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

Title: On-the-fly machine-learning for high-throughput experiments: search for rare-earth-free permanent magnets

Abstract

Advanced materials characterization techniques with ever-growing data acquisition speed and storage capabilities represent a challenge in modern materials science, and new procedures to quickly assess and analyze the data are needed. Machine learning approaches are effective in reducing the complexity of data and rapidly homing in on the underlying trend in multi-dimensional data. Here, we show that by employing an algorithm called the mean shift theory to a large amount of diffraction data in high-throughput experimentation, one can streamline the process of delineating the structural evolution across compositional variations mapped on combinatorial libraries with minimal computational cost. Data collected at a synchrotron beamline are analyzed on the fly, and by integrating experimental data with the inorganic crystal structure database (ICSD), we can substantially enhance the accuracy in classifying the structural phases across ternary phase spaces. We have used this approach to identify a novel magnetic phase with enhanced magnetic anisotropy which is a candidate for rare-earth free permanent magnet.

Authors:
; ; ; ; ; ; ; ; ; ;
Publication Date:
Research Org.:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility (OLCF)
Sponsoring Org.:
USDOE Office of Science (SC); USDOE Advanced Research Projects Agency - Energy (ARPA-E)
OSTI Identifier:
1211231
Resource Type:
Journal Article
Journal Name:
Scientific Reports
Additional Journal Information:
Journal Volume: 4; Journal ID: ISSN 2045-2322
Country of Publication:
United States
Language:
English

Citation Formats

Kusne, AG, Gao, TR, Mehta, A, Ke, LQ, Nguyen, MC, Ho, KM, Antropov, V, Wang, CZ, Kramer, MJ, Long, C, and Takeuchi, I. On-the-fly machine-learning for high-throughput experiments: search for rare-earth-free permanent magnets. United States: N. p., 2014. Web. doi:10.1038/srep06367.
Kusne, AG, Gao, TR, Mehta, A, Ke, LQ, Nguyen, MC, Ho, KM, Antropov, V, Wang, CZ, Kramer, MJ, Long, C, & Takeuchi, I. On-the-fly machine-learning for high-throughput experiments: search for rare-earth-free permanent magnets. United States. doi:10.1038/srep06367.
Kusne, AG, Gao, TR, Mehta, A, Ke, LQ, Nguyen, MC, Ho, KM, Antropov, V, Wang, CZ, Kramer, MJ, Long, C, and Takeuchi, I. Mon . "On-the-fly machine-learning for high-throughput experiments: search for rare-earth-free permanent magnets". United States. doi:10.1038/srep06367.
@article{osti_1211231,
title = {On-the-fly machine-learning for high-throughput experiments: search for rare-earth-free permanent magnets},
author = {Kusne, AG and Gao, TR and Mehta, A and Ke, LQ and Nguyen, MC and Ho, KM and Antropov, V and Wang, CZ and Kramer, MJ and Long, C and Takeuchi, I},
abstractNote = {Advanced materials characterization techniques with ever-growing data acquisition speed and storage capabilities represent a challenge in modern materials science, and new procedures to quickly assess and analyze the data are needed. Machine learning approaches are effective in reducing the complexity of data and rapidly homing in on the underlying trend in multi-dimensional data. Here, we show that by employing an algorithm called the mean shift theory to a large amount of diffraction data in high-throughput experimentation, one can streamline the process of delineating the structural evolution across compositional variations mapped on combinatorial libraries with minimal computational cost. Data collected at a synchrotron beamline are analyzed on the fly, and by integrating experimental data with the inorganic crystal structure database (ICSD), we can substantially enhance the accuracy in classifying the structural phases across ternary phase spaces. We have used this approach to identify a novel magnetic phase with enhanced magnetic anisotropy which is a candidate for rare-earth free permanent magnet.},
doi = {10.1038/srep06367},
journal = {Scientific Reports},
issn = {2045-2322},
number = ,
volume = 4,
place = {United States},
year = {2014},
month = {9}
}

Works referenced in this record:

Generalized Gradient Approximation Made Simple
journal, October 1996

  • Perdew, John P.; Burke, Kieron; Ernzerhof, Matthias
  • Physical Review Letters, Vol. 77, Issue 18, p. 3865-3868
  • DOI: 10.1103/PhysRevLett.77.3865

Finding Density Functionals with Machine Learning
journal, June 2012


Projector augmented-wave method
journal, December 1994


High-throughput powder diffraction. II. Applications of clustering methods and multivariate data analysis
journal, March 2004

  • Barr, Gordon; Dong, Wei; Gilmore, Christopher J.
  • Journal of Applied Crystallography, Vol. 37, Issue 2
  • DOI: 10.1107/S0021889804000391

Combinatorial search of structural transitions: Systematic investigation of morphotropic phase boundaries in chemically substituted BiFeO 3
journal, September 2012

  • Kan, Daisuke; Long, Christian J.; Steinmetz, Christian
  • Journal of Materials Research, Vol. 27, Issue 21
  • DOI: 10.1557/jmr.2012.314

Effects of alloying and strain on the magnetic properties of Fe 16 N 2
journal, July 2013


Understanding and visualizing microstructure and microstructure variance as a stochastic process
journal, September 2011


Rapid structural mapping of ternary metallic alloy systems using the combinatorial approach and cluster analysis
journal, July 2007

  • Long, C. J.; Hattrick-Simpers, J.; Murakami, M.
  • Review of Scientific Instruments, Vol. 78, Issue 7
  • DOI: 10.1063/1.2755487

From ultrasoft pseudopotentials to the projector augmented-wave method
journal, January 1999


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


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

Machine learning of molecular electronic properties in chemical compound space
journal, September 2013


Neural network approach to quantum-chemistry data: Accurate prediction of density functional theory energies
journal, August 2009

  • Balabin, Roman M.; Lomakina, Ekaterina I.
  • The Journal of Chemical Physics, Vol. 131, Issue 7
  • DOI: 10.1063/1.3206326

Giant magnetostriction in annealed Co1−xFex thin-films
journal, September 2011

  • Hunter, Dwight; Osborn, Will; Wang, Ke
  • Nature Communications, Vol. 2, Issue 1
  • DOI: 10.1038/ncomms1529

Prospects for Non-Rare Earth Permanent Magnets for Traction Motors and Generators
journal, June 2012


Rapid identification of structural phases in combinatorial thin-film libraries using x-ray diffraction and non-negative matrix factorization
journal, October 2009

  • Long, C. J.; Bunker, D.; Li, X.
  • Review of Scientific Instruments, Vol. 80, Issue 10
  • DOI: 10.1063/1.3216809

Comparing efficiencies of genetic and minima hopping algorithms for crystal structure prediction
journal, January 2010

  • Ji, Min; Wang, Cai-Zhuang; Ho, Kai-Ming
  • Physical Chemistry Chemical Physics, Vol. 12, Issue 37
  • DOI: 10.1039/c004096g

Application and further development of advanced image processing algorithms for automated analysis of serial section image data
journal, December 2008

  • Simmons, J. P.; Chuang, P.; Comer, M.
  • Modelling and Simulation in Materials Science and Engineering, Vol. 17, Issue 2
  • DOI: 10.1088/0965-0393/17/2/025002

Self-Consistent Equations Including Exchange and Correlation Effects
journal, November 1965


Combinatorial exploration of rare-earth-free permanent magnets: Magnetic and microstructural properties of Fe-Co-W thin films
journal, January 2013

  • Gao, T. R.; Wu, Y. Q.; Fackler, S.
  • Applied Physics Letters, Vol. 102, Issue 2
  • DOI: 10.1063/1.4775581

Giant Magnetic Anisotropy in Tetragonal FeCo Alloys
journal, July 2004


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


Accelerating materials property predictions using machine learning
journal, September 2013

  • Pilania, Ghanshyam; Wang, Chenchen; Jiang, Xun
  • Scientific Reports, Vol. 3, Issue 1
  • DOI: 10.1038/srep02810

Near equiatomic FeCo alloys: Constitution, mechanical and magnetic properties
journal, September 2005


Magnetic and magneto‐optical properties of cobalt‐platinum alloys with perpendicular magnetic anisotropy
journal, November 1992

  • Weller, D.; Brändle, H.; Gorman, G.
  • Applied Physics Letters, Vol. 61, Issue 22
  • DOI: 10.1063/1.108074

Bayesian methods for image segmentation
journal, July 2011


Data mining for materials: Computational experiments with A B compounds
journal, March 2012


Identification of novel compositions of ferromagnetic shape-memory alloys using composition spreads
journal, February 2003

  • Takeuchi, I.; Famodu, O. O.; Read, J. C.
  • Nature Materials, Vol. 2, Issue 3
  • DOI: 10.1038/nmat829

Special points for Brillouin-zone integrations
journal, June 1976

  • Monkhorst, Hendrik J.; Pack, James D.
  • Physical Review B, Vol. 13, Issue 12, p. 5188-5192
  • DOI: 10.1103/PhysRevB.13.5188

The Computational Materials Repository
journal, November 2012

  • Landis, David D.; Hummelshoj, Jens S.; Nestorov, Svetlozar
  • Computing in Science & Engineering, Vol. 14, Issue 6
  • DOI: 10.1109/MCSE.2012.16

Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set
journal, October 1996


On the use of 2-D moment invariants for the automated classification of particle shapes
journal, February 2008


Misfit-energy-increasing dislocations in vapor-deposited CoFe/NiFe multilayers
journal, April 2004


Perpendicular Magnetocrystalline Anisotropy in Tetragonally Distorted Fe-Co Alloys
journal, January 2006


Molecular Geometry Optimization with a Genetic Algorithm
journal, July 1995


Assessment and Validation of Machine Learning Methods for Predicting Molecular Atomization Energies
journal, July 2013

  • Hansen, Katja; Montavon, Grégoire; Biegler, Franziska
  • Journal of Chemical Theory and Computation, Vol. 9, Issue 8
  • DOI: 10.1021/ct400195d

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


Mean shift: a robust approach toward feature space analysis
journal, May 2002

  • Comaniciu, D.; Meer, P.
  • IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, Issue 5
  • DOI: 10.1109/34.1000236

Neural network potential-energy surfaces in chemistry: a tool for large-scale simulations
journal, January 2011

  • Behler, Jörg
  • Physical Chemistry Chemical Physics, Vol. 13, Issue 40
  • DOI: 10.1039/c1cp21668f

A reliable methodology for high throughput identification of a mixture of crystallographic phases from powder X-ray diffraction data
journal, January 2008

  • Baumes, Laurent Allan; Moliner, Manuel; Nicoloyannis, Nicolas
  • CrystEngComm, Vol. 10, Issue 10
  • DOI: 10.1039/b812395k

The estimation of the gradient of a density function, with applications in pattern recognition
journal, January 1975


Genetic-Algorithm Discovery of a Direct-Gap and Optically Allowed Superstructure from Indirect-Gap Si and Ge Semiconductors
journal, January 2012


Ab initio calculations of cohesive energies of Fe -based glass-forming alloys
journal, October 2004


Finding Nature’s Missing Ternary Oxide Compounds Using Machine Learning and Density Functional Theory
journal, June 2010

  • Hautier, Geoffroy; Fischer, Christopher C.; Jain, Anubhav
  • Chemistry of Materials, Vol. 22, Issue 12
  • DOI: 10.1021/cm100795d

Microstructure informatics using higher-order statistics and efficient data-mining protocols
journal, April 2011


Predicting crystal structure by merging data mining with quantum mechanics
journal, July 2006

  • Fischer, Christopher C.; Tibbetts, Kevin J.; Morgan, Dane
  • Nature Materials, Vol. 5, Issue 8
  • DOI: 10.1038/nmat1691

Combinatorial screening for new materials in unconstrained composition space with machine learning
journal, March 2014