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

Title: Materials prediction via classification learning

Abstract

In the paradigm of materials informatics for accelerated materials discovery, the choice of feature set (i.e. attributes that capture aspects of structure, chemistry and/or bonding) is critical. Ideally, the feature sets should provide a simple physical basis for extracting major structural and chemical trends and furthermore, enable rapid predictions of new material chemistries. Orbital radii calculated from model pseudopotential fits to spectroscopic data are potential candidates to satisfy these conditions. Although these radii (and their linear combinations) have been utilized in the past, their functional forms are largely justified with heuristic arguments. Here we show that machine learning methods naturally uncover the functional forms that mimic most frequently used features in the literature, thereby providing a mathematical basis for feature set construction without a priori assumptions. We apply these principles to study two broad materials classes: (i) wide band gap AB compounds and (ii) rare earth-main group RM intermetallics. The AB compounds serve as a prototypical example to demonstrate our approach, whereas the RM intermetallics show how these concepts can be used to rapidly design new ductile materials. In conclusion, our predictive models indicate that ScCo, ScIr, and YCd should be ductile, whereas each was previously proposed to be brittle.

Authors:
 [1];  [2];  [3];  [1]
  1. Los Alamos National Lab. (LANL), Los Alamos, NM (United States). Theoretical Division
  2. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
  3. Northwestern Univ., Evanston, IL (United States)
Publication Date:
Research Org.:
Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Sponsoring Org.:
USDOE; National Science Foundation (NSF)
OSTI Identifier:
1259293
Grant/Contract Number:  
DMR 1454688; 20140013DR
Resource Type:
Accepted Manuscript
Journal Name:
Scientific Reports
Additional Journal Information:
Journal Volume: 5; Journal ID: ISSN 2045-2322
Publisher:
Nature Publishing Group
Country of Publication:
United States
Language:
English
Subject:
36 MATERIALS SCIENCE; electronic properties and materials; mechanical properties

Citation Formats

Balachandran, Prasanna V., Theiler, James, Rondinelli, James M., and Lookman, Turab. Materials prediction via classification learning. United States: N. p., 2015. Web. doi:10.1038/srep13285.
Balachandran, Prasanna V., Theiler, James, Rondinelli, James M., & Lookman, Turab. Materials prediction via classification learning. United States. doi:10.1038/srep13285.
Balachandran, Prasanna V., Theiler, James, Rondinelli, James M., and Lookman, Turab. Tue . "Materials prediction via classification learning". United States. doi:10.1038/srep13285. https://www.osti.gov/servlets/purl/1259293.
@article{osti_1259293,
title = {Materials prediction via classification learning},
author = {Balachandran, Prasanna V. and Theiler, James and Rondinelli, James M. and Lookman, Turab},
abstractNote = {In the paradigm of materials informatics for accelerated materials discovery, the choice of feature set (i.e. attributes that capture aspects of structure, chemistry and/or bonding) is critical. Ideally, the feature sets should provide a simple physical basis for extracting major structural and chemical trends and furthermore, enable rapid predictions of new material chemistries. Orbital radii calculated from model pseudopotential fits to spectroscopic data are potential candidates to satisfy these conditions. Although these radii (and their linear combinations) have been utilized in the past, their functional forms are largely justified with heuristic arguments. Here we show that machine learning methods naturally uncover the functional forms that mimic most frequently used features in the literature, thereby providing a mathematical basis for feature set construction without a priori assumptions. We apply these principles to study two broad materials classes: (i) wide band gap AB compounds and (ii) rare earth-main group RM intermetallics. The AB compounds serve as a prototypical example to demonstrate our approach, whereas the RM intermetallics show how these concepts can be used to rapidly design new ductile materials. In conclusion, our predictive models indicate that ScCo, ScIr, and YCd should be ductile, whereas each was previously proposed to be brittle.},
doi = {10.1038/srep13285},
journal = {Scientific Reports},
number = ,
volume = 5,
place = {United States},
year = {2015},
month = {8}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 19 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

New Model Potential for Pseudopotential Calculations
journal, July 1971

  • Simons, Gary
  • The Journal of Chemical Physics, Vol. 55, Issue 2
  • DOI: 10.1063/1.1676142

Pauli-Force Model Potential for Solids
journal, March 1973


Structural index for elemental solids
journal, November 1972

  • Bloch, Aaron N.; Simons, Gary
  • Journal of the American Chemical Society, Vol. 94, Issue 24
  • DOI: 10.1021/ja00779a071

Quantum-Defect Electronegativity Scale for Nontransition Elements
journal, October 1974


Atomic Radii in Crystals
journal, November 1964

  • Slater, J. C.
  • The Journal of Chemical Physics, Vol. 41, Issue 10
  • DOI: 10.1063/1.1725697

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


An interpretation of structural sorting diagrams for AB type compounds using molecular orbital ideas
journal, January 1982


On the crystal chemistry of normal valence compounds
journal, December 1959


The Nature of the Chemical Bond. iv. the Energy of Single Bonds and the Relative Electronegativity of Atoms
journal, September 1932

  • Pauling, Linus
  • Journal of the American Chemical Society, Vol. 54, Issue 9
  • DOI: 10.1021/ja01348a011

Spectroscopic Analysis of Cohesive Energies and Heats of Formation of Tetrahedrally Coordinated Semiconductors
journal, September 1970


Structural pseudoion form factors
journal, June 1977


Structural Stability of Suboctet Simple Binary Compounds
journal, May 1977


Structure and bonding in narrow gap semiconductors
journal, January 1983

  • Littlewood, Peter B.
  • Critical Reviews in Solid State and Materials Sciences, Vol. 11, Issue 3
  • DOI: 10.1080/01611598308244064

Doping Rules and Doping Prototypes in A2BO4 Spinel Oxides
journal, October 2011

  • Paudel, Tula R.; Zakutayev, Andriy; Lany, Stephan
  • Advanced Functional Materials, Vol. 21, Issue 23
  • DOI: 10.1002/adfm.201101469

Unified structural classification of AB2 molecules and solids from valence electron orbital radii
journal, January 1987

  • Andreoni, Wanda; Galli, Giulia
  • Physics and Chemistry of Minerals, Vol. 14, Issue 5
  • DOI: 10.1007/BF00628814

Quantum diagrams and the prediction of new materials
journal, June 1993


A map for phase-change materials
journal, November 2008

  • Lencer, Dominic; Salinga, Martin; Grabowski, Blazej
  • Nature Materials, Vol. 7, Issue 12
  • DOI: 10.1038/nmat2330

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


Big Data of Materials Science: Critical Role of the Descriptor
journal, March 2015


Orbital Radii of Atoms and Ions
journal, June 1965

  • Waber, J. T.; Cromer, Don T.
  • The Journal of Chemical Physics, Vol. 42, Issue 12
  • DOI: 10.1063/1.1695904

Influence of the electronic structure on the ductile behavior of B2 CsCl-type AB intermetallics
journal, November 2009


What is principal component analysis?
journal, March 2008


A family of ductile intermetallic compounds
journal, August 2003

  • Gschneidner, Karl; Russell, Alan; Pecharsky, Alexandra
  • Nature Materials, Vol. 2, Issue 9
  • DOI: 10.1038/nmat958

Stability maps to predict anomalous ductility in B2 materials
journal, March 2013


Extreme Poisson's ratios and their electronic origin in B2 CsCl-type AB intermetallic compounds
journal, April 2012


Commentary: The Materials Project: A materials genome approach to accelerating materials innovation
journal, July 2013

  • Jain, Anubhav; Ong, Shyue Ping; Hautier, Geoffroy
  • APL Materials, Vol. 1, Issue 1
  • DOI: 10.1063/1.4812323

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


New developments in the Inorganic Crystal Structure Database (ICSD): accessibility in support of materials research and design
journal, May 2002

  • Belsky, Alec; Hellenbrandt, Mariette; Karen, Vicky Lynn
  • Acta Crystallographica Section B Structural Science, Vol. 58, Issue 3
  • DOI: 10.1107/S0108768102006948

Identifying the ‘inorganic gene’ for high-temperature piezoelectric perovskites through statistical learning
journal, February 2011

  • Balachandran, Prasanna V.; Broderick, Scott R.; Rajan, Krishna
  • Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 467, Issue 2132
  • DOI: 10.1098/rspa.2010.0543

Crystal-Chemistry Guidelines for Noncentrosymmetric A 2 BO 4 Ruddlesden−Popper Oxides
journal, December 2013

  • Balachandran, Prasanna V.; Puggioni, Danilo; Rondinelli, James M.
  • Inorganic Chemistry, Vol. 53, Issue 1
  • DOI: 10.1021/ic402283c

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


Dissolving the Periodic Table in Cubic Zirconia: Data Mining to Discover Chemical Trends
journal, March 2014

  • Meredig, Bryce; Wolverton, C.
  • Chemistry of Materials, Vol. 26, Issue 6
  • DOI: 10.1021/cm403727z

Materials Cartography: Representing and Mining Materials Space Using Structural and Electronic Fingerprints
journal, January 2015

  • Isayev, Olexandr; Fourches, Denis; Muratov, Eugene N.
  • Chemistry of Materials, Vol. 27, Issue 3
  • DOI: 10.1021/cm503507h

What are decision trees?
journal, September 2008

  • Kingsford, Carl; Salzberg, Steven L.
  • Nature Biotechnology, Vol. 26, Issue 9
  • DOI: 10.1038/nbt0908-1011

What is a support vector machine?
journal, December 2006


The WEKA data mining software: an update
journal, November 2009

  • Hall, Mark; Frank, Eibe; Holmes, Geoffrey
  • ACM SIGKDD Explorations Newsletter, Vol. 11, Issue 1
  • DOI: 10.1145/1656274.1656278

The Lack of A Priori Distinctions Between Learning Algorithms
journal, October 1996


Restoring the Density-Gradient Expansion for Exchange in Solids and Surfaces
journal, April 2008


Soft self-consistent pseudopotentials in a generalized eigenvalue formalism
journal, April 1990


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

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

Projector augmented-wave method
journal, December 1994


Accurate projected augmented wave (PAW) datasets for rare-earth elements (RE=La–Lu)
journal, December 2014


Electron-energy-loss spectra and the structural stability of nickel oxide: An LSDA+U study
journal, January 1998

  • Dudarev, S. L.; Botton, G. A.; Savrasov, S. Y.
  • Physical Review B, Vol. 57, Issue 3, p. 1505-1509
  • DOI: 10.1103/PhysRevB.57.1505

Efficient pseudopotentials for plane-wave calculations
journal, January 1991


FINDSYM : program for identifying the space-group symmetry of a crystal
journal, January 2005


VESTA : a three-dimensional visualization system for electronic and structural analysis
journal, May 2008


    Works referencing / citing this record:

    Mapping and classifying molecules from a high-throughput structural database
    journal, February 2017