issue 3
Artificial Intelligent Atomic Force Microscope Enabled by Machine Learning
text, January 2018
- Huang, Boyuan; Li, Zhenghao; Li, Jiangyu
- arXiv
Evaluation of the spectrum of a quantum system using machine learning based on incomplete information about the wavefunctions
text, January 2019
- Burlak, Gennadiy
- arXiv