Search Menu
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information
Search Scholarly Publications

Title: Learning crystal field parameters using convolutional neural networks

Abstract

We present a deep machine learning algorithm to extract crystal field (CF) Stevens parameters from thermodynamic data of rare-earth magnetic materials. The algorithm employs a two-dimensional convolutional neural network (CNN) that is trained on magnetization, magnetic susceptibility and specific heat data that is calculated theoretically within the single-ion approximation and further processed using a standard wavelet transformation. We apply the method to crystal fields of cubic, hexagonal and tetragonal symmetry and for both integer and half-integer total angular momentum values J J of the ground state multiplet. We evaluate its performance on both theoretically generated synthetic and previously published experimental data on CeAgSb _2 2 , PrAgSb _2 2 and PrMg _2 2 Cu _9 9 , and find that it can reliably and accurately extract the CF parameters for all site symmetries and values of J J considered. This demonstrates that CNNs provide an unbiased approach to extracting CF parameters that avoids tedious multi-parameter fitting procedures.

Authors:
 [1];  [1];  [2];  [1]
+ Show Author Affiliations
  1. Ames Laboratory, Iowa State University
  2. University of Innsbruck, Harvard University
Publication Date:
Research Org.:
Ames Laboratory (AMES), Ames, IA (United States)
Sponsoring Org.:
USDOE; USDOE Office of Science (SC), Basic Energy Sciences (BES). Materials Sciences & Engineering Division; National Science Foundation (NSF)
OSTI Identifier:
1807978
Alternate Identifier(s):
OSTI ID: 1809235
Report Number(s):
IS-J-10,548
Journal ID: ISSN 2542-4653; 011
Grant/Contract Number:  
AC02-07CH11358; DMR-2002850
Resource Type:
Published Article
Journal Name:
SciPost Physics Proceedings
Additional Journal Information:
Journal Name: SciPost Physics Proceedings Journal Volume: 11 Journal Issue: 1; Journal ID: ISSN 2542-4653
Publisher:
Stichting SciPost
Country of Publication:
Netherlands
Language:
English
Subject:
71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSICS

Citation Formats

Berthusen, Noah F., Sizyuk, Yuriy, Scheurer, Mathias, and Orth, Peter. Learning crystal field parameters using convolutional neural networks. Netherlands: N. p., 2021. Web. doi:10.21468/SciPostPhys.11.1.011.
Copy to clipboard
Berthusen, Noah F., Sizyuk, Yuriy, Scheurer, Mathias, & Orth, Peter. Learning crystal field parameters using convolutional neural networks. Netherlands. https://doi.org/10.21468/SciPostPhys.11.1.011
Copy to clipboard
Berthusen, Noah F., Sizyuk, Yuriy, Scheurer, Mathias, and Orth, Peter. Wed . "Learning crystal field parameters using convolutional neural networks". Netherlands. https://doi.org/10.21468/SciPostPhys.11.1.011.
Copy to clipboard
@article{osti_1807978,
title = {Learning crystal field parameters using convolutional neural networks},
author = {Berthusen, Noah F. and Sizyuk, Yuriy and Scheurer, Mathias and Orth, Peter},
abstractNote = {We present a deep machine learning algorithm to extract crystal field (CF) Stevens parameters from thermodynamic data of rare-earth magnetic materials. The algorithm employs a two-dimensional convolutional neural network (CNN) that is trained on magnetization, magnetic susceptibility and specific heat data that is calculated theoretically within the single-ion approximation and further processed using a standard wavelet transformation. We apply the method to crystal fields of cubic, hexagonal and tetragonal symmetry and for both integer and half-integer total angular momentum values J J of the ground state multiplet. We evaluate its performance on both theoretically generated synthetic and previously published experimental data on CeAgSb _2 2 , PrAgSb _2 2 and PrMg _2 2 Cu _9 9 , and find that it can reliably and accurately extract the CF parameters for all site symmetries and values of J J considered. This demonstrates that CNNs provide an unbiased approach to extracting CF parameters that avoids tedious multi-parameter fitting procedures.},
doi = {10.21468/SciPostPhys.11.1.011},
journal = {SciPost Physics Proceedings},
number = 1,
volume = 11,
place = {Netherlands},
year = {Wed Jul 14 00:00:00 EDT 2021},
month = {Wed Jul 14 00:00:00 EDT 2021}
}
Copy to clipboard
Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record
https://doi.org/10.21468/SciPostPhys.11.1.011
Copyright Statement
Other availability
Search WorldCat Search WorldCat to find libraries that may hold this journal
Save / Share:
Export Metadata
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.

Works referenced in this record:

Matrix Elements and Operator Equivalents Connected with the Magnetic Properties of Rare Earth Ions
journal, March 1952

Field-induced ferrohastatic phase in cubic non-Kramers doublet systems
journal, November 2019

Topological Kondo Insulators
journal, March 2010

Crystal structure, magnetic ordering, and magnetic excitation in the 4 f -localized ferromagnet CeAgSb 2
journal, July 2003

Machine learning design of a trapped-ion quantum spin simulator
journal, January 2020

  • Teoh, Yi Hong; Drygala, Marina; Melko, Roger G.
  • Quantum Science and Technology, Vol. 5, Issue 2
  • DOI: 10.1088/2058-9565/ab657a

Interpretation of experimental results on Kondo systems with crystal field
journal, December 2013

Magnetization and electrical-transport investigation of the dense Kondo system Ce Ag Sb 2
journal, September 2005

Hastatic order in the heavy-fermion compound URu2Si2
journal, January 2013

  • Chandra, Premala; Coleman, Piers; Flint, Rebecca
  • Nature, Vol. 493, Issue 7434
  • DOI: 10.1038/nature11820

The use of `operator equivalents'
journal, December 1966

The raising of angular momentum degeneracy of f-Electron terms by cubic crystal fields
journal, October 1962

Preserved entropy and fragile magnetism
journal, July 2016

Crystal-field effects of paramagnetic Curie temperature
journal, June 1971

Magnetic and Thermal Properties of CeIrIn 5 and CeRhIn 5
journal, March 2001

  • Takeuchi, Tetsuya; Inoue, Tetsutaro; Sugiyama, Kiyohiro
  • Journal of the Physical Society of Japan, Vol. 70, Issue 3
  • DOI: 10.1143/JPSJ.70.877

Quadrupolar Kondo effect in uranium heavy-electron materials?
journal, September 1987

Evolution of quantum criticality in CeNi 9− x Cu x Ge 4
journal, May 2009

Treating crystal field parameters in lower than cubic symmetries
journal, January 1984

A Theory of Anisotropic Semiconductor of Heavy Fermions
journal, June 1996

  • Ikeda, Hiroaki; Miyake, Kazumasa
  • Journal of the Physical Society of Japan, Vol. 65, Issue 6
  • DOI: 10.1143/JPSJ.65.1769

Machine learning and the physical sciences
journal, December 2019

Systematic study of anisotropic transport and magnetic properties of RAgSb2 (R=Y, La–Nd, Sm, Gd–Tm)
journal, October 1999

Dynamical mean-field theory within the full-potential methods: Electronic structure of CeIrIn 5 , CeCoIn 5 , and CeRhIn 5
journal, May 2010

Machine learning & artificial intelligence in the quantum domain: a review of recent progress
journal, June 2018

Theory of Crystal-Field Effects in 3d-4f Intermetallic Compounds
book, January 2007

Crystal-Field Splitting in Kondo Systems
journal, January 1989

Anisotropy and metamagnetism in the RNi2Ge2 (R=Y, La–Nd, Sm–Lu) series
journal, October 1999

Forward and inverse design of kirigami via supervised autoencoder
journal, October 2020

Anisotropic, thermal, and magnetic properties of CeAgSb 2 : Explanation via a crystalline electric field scheme
journal, February 2003

Crystal fields and Kondo effect: Specific heat for Cerium compounds
journal, December 2014

Tables of Matrix Elements for the Operators , , ,
journal, November 1962

  • Buckmaster, H. A.
  • Canadian Journal of Physics, Vol. 40, Issue 11
  • DOI: 10.1139/p62-171

GTPack: A Mathematica Group Theory Package for Application in Solid-State Physics and Photonics
journal, August 2018

Artificial Neural Network Approach to the Analytic Continuation Problem
journal, February 2020

Unified molecular field theory for collinear and noncollinear Heisenberg antiferromagnets
journal, February 2015

Magnetic excitations in crystal-field split 4f systems
journal, January 1985

Exotic Kondo effects in metals: Magnetic ions in a crystalline electric field and tunnelling centres
journal, September 1998

A high-bias, low-variance introduction to Machine Learning for physicists
journal, May 2019

Projected regression method for solving Fredholm integral equations arising in the analytic continuation problem of quantum physics
journal, October 2017

  • Arsenault, Louis-François; Neuberg, Richard; Hannah, Lauren A.
  • Inverse Problems, Vol. 33, Issue 11
  • DOI: 10.1088/1361-6420/aa8d93

Gradient-based learning applied to document recognition
journal, January 1998

  • Lecun, Y.; Bottou, L.; Bengio, Y.
  • Proceedings of the IEEE, Vol. 86, Issue 11
  • DOI: 10.1109/5.726791

Termaufspaltung in Kristallen
journal, January 1929

Can Competition between the Crystal Field and the Kondo Effect Cause Non-Fermi-Liquid-Like Behavior?
journal, March 2006

Crystal-field states of Pr 3 + in the candidate quantum spin ice Pr 2 Sn 2 O 7
journal, September 2013

Lecture Notes on Electron Correlation and Magnetism
book, January 1999

Paramagnetic resonance
journal, January 1953

    Sort by:
    [ × clear filter / sort ]

    Similar Records in DOE PAGES and OSTI.GOV collections: