Machine learning predictions for local electronic properties of disordered correlated electron systems

Liu, Yi-Hsuan; Zhang, Sheng; Zhang, Puhan; Lee, Ting-Kuo; Chern, Gia-Wei

doi:10.1103/physrevb.106.035131

Title: Machine learning predictions for local electronic properties of disordered correlated electron systems

Journal Article · 18 July 2022 · Physical Review. B

DOI: https://doi.org/10.1103/physrevb.106.035131 · OSTI ID:1979792

^[1];

^[2]; Zhang, Puhan ^[2];

^[3]; Chern, Gia-Wei ^[2]

National Tsing Hua Univ., Hsinchu (Taiwan); Academia Sinica, Taipei (Taiwan); OSTI
Univ. of Virginia, Charlottesville, VA (United States)
National Tsing Hua Univ., Hsinchu (Taiwan); Academia Sinica, Taipei (Taiwan); National Sun Yat-sen Univ., Kaohsiun (Taiwan)

We present a scalable machine learning (ML) model to predict local electronic properties such as on-site electron number and double occupation for disordered correlated electron systems. Our approach is based on the locality principle, or the nearsightedness nature, of many-electron systems, which means local electronic properties depend mainly on the immediate environment. A ML model is developed to encode this complex dependence of local quantities on the neighborhood. We demonstrate our approach using the square-lattice Anderson-Hubbard model, which is a paradigmatic system for studying the interplay between Mott transition and Anderson localization. We develop a lattice descriptor based on the group-theoretical method to represent the on-site random potentials within a finite region. The resultant feature variables are used as input to a multilayer fully connected neural network, which is trained from data sets of variational Monte Carlo (VMC) simulations on small systems. We show that the ML predictions agree reasonably well with the VMC data. Our work underscores the promising potential of ML methods for multiscale modeling of correlated electron systems.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Univ. of Virginia, Charlottesville, VA (United States)

Sponsoring Organization:: Taiwan Ministry of Science and Technology (MOST); USDOE Office of Science (SC), Basic Energy Sciences (BES)

Grant/Contract Number:: SC0020330

OSTI ID:: 1979792

Journal Information:: Physical Review. B, Journal Name: Physical Review. B Journal Issue: 3 Vol. 106; ISSN 2469-9950

Publisher:: American Physical Society (APS)Copyright Statement

Country of Publication:: United States

Language:: English

References (79)

Machine Learning Interatomic Potentials as Emerging Tools for Materials Science Deringer, Volker L.; Caro, Miguel A.; Csányi, Gábor Advanced Materials, Vol. 31, Issue 46 https://doi.org/10.1002/adma.201902765	journal	September 2019
Crystal structure representations for machine learning models of formation energies Faber, Felix; Lindmaa, Alexander; von Lilienfeld, O. Anatole International Journal of Quantum Chemistry, Vol. 115, Issue 16 https://doi.org/10.1002/qua.24917	journal	April 2015
Approximation by superpositions of a sigmoidal function Cybenko, G. Mathematics of Control, Signals, and Systems, Vol. 2, Issue 4 https://doi.org/10.1007/BF02551274	journal	December 1989
Studies of polaron motion Holstein, T. Annals of Physics, Vol. 8, Issue 3 https://doi.org/10.1016/0003-4916(59)90002-8	journal	November 1959
Multilayer feedforward networks are universal approximators Hornik, Kurt; Stinchcombe, Maxwell; White, Halbert Neural Networks, Vol. 2, Issue 5 https://doi.org/10.1016/0893-6080(89)90020-8	journal	January 1989
DScribe: Library of descriptors for machine learning in materials science Himanen, Lauri; Jäger, Marc O. J.; Morooka, Eiaki V. Computer Physics Communications, Vol. 247 https://doi.org/10.1016/j.cpc.2019.106949	journal	February 2020
Deep learning in neural networks: An overview Schmidhuber, Jürgen Neural Networks, Vol. 61 https://doi.org/10.1016/j.neunet.2014.09.003	journal	January 2015
Quantum Monte Carlo Approaches for Correlated Systems Becca, Federico; Sorella, Sandro https://doi.org/10.1017/9781316417041	book	November 2017
Ab Initio Molecular Dynamics Marx, Dominik; Hutter, Jurg https://doi.org/10.1017/CBO9780511609633	book	January 2009
Machine Learning Force Field Parameters from Ab Initio Data Li, Ying; Li, Hui; Pickard, Frank C. Journal of Chemical Theory and Computation, Vol. 13, Issue 9 https://doi.org/10.1021/acs.jctc.7b00521	journal	August 2017
Machine Learning Force Fields: Construction, Validation, and Outlook Botu, V.; Batra, R.; Chapman, J. The Journal of Physical Chemistry C, Vol. 121, Issue 1 https://doi.org/10.1021/acs.jpcc.6b10908	journal	December 2016
Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space Hansen, Katja; Biegler, Franziska; Ramakrishnan, Raghunathan The Journal of Physical Chemistry Letters, Vol. 6, Issue 12 https://doi.org/10.1021/acs.jpclett.5b00831	journal	June 2015
Multitask Learning Caruana, Rich Machine Learning, Vol. 28, Issue 1, p. 41-75 https://doi.org/10.1023/A:1007379606734	journal	January 1997
Deep learning LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey Nature, Vol. 521, Issue 7553 https://doi.org/10.1038/nature14539	journal	May 2015
Machine learning at the energy and intensity frontiers of particle physics Radovic, Alexander; Williams, Mike; Rousseau, David Nature, Vol. 560, Issue 7716 https://doi.org/10.1038/s41586-018-0361-2	journal	August 2018
ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost Smith, J. S.; Isayev, O.; Roitberg, A. E. Chemical Science, Vol. 8, Issue 4 https://doi.org/10.1039/C6SC05720A	journal	January 2017
Atom-centered symmetry functions for constructing high-dimensional neural network potentials Behler, Jörg The Journal of Chemical Physics, Vol. 134, Issue 7 https://doi.org/10.1063/1.3553717	journal	February 2011
Perspective: Machine learning potentials for atomistic simulations Behler, Jörg The Journal of Chemical Physics, Vol. 145, Issue 17 https://doi.org/10.1063/1.4966192	journal	November 2016
Improving the accuracy of Møller-Plesset perturbation theory with neural networks McGibbon, Robert T.; Taube, Andrew G.; Donchev, Alexander G. The Journal of Chemical Physics, Vol. 147, Issue 16 https://doi.org/10.1063/1.4986081	journal	October 2017
Gradient-based stochastic estimation of the density matrix Wang, Zhentao; Chern, Gia-Wei; Batista, Cristian D. The Journal of Chemical Physics, Vol. 148, Issue 9 https://doi.org/10.1063/1.5017741	journal	March 2018
Machine learning for interatomic potential models Mueller, Tim; Hernandez, Alberto; Wang, Chuhong The Journal of Chemical Physics, Vol. 152, Issue 5 https://doi.org/10.1063/1.5126336	journal	February 2020
Machine learning meets quantum physics Das Sarma, Sankar; Deng, Dong-Ling; Duan, Lu-Ming Physics Today, Vol. 72, Issue 3 https://doi.org/10.1063/PT.3.4164	journal	March 2019
Nearsightedness of electronic matter Prodan, E.; Kohn, W. Proceedings of the National Academy of Sciences, Vol. 102, Issue 33 https://doi.org/10.1073/pnas.0505436102	journal	August 2005
Anomalous phase separation in a correlated electron system: Machine-learning–enabled large-scale kinetic Monte Carlo simulations Zhang, Sheng; Zhang, Puhan; Chern, Gia-Wei Proceedings of the National Academy of Sciences, Vol. 119, Issue 18 https://doi.org/10.1073/pnas.2119957119	journal	April 2022
Machine learning for condensed matter physics Bedolla, Edwin; Padierna, Luis Carlos; Castañeda-Priego, Ramón Journal of Physics: Condensed Matter, Vol. 33, Issue 5 https://doi.org/10.1088/1361-648X/abb895	journal	November 2020
Correlation of Electrons in a Narrow s Band Gutzwiller, Martin C. Physical Review, Vol. 137, Issue 6A https://doi.org/10.1103/PhysRev.137.A1726	journal	March 1965
Two-dimensional disordered Mott metal-insulator transition Suárez-Villagrán, M. Y.; Mitsakos, N.; Lee, Tsung-Han Physical Review B, Vol. 101, Issue 23 https://doi.org/10.1103/PhysRevB.101.235112	journal	June 2020
Bond-orientational order in liquids and glasses Steinhardt, Paul J.; Nelson, David R.; Ronchetti, Marco Physical Review B, Vol. 28, Issue 2 https://doi.org/10.1103/PhysRevB.28.784	journal	July 1983
Effects of weak random disorder in the one-dimensional Hubbard model Sandvik, A. W.; Scalapino, D. J. Physical Review B, Vol. 47, Issue 16 https://doi.org/10.1103/PhysRevB.47.10090	journal	April 1993
Interplay between disorder and electron interactions in ad=3 site-disordered Anderson-Hubbard model: A numerical mean-field study Tusch, Michael A.; Logan, David E. Physical Review B, Vol. 48, Issue 20 https://doi.org/10.1103/PhysRevB.48.14843	journal	November 1993
Quantum Monte Carlo study of the one-dimensional Hubbard model with random hopping and random potentials Sandvik, A. W.; Scalapino, D. J.; Henelius, P. Physical Review B, Vol. 50, Issue 15 https://doi.org/10.1103/PhysRevB.50.10474	journal	October 1994
Anderson-Hubbard model in infinite dimensions Ulmke, M.; Janiš, V.; Vollhardt, D. Physical Review B, Vol. 51, Issue 16 https://doi.org/10.1103/PhysRevB.51.10411	journal	April 1995
Magnetic correlations in the two-dimensional Anderson-Hubbard model Ulmke, M.; Scalettar, R. T. Physical Review B, Vol. 55, Issue 7 https://doi.org/10.1103/PhysRevB.55.4149	journal	February 1997
Collapse of the charge gap in random Mott insulators Otsuka, Y.; Morita, Y.; Hatsugai, Y. Physical Review B, Vol. 58, Issue 23 https://doi.org/10.1103/PhysRevB.58.15314	journal	December 1998
Delocalizing effect of the Hubbard repulsion for electrons on a two-dimensional disordered lattice Srinivasan, Bhargavi; Benenti, Giuliano; Shepelyansky, Dima L. Physical Review B, Vol. 67, Issue 20 https://doi.org/10.1103/PhysRevB.67.205112	journal	May 2003
Wave function optimization in the variational Monte Carlo method Sorella, Sandro Physical Review B, Vol. 71, Issue 24 https://doi.org/10.1103/PhysRevB.71.241103	journal	June 2005
Local moments and magnetic order in the two-dimensional Anderson-Mott transition Pezzoli, Maria Elisabetta; Becca, Federico; Fabrizio, Michele Physical Review B, Vol. 79, Issue 3 https://doi.org/10.1103/PhysRevB.79.033111	journal	January 2009
Real-space variational Gutzwiller wave functions for the Anderson-Hubbard model Farhoodfar, A.; Chen, X.; Gooding, R. J. Physical Review B, Vol. 80, Issue 4 https://doi.org/10.1103/PhysRevB.80.045108	journal	July 2009
Ground-state properties of the disordered Hubbard model in two dimensions Pezzoli, Maria Elisabetta; Becca, Federico Physical Review B, Vol. 81, Issue 7 https://doi.org/10.1103/PhysRevB.81.075106	journal	February 2010
Anderson-Hubbard model with box disorder: Statistical dynamical mean-field theory investigation Semmler, D.; Byczuk, K.; Hofstetter, W. Physical Review B, Vol. 84, Issue 11 https://doi.org/10.1103/PhysRevB.84.115113	journal	September 2011
Variational Monte Carlo study of Anderson localization in the Hubbard model Farhoodfar, A.; Gooding, R. J.; Atkinson, W. A. Physical Review B, Vol. 84, Issue 20 https://doi.org/10.1103/PhysRevB.84.205125	journal	November 2011
On representing chemical environments Bartók, Albert P.; Kondor, Risi; Csányi, Gábor Physical Review B, Vol. 87, Issue 18 https://doi.org/10.1103/PhysRevB.87.184115	journal	May 2013
Two-dimensional Holstein-Hubbard model: Critical temperature, Ising universality, and bipolaron liquid Weber, Manuel; Hohenadler, Martin Physical Review B, Vol. 98, Issue 8 https://doi.org/10.1103/PhysRevB.98.085405	journal	August 2018
Atomic cluster expansion for accurate and transferable interatomic potentials Drautz, Ralf Physical Review B, Vol. 99, Issue 1 https://doi.org/10.1103/PhysRevB.99.014104	journal	January 2019
Machine learning electron correlation in a disordered medium Ma, Jianhua; Zhang, Puhan; Tan, Yaohua Physical Review B, Vol. 99, Issue 8 https://doi.org/10.1103/PhysRevB.99.085118	journal	February 2019
Machine learning for molecular dynamics with strongly correlated electrons Suwa, Hidemaro; Smith, Justin S.; Lubbers, Nicholas Physical Review B, Vol. 99, Issue 16 https://doi.org/10.1103/PhysRevB.99.161107	journal	April 2019
Effect of Correlation on the Ferromagnetism of Transition Metals Gutzwiller, Martin C. Physical Review Letters, Vol. 10, Issue 5 https://doi.org/10.1103/PhysRevLett.10.159	journal	March 1963
Disorder-Induced Stabilization of the Pseudogap in Strongly Correlated Systems Chiesa, Simone; Chakraborty, Prabuddha B.; Pickett, Warren E. Physical Review Letters, Vol. 101, Issue 8 https://doi.org/10.1103/PhysRevLett.101.086401	journal	August 2008
Critical Behavior at the Mott-Anderson Transition: A Typical-Medium Theory Perspective Aguiar, M. C. O.; Dobrosavljević, V.; Abrahams, E. Physical Review Letters, Vol. 102, Issue 15 https://doi.org/10.1103/PhysRevLett.102.156402	journal	April 2009
Electronic Griffiths Phase of the d = 2 Mott Transition Andrade, E. C.; Miranda, E.; Dobrosavljević, V. Physical Review Letters, Vol. 102, Issue 20 https://doi.org/10.1103/PhysRevLett.102.206403	journal	May 2009
Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the Electrons Bartók, Albert P.; Payne, Mike C.; Kondor, Risi Physical Review Letters, Vol. 104, Issue 13 https://doi.org/10.1103/PhysRevLett.104.136403	journal	April 2010
Quantum Ripples in Strongly Correlated Metals Andrade, E. C.; Miranda, E.; Dobrosavljević, V. Physical Review Letters, Vol. 104, Issue 23 https://doi.org/10.1103/PhysRevLett.104.236401	journal	June 2010
Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning Rupp, Matthias; Tkatchenko, Alexandre; Müller, Klaus-Robert Physical Review Letters, Vol. 108, Issue 5 https://doi.org/10.1103/PhysRevLett.108.058301	journal	January 2012
Emergence of a Novel Pseudogap Metallic State in a Disordered 2D Mott Insulator Lahoud, Elias; Meetei, O. Nganba; Chaska, K. B. Physical Review Letters, Vol. 112, Issue 20 https://doi.org/10.1103/PhysRevLett.112.206402	journal	May 2014
Molecular Dynamics with On-the-Fly Machine Learning of Quantum-Mechanical Forces Li, Zhenwei; Kermode, James R.; De Vita, Alessandro Physical Review Letters, Vol. 114, Issue 9 https://doi.org/10.1103/PhysRevLett.114.096405	journal	March 2015
Big Data of Materials Science: Critical Role of the Descriptor Ghiringhelli, Luca M.; Vybiral, Jan; Levchenko, Sergey V. Physical Review Letters, Vol. 114, Issue 10 https://doi.org/10.1103/PhysRevLett.114.105503	journal	March 2015
Non-Fermi Liquid Behavior and Continuously Tunable Resistivity Exponents in the Anderson-Hubbard Model at Finite Temperature Patel, Niravkumar D.; Mukherjee, Anamitra; Kaushal, Nitin Physical Review Letters, Vol. 119, Issue 8 https://doi.org/10.1103/PhysRevLett.119.086601	journal	August 2017
Deep Potential Molecular Dynamics: A Scalable Model with the Accuracy of Quantum Mechanics Zhang, Linfeng; Han, Jiequn; Wang, Han Physical Review Letters, Vol. 120, Issue 14 https://doi.org/10.1103/PhysRevLett.120.143001	journal	April 2018
Local Spectroscopies Reveal Percolative Metal in Disordered Mott Insulators Szabo, Joseph C.; Lee, Kyungmin; Madhavan, Vidya Physical Review Letters, Vol. 124, Issue 13 https://doi.org/10.1103/PhysRevLett.124.137402	journal	April 2020
Arrested Phase Separation in Double-Exchange Models: Large-Scale Simulation Enabled by Machine Learning Zhang, Puhan; Chern, Gia-Wei Physical Review Letters, Vol. 127, Issue 14 https://doi.org/10.1103/PhysRevLett.127.146401	journal	September 2021
Polaronic anharmonicity in the Holstein-Hubbard model Zhong, J.; Schüttler, H. -B. Physical Review Letters, Vol. 69, Issue 10 https://doi.org/10.1103/PhysRevLett.69.1600	journal	September 1992
Density Functional and Density Matrix Method Scaling Linearly with the Number of Atoms Kohn, W. Physical Review Letters, Vol. 76, Issue 17 https://doi.org/10.1103/PhysRevLett.76.3168	journal	April 1996
Mean Field Theory of the Mott-Anderson Transition Dobrosavljević, V.; Kotliar, G. Physical Review Letters, Vol. 78, Issue 20 https://doi.org/10.1103/PhysRevLett.78.3943	journal	May 1997
Disorder and Interaction in 2D: Exact Diagonalization Study of the Anderson-Hubbard-Mott Model Kotlyar, R.; Das Sarma, S. Physical Review Letters, Vol. 86, Issue 11 https://doi.org/10.1103/PhysRevLett.86.2388	journal	March 2001
Glassy Behavior of Electrons Near Metal-Insulator Transitions Dobrosavljević, V.; Tanasković, D.; Pastor, A. A. Physical Review Letters, Vol. 90, Issue 1 https://doi.org/10.1103/PhysRevLett.90.016402	journal	January 2003
Disorder Screening in Strongly Correlated Systems Tanasković, D.; Dobrosavljević, V.; Abrahams, E. Physical Review Letters, Vol. 91, Issue 6 https://doi.org/10.1103/PhysRevLett.91.066603	journal	August 2003
Inhomogeneous Metallic Phase in a Disordered Mott Insulator in Two Dimensions Heidarian, Dariush; Trivedi, Nandini Physical Review Letters, Vol. 93, Issue 12 https://doi.org/10.1103/PhysRevLett.93.126401	journal	September 2004
Variational Description of Mott Insulators Capello, Manuela; Becca, Federico; Fabrizio, Michele Physical Review Letters, Vol. 94, Issue 2 https://doi.org/10.1103/PhysRevLett.94.026406	journal	January 2005
Mott-Hubbard Transition versus Anderson Localization in Correlated Electron Systems with Disorder Byczuk, Krzysztof; Hofstetter, Walter; Vollhardt, Dieter Physical Review Letters, Vol. 94, Issue 5 https://doi.org/10.1103/PhysRevLett.94.056404	journal	February 2005
Role of Strong Electronic Correlations in the Metal-To-Insulator Transition in DisorderedLiAlyTi2−yO4 Fazileh, F.; Gooding, R. J.; Atkinson, W. A. Physical Review Letters, Vol. 96, Issue 4 https://doi.org/10.1103/PhysRevLett.96.046410	journal	February 2006
Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces Behler, Jörg; Parrinello, Michele Physical Review Letters, Vol. 98, Issue 14 https://doi.org/10.1103/PhysRevLett.98.146401	journal	April 2007
Dynamical mean-field theory of strongly correlated fermion systems and the limit of infinite dimensions Georges, Antoine; Kotliar, Gabriel; Krauth, Werner Reviews of Modern Physics, Vol. 68, Issue 1 https://doi.org/10.1103/RevModPhys.68.13	journal	January 1996
The kernel polynomial method Weiße, Alexander; Wellein, Gerhard; Alvermann, Andreas Reviews of Modern Physics, Vol. 78, Issue 1 https://doi.org/10.1103/RevModPhys.78.275	journal	March 2006
Machine learning and the physical sciences Carleo, Giuseppe; Cirac, Ignacio; Cranmer, Kyle Reviews of Modern Physics, Vol. 91, Issue 4 https://doi.org/10.1103/RevModPhys.91.045002	journal	December 2019
Universal approximation bounds for superpositions of a sigmoidal function Barron, A. R. IEEE Transactions on Information Theory, Vol. 39, Issue 3 https://doi.org/10.1109/18.256500	journal	May 1993
Moment Tensor Potentials: A Class of Systematically Improvable Interatomic Potentials Shapeev, Alexander V. Multiscale Modeling & Simulation, Vol. 14, Issue 3 https://doi.org/10.1137/15M1054183	journal	January 2016
Single-Particle Excitations under Coexisting Electron Correlation and Disorder: A Numerical Study of the Anderson–Hubbard Model Shinaoka, Hiroshi; Imada, Masatoshi Journal of the Physical Society of Japan, Vol. 78, Issue 9 https://doi.org/10.1143/JPSJ.78.094708	journal	September 2009
Machine Learning for Molecular Simulation Noé, Frank; Tkatchenko, Alexandre; Müller, Klaus-Robert Annual Review of Physical Chemistry, Vol. 71, Issue 1 https://doi.org/10.1146/annurev-physchem-042018-052331	journal	April 2020
Typical medium theory of Anderson localization: A local order parameter approach to strong-disorder effects Dobrosavljević, V.; Pastor, A. A.; Nikolić, B. K. Europhysics Letters (EPL), Vol. 62, Issue 1 https://doi.org/10.1209/epl/i2003-00364-5	journal	April 2003

Similar Records

Two-dimensional Anderson-Hubbard model in the DMFT + {Sigma} approximation

Journal Article · 2010 · Journal of Experimental and Theoretical Physics · OSTI ID:21443406

Kuleeva, N A; Nekrasov, I A

Mean-field phase diagram of cold lattice bosons in disordered potentials

Journal Article · 2007 · Physical Review. A · OSTI ID:21011139

Buonsante, P; Penna, V; Vezzani, A; +1 more

Disorder and pseudogap in strongly correlated systems: Phase diagram in the DMFT + {Sigma} approach

Journal Article · 2013 · Journal of Experimental and Theoretical Physics · OSTI ID:22122849

Related Subjects

36 MATERIALS SCIENCE
Anderson localization
Hubbard model
Physics
deep learning
electron-correlation calculations
electronic phase separation
electronic structure
localization
machine learning
multiscale modeling
quantum Monte Carlo
strongly correlated systems

Title: Machine learning predictions for local electronic properties of disordered correlated electron systems

Citation Formats

References (79)

Similar Records

Related Subjects