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

Title: Machine learning properties of binary wurtzite superlattices

Abstract

The burgeoning paradigm of high-throughput computations and materials informatics brings new opportunities in terms of targeted materials design and discovery. The discovery process can be significantly accelerated and streamlined if one can learn effectively from available knowledge and past data to predict materials properties efficiently. Indeed, a very active area in materials science research is to develop machine learning based methods that can deliver automated and cross-validated predictive models using either already available materials data or new data generated in a targeted manner. In the present paper, we show that fast and accurate predictions of a wide range of properties of binary wurtzite superlattices, formed by a diverse set of chemistries, can be made by employing state-of-the-art statistical learning methods trained on quantum mechanical computations in combination with a judiciously chosen numerical representation to encode materials’ similarity. These surrogate learning models then allow for efficient screening of vast chemical spaces by providing instant predictions of the targeted properties. Moreover, the models can be systematically improved in an adaptive manner, incorporate properties computed at different levels of fidelities and are naturally amenable to inverse materials design strategies. Finally, while the learning approach to make predictions for a wide range of propertiesmore » (including structural, elastic and electronic properties) is demonstrated here for a specific example set containing more than 1200 binary wurtzite superlattices, the adopted framework is equally applicable to other classes of materials as well.« less

Authors:
ORCiD logo [1];  [1]
  1. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Publication Date:
Research Org.:
Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
1430015
Report Number(s):
LA-UR-17-30057
Journal ID: ISSN 0022-2461; TRN: US1802746
Grant/Contract Number:  
AC52-06NA25396
Resource Type:
Journal Article: Accepted Manuscript
Journal Name:
Journal of Materials Science
Additional Journal Information:
Journal Volume: 53; Journal Issue: 9; Journal ID: ISSN 0022-2461
Publisher:
Springer
Country of Publication:
United States
Language:
English
Subject:
36 MATERIALS SCIENCE; materials informatics, wurtzite superlattices, binary octets, statistical learning

Citation Formats

Pilania, G., and Liu, X. -Y. Machine learning properties of binary wurtzite superlattices. United States: N. p., 2018. Web. doi:10.1007/s10853-018-1987-z.
Pilania, G., & Liu, X. -Y. Machine learning properties of binary wurtzite superlattices. United States. doi:10.1007/s10853-018-1987-z.
Pilania, G., and Liu, X. -Y. Fri . "Machine learning properties of binary wurtzite superlattices". United States. doi:10.1007/s10853-018-1987-z. https://www.osti.gov/servlets/purl/1430015.
@article{osti_1430015,
title = {Machine learning properties of binary wurtzite superlattices},
author = {Pilania, G. and Liu, X. -Y.},
abstractNote = {The burgeoning paradigm of high-throughput computations and materials informatics brings new opportunities in terms of targeted materials design and discovery. The discovery process can be significantly accelerated and streamlined if one can learn effectively from available knowledge and past data to predict materials properties efficiently. Indeed, a very active area in materials science research is to develop machine learning based methods that can deliver automated and cross-validated predictive models using either already available materials data or new data generated in a targeted manner. In the present paper, we show that fast and accurate predictions of a wide range of properties of binary wurtzite superlattices, formed by a diverse set of chemistries, can be made by employing state-of-the-art statistical learning methods trained on quantum mechanical computations in combination with a judiciously chosen numerical representation to encode materials’ similarity. These surrogate learning models then allow for efficient screening of vast chemical spaces by providing instant predictions of the targeted properties. Moreover, the models can be systematically improved in an adaptive manner, incorporate properties computed at different levels of fidelities and are naturally amenable to inverse materials design strategies. Finally, while the learning approach to make predictions for a wide range of properties (including structural, elastic and electronic properties) is demonstrated here for a specific example set containing more than 1200 binary wurtzite superlattices, the adopted framework is equally applicable to other classes of materials as well.},
doi = {10.1007/s10853-018-1987-z},
journal = {Journal of Materials Science},
issn = {0022-2461},
number = 9,
volume = 53,
place = {United States},
year = {2018},
month = {1}
}

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

Citation Metrics:
Cited by: 3 works
Citation information provided by
Web of Science

Figures / Tables:

Fig. 1 Fig. 1: A schematic representation of the overall ML scheme adopted in this work. Staring from a set 32 ABi bulk compounds, multilayer superlattices are formed in a combinatorial fashion. Subsequently, a simple numerical representation or fingerprint is constructed by counting different possible ABi–ABj pairs appearing within a given superlattice.more » Finally, validated ML models built on these fingerprints are used to predict various properties.« less

Save / Share:

Works referenced in this record:

Perspective: Materials informatics and big data: Realization of the “fourth paradigm” of science in materials science
journal, April 2016

  • Agrawal, Ankit; Choudhary, Alok
  • APL Materials, Vol. 4, Issue 5
  • DOI: 10.1063/1.4946894

From Organized High-Throughput Data to Phenomenological Theory using Machine Learning: The Example of Dielectric Breakdown
journal, February 2016


Descriptors of Oxygen-Evolution Activity for Oxides: A Statistical Evaluation
journal, December 2015

  • Hong, Wesley T.; Welsch, Roy E.; Shao-Horn, Yang
  • The Journal of Physical Chemistry C, Vol. 120, Issue 1
  • DOI: 10.1021/acs.jpcc.5b10071

Projector augmented-wave method
journal, December 1994


New opportunities for materials informatics: Resources and data mining techniques for uncovering hidden relationships
journal, April 2016

  • Jain, Anubhav; Hautier, Geoffroy; Ong, Shyue Ping
  • Journal of Materials Research, Vol. 31, Issue 8
  • DOI: 10.1557/jmr.2016.80

A genomic approach to the stability, elastic, and electronic properties of the MAX phases: A genomic approach to stability and properties of the MAX phases
journal, June 2014

  • Aryal, Sitaram; Sakidja, Ridwan; Barsoum, Michel W.
  • physica status solidi (b), Vol. 251, Issue 8
  • DOI: 10.1002/pssb.201451226

Representing potential energy surfaces by high-dimensional neural network potentials
journal, April 2014


Computational predictions of energy materials using density functional theory
journal, January 2016


An introduction to kernel-based learning algorithms
journal, March 2001

  • Muller, K. -R.; Mika, S.; Ratsch, G.
  • IEEE Transactions on Neural Networks, Vol. 12, Issue 2
  • DOI: 10.1109/72.914517

Predicting density functional theory total energies and enthalpies of formation of metal-nonmetal compounds by linear regression
journal, February 2016


Accelerated materials property predictions and design using motif-based fingerprints
journal, July 2015

  • Huan, Tran Doan; Mannodi-Kanakkithodi, Arun; Ramprasad, Rampi
  • Physical Review B, Vol. 92, Issue 1
  • DOI: 10.1103/PhysRevB.92.014106

Rapid and Accurate Machine Learning Recognition of High Performing Metal Organic Frameworks for CO 2 Capture
journal, August 2014

  • Fernandez, Michael; Boyd, Peter G.; Daff, Thomas D.
  • The Journal of Physical Chemistry Letters, Vol. 5, Issue 17
  • DOI: 10.1021/jz501331m

Computational discovery of stable M 2 A X phases
journal, August 2016


Understanding kernel ridge regression: Common behaviors from simple functions to density functionals
journal, May 2015

  • Vu, Kevin; Snyder, John C.; Li, Li
  • International Journal of Quantum Chemistry, Vol. 115, Issue 16
  • DOI: 10.1002/qua.24939

Materials informatics: An emerging technology for materials development
journal, June 2009

  • LeSar, Richard
  • Statistical Analysis and Data Mining, Vol. 1, Issue 6
  • DOI: 10.1002/sam.10034

On representing chemical environments
journal, May 2013


Commutativity of the GaAs/AlAs(100) band offset
journal, December 1988


Prediction of Low-Thermal-Conductivity Compounds with First-Principles Anharmonic Lattice-Dynamics Calculations and Bayesian Optimization
journal, November 2015


Informatics-aided bandgap engineering for solar materials
journal, February 2014


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

Accelerated search for BaTiO 3 -based piezoelectrics with vertical morphotropic phase boundary using Bayesian learning
journal, November 2016

  • Xue, Dezhen; Balachandran, Prasanna V.; Yuan, Ruihao
  • Proceedings of the National Academy of Sciences, Vol. 113, Issue 47
  • DOI: 10.1073/pnas.1607412113

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


Molecular Dynamics with On-the-Fly Machine Learning of Quantum-Mechanical Forces
journal, March 2015


Machine learning in materials informatics: recent applications and prospects
journal, December 2017

  • Ramprasad, Rampi; Batra, Rohit; Pilania, Ghanshyam
  • npj Computational Materials, Vol. 3, Issue 1
  • DOI: 10.1038/s41524-017-0056-5

Erratum: “Hybrid functionals based on a screened Coulomb potential” [J. Chem. Phys. 118, 8207 (2003)]
journal, June 2006

  • Heyd, Jochen; Scuseria, Gustavo E.; Ernzerhof, Matthias
  • The Journal of Chemical Physics, Vol. 124, Issue 21
  • DOI: 10.1063/1.2204597

Adaptive machine learning framework to accelerate ab initio molecular dynamics
journal, December 2014

  • Botu, Venkatesh; Ramprasad, Rampi
  • International Journal of Quantum Chemistry, Vol. 115, Issue 16
  • DOI: 10.1002/qua.24836

Representations in neural network based empirical potentials
journal, July 2017

  • Cubuk, Ekin D.; Malone, Brad D.; Onat, Berk
  • The Journal of Chemical Physics, Vol. 147, Issue 2
  • DOI: 10.1063/1.4990503

Machine learning for quantum mechanics in a nutshell
journal, July 2015

  • Rupp, Matthias
  • International Journal of Quantum Chemistry, Vol. 115, Issue 16
  • DOI: 10.1002/qua.24954

Machine Learning Assisted Predictions of Intrinsic Dielectric Breakdown Strength of ABX 3 Perovskites
journal, June 2016

  • Kim, Chiho; Pilania, Ghanshyam; Ramprasad, Rampi
  • The Journal of Physical Chemistry C, Vol. 120, Issue 27
  • DOI: 10.1021/acs.jpcc.6b05068

Density-Functional Theory of the Energy Gap
journal, November 1983


Nobel Lecture: Electronic structure of matter—wave functions and density functionals
journal, October 1999


Predicting defect behavior in B2 intermetallics by merging ab initio modeling and machine learning
journal, December 2016


Stability and bandgaps of layered perovskites for one- and two-photon water splitting
journal, October 2013


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

Accelerated search for materials with targeted properties by adaptive design
journal, April 2016

  • Xue, Dezhen; Balachandran, Prasanna V.; Hogden, John
  • Nature Communications, Vol. 7, Issue 1
  • DOI: 10.1038/ncomms11241

How Chemical Composition Alone Can Predict Vibrational Free Energies and Entropies of Solids
journal, July 2017


The electrostatic coupling of longitudinal optical phonon and plasmon in wurtzite InN thin films
journal, January 2010

  • Chang, Y. -M.; Liou, S. C.; Chen, C. H.
  • Applied Physics Letters, Vol. 96, Issue 4
  • DOI: 10.1063/1.3299021

A Statistical Learning Framework for Materials Science: Application to Elastic Moduli of k-nary Inorganic Polycrystalline Compounds
journal, October 2016

  • de Jong, Maarten; Chen, Wei; Notestine, Randy
  • Scientific Reports, Vol. 6, Issue 1
  • DOI: 10.1038/srep34256

Machine learning bandgaps of double perovskites
journal, January 2016

  • Pilania, G.; Mannodi-Kanakkithodi, A.; Uberuaga, B. P.
  • Scientific Reports, Vol. 6, Issue 1
  • DOI: 10.1038/srep19375

High-Throughput Computational Screening of Perovskites for Thermochemical Water Splitting Applications
journal, July 2016


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

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


Localization and Delocalization Errors in Density Functional Theory and Implications for Band-Gap Prediction
journal, April 2008


Multi-fidelity machine learning models for accurate bandgap predictions of solids
journal, March 2017


Finding New Perovskite Halides via Machine Learning
journal, April 2016

  • Pilania, Ghanshyam; Balachandran, Prasanna V.; Kim, Chiho
  • Frontiers in Materials, Vol. 3
  • DOI: 10.3389/fmats.2016.00019

Strain mapping in free-standing heterostructured wurtzite InAs/InP nanowires
journal, December 2006


Structure classification and melting temperature prediction in octet AB solids via machine learning
journal, June 2015


Learning scheme to predict atomic forces and accelerate materials simulations
journal, September 2015


Accurate and simple analytic representation of the electron-gas correlation energy
journal, June 1992


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


First-principles identification of novel double perovskites for water-splitting applications
journal, April 2017


Machine Learning Strategy for Accelerated Design of Polymer Dielectrics
journal, February 2016

  • Mannodi-Kanakkithodi, Arun; Pilania, Ghanshyam; Huan, Tran Doan
  • Scientific Reports, Vol. 6, Issue 1
  • DOI: 10.1038/srep20952

Accelerated computational discovery of high-performance materials for organic photovoltaics by means of cheminformatics
journal, January 2011

  • Olivares-Amaya, Roberto; Amador-Bedolla, Carlos; Hachmann, Johannes
  • Energy & Environmental Science, Vol. 4, Issue 12
  • DOI: 10.1039/c1ee02056k

Feature engineering of machine-learning chemisorption models for catalyst design
journal, February 2017


Machine Learning Energies of 2 Million Elpasolite ( A B C 2 D 6 ) Crystals
journal, September 2016


Machine Learning Force Fields: Construction, Validation, and Outlook
journal, December 2016


Computational 2D Materials Database: Electronic Structure of Transition-Metal Dichalcogenides and Oxides
journal, June 2015

  • Rasmussen, Filip A.; Thygesen, Kristian S.
  • The Journal of Physical Chemistry C, Vol. 119, Issue 23
  • DOI: 10.1021/acs.jpcc.5b02950

Crystal Structure Change of GaAs and InAs Whiskers from Zinc-Blende to Wurtzite Type
journal, July 1992

  • Koguchi, Masanari; Kakibayashi, Hiroshi; Yazawa, Masamitsu
  • Japanese Journal of Applied Physics, Vol. 31, Issue Part 1, No. 7
  • DOI: 10.1143/JJAP.31.2061

Communication: Understanding molecular representations in machine learning: The role of uniqueness and target similarity
journal, October 2016

  • Huang, Bing; von Lilienfeld, O. Anatole
  • The Journal of Chemical Physics, Vol. 145, Issue 16
  • DOI: 10.1063/1.4964627

Nanobelts, Nanocombs, and Nanowindmills of Wurtzite ZnS
journal, February 2003


Using Machine Learning To Identify Factors That Govern Amorphization of Irradiated Pyrochlores
journal, November 2016


Materials informatics
journal, October 2005


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


    Figures/Tables have been extracted from DOE-funded journal article accepted manuscripts.