DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Machine learning substitutional defect formation energies in ABO3 perovskites

Abstract

Perovskite oxides are a promising material platform for use in a wide range of technological applications including electronics, sensors, fuel cells, and catalysis. This is owing to the extraordinary tunability of their physical and chemical properties via defect engineering. The feasibility and the stability of a defect, such as a substitutional dopant, in the host lattice is usually obtained via experiments and/or through detailed quantum mechanical calculations. Both of these conventional routes are expensive and time consuming. An alternative is a data-driven machine learning (ML)-based approach. In this work, we have applied ML techniques to identify the factors that influence defect formation energy, which is an important measure of the stability of the defects, in perovskite oxides. Using 13 elemental properties as features and random forest regression, we demonstrate a systematic approach to down-selecting from the larger set of features to those that are important, establishing a framework for accurate predictions of the defect formation energy. We quantitatively show that the most important factors that control the dopant stability are the dopant ionic size, heat of formation, effective tolerance factor, and oxidation state. Our work reveals previously unknown correlations, chemical trends, and the interplay between stability and underlying chemistries. Hence,more » these results showcase the efficacy of ML tools in identifying and quantifying different feature-dependencies and provide a promising route toward dopant selection in the perovskites. Herein, we have developed a framework that itself is general and can be potentially applied to other material classes.« less

Authors:
ORCiD logo [1]; ORCiD logo [2]; ORCiD logo [2]; ORCiD logo [3]
  1. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States); Univ. of Tennessee, Knoxville, TN (United States)
  2. Howard Univ., Washington, DC (United States)
  3. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Publication Date:
Research Org.:
Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA); USDOE Laboratory Directed Research and Development (LDRD) Program; National Science Foundation (NSF)
OSTI Identifier:
1756805
Alternate Identifier(s):
OSTI ID: 1638546
Report Number(s):
LA-UR-20-24008
Journal ID: ISSN 0021-8979; TRN: US2206008
Grant/Contract Number:  
89233218CNA000001; 20190043DR; TG-DMR160051; PHY180014; ACI-1548562; ECCS-1831954; AC52-06NA25396
Resource Type:
Accepted Manuscript
Journal Name:
Journal of Applied Physics
Additional Journal Information:
Journal Volume: 128; Journal Issue: 3; Journal ID: ISSN 0021-8979
Publisher:
American Institute of Physics (AIP)
Country of Publication:
United States
Language:
English
Subject:
36 MATERIALS SCIENCE

Citation Formats

Sharma, Vinit, Kumar, Pankaj, Dev, Pratibha, and Pilania, Ghanshyam. Machine learning substitutional defect formation energies in ABO3 perovskites. United States: N. p., 2020. Web. doi:10.1063/5.0015538.
Sharma, Vinit, Kumar, Pankaj, Dev, Pratibha, & Pilania, Ghanshyam. Machine learning substitutional defect formation energies in ABO3 perovskites. United States. https://doi.org/10.1063/5.0015538
Sharma, Vinit, Kumar, Pankaj, Dev, Pratibha, and Pilania, Ghanshyam. Wed . "Machine learning substitutional defect formation energies in ABO3 perovskites". United States. https://doi.org/10.1063/5.0015538. https://www.osti.gov/servlets/purl/1756805.
@article{osti_1756805,
title = {Machine learning substitutional defect formation energies in ABO3 perovskites},
author = {Sharma, Vinit and Kumar, Pankaj and Dev, Pratibha and Pilania, Ghanshyam},
abstractNote = {Perovskite oxides are a promising material platform for use in a wide range of technological applications including electronics, sensors, fuel cells, and catalysis. This is owing to the extraordinary tunability of their physical and chemical properties via defect engineering. The feasibility and the stability of a defect, such as a substitutional dopant, in the host lattice is usually obtained via experiments and/or through detailed quantum mechanical calculations. Both of these conventional routes are expensive and time consuming. An alternative is a data-driven machine learning (ML)-based approach. In this work, we have applied ML techniques to identify the factors that influence defect formation energy, which is an important measure of the stability of the defects, in perovskite oxides. Using 13 elemental properties as features and random forest regression, we demonstrate a systematic approach to down-selecting from the larger set of features to those that are important, establishing a framework for accurate predictions of the defect formation energy. We quantitatively show that the most important factors that control the dopant stability are the dopant ionic size, heat of formation, effective tolerance factor, and oxidation state. Our work reveals previously unknown correlations, chemical trends, and the interplay between stability and underlying chemistries. Hence, these results showcase the efficacy of ML tools in identifying and quantifying different feature-dependencies and provide a promising route toward dopant selection in the perovskites. Herein, we have developed a framework that itself is general and can be potentially applied to other material classes.},
doi = {10.1063/5.0015538},
journal = {Journal of Applied Physics},
number = 3,
volume = 128,
place = {United States},
year = {Wed Jul 15 00:00:00 EDT 2020},
month = {Wed Jul 15 00:00:00 EDT 2020}
}

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

Citation Metrics:
Cited by: 15 works
Citation information provided by
Web of Science

Save / Share:

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

Effects of moisture on (La, A)MnO 3 (A = Ca, Sr, and Ba) solid oxide fuel cell cathodes: a first-principles and experimental study
journal, January 2016

  • Sharma, Vinit; Mahapatra, Manoj K.; Krishnan, Sridevi
  • Journal of Materials Chemistry A, Vol. 4, Issue 15
  • DOI: 10.1039/C6TA00603E

Spectroscopic and photorefractive properties of molybdenum‐doped barium titanate
journal, September 1995

  • Schwartz, Robert N.; Wechsler, Barry A.; West, Linda
  • Applied Physics Letters, Vol. 67, Issue 10
  • DOI: 10.1063/1.115548

Incorporation of Yttrium in Barium Titanate Ceramics
journal, May 1999


Ca 2+ and Ga 3+ doped LaMnO 3 perovskite as a highly efficient and stable catalyst for two-step thermochemical water splitting
journal, January 2017

  • Wang, Lulu; Al-Mamun, Mohammad; Zhong, Yu Lin
  • Sustainable Energy & Fuels, Vol. 1, Issue 5
  • DOI: 10.1039/C6SE00097E

Substituting Sites of Rare Earth Ions in BaTiO 3
journal, March 1968

  • Takeda, Takeshi; Watanabe, Akinori
  • Japanese Journal of Applied Physics, Vol. 7, Issue 3
  • DOI: 10.1143/JJAP.7.232

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


Perovskite Oxides: Preparation, Characterizations, and Applications in Heterogeneous Catalysis
journal, August 2014

  • Zhu, Junjiang; Li, Hailong; Zhong, Linyun
  • ACS Catalysis, Vol. 4, Issue 9
  • DOI: 10.1021/cs500606g

Simplifying decision trees
journal, September 1987


Magnetic entropy change in polycrystalline La1−xKxMnO3 perovskites
journal, August 2007


Ageing of low field dielectric constant and losses in (Hf, Zr)-doped BaTiO 3 ceramics
journal, June 2000


Temperature stable Ba1−xCdxTiO3 dielectrics
journal, October 2002


Influence of calcium doping on performance of LaMnO3 supercapacitors
journal, June 2018


Ensemble Machine Learning
book, January 2012


Dopants in Lanthanum Manganite: Insights from First-Principles Chemical Space Exploration
journal, September 2016

  • Krishnan, Sridevi; Sharma, Vinit; Singh, Prabhakar
  • The Journal of Physical Chemistry C, Vol. 120, Issue 39
  • DOI: 10.1021/acs.jpcc.6b04524

Ferroelectric Ceramics: History and Technology
journal, April 1999


Experimental study on the high performance of Zr doped LaCoO3 for solar thermochemical CO production
journal, June 2020


Theoretical Prediction of Magnetic Properties of Ba(Ti1-xMx)O3 (M=Sc,V,Cr,Mn,Fe,Co,Ni,Cu)
journal, December 2001

  • Nakayama, Hiroyuki; Katayama-Yoshida, Hiroshi
  • Japanese Journal of Applied Physics, Vol. 40, Issue Part 2, No. 12B
  • DOI: 10.1143/JJAP.40.L1355

PTC Effect in BaTiO3 as a Function of Doping with 3d Elements
journal, October 1981


Electric field control of the LaAlO3/SrTiO3 interface ground state
journal, December 2008

  • Caviglia, A. D.; Gariglio, S.; Reyren, N.
  • Nature, Vol. 456, Issue 7222
  • DOI: 10.1038/nature07576

Density functional theory and the band gap problem
journal, March 1985

  • Perdew, John P.
  • International Journal of Quantum Chemistry, Vol. 28, Issue S19
  • DOI: 10.1002/qua.560280846

Understanding band gaps of solids in generalized Kohn–Sham theory
journal, March 2017

  • Perdew, John P.; Yang, Weitao; Burke, Kieron
  • Proceedings of the National Academy of Sciences, Vol. 114, Issue 11
  • DOI: 10.1073/pnas.1621352114

Giant thermoelectric Seebeck coefficient of a two-dimensional electron gas in SrTiO3
journal, January 2007

  • Ohta, Hiromichi; Kim, SungWng; Mune, Yoriko
  • Nature Materials, Vol. 6, Issue 2
  • DOI: 10.1038/nmat1821

The phase stability of BaTiO 3 as a function of doped 3d elements: an experimental study
journal, February 1978


Theoretical Study on Interactions between Oxygen Vacancy and Doped Rare-Earth Elements in Barium Titanate
journal, September 2011

  • Honda, Atsushi; Higai, Shin'ichi; Motoyoshi, Yasuhiro
  • Japanese Journal of Applied Physics, Vol. 50, Issue 9
  • DOI: 10.1143/JJAP.50.09NE01

Defect Chemistry of Donor-Doped BaTiO3
journal, April 1984


Ground-state properties of multivalent manganese oxides: Density functional and hybrid density functional calculations
journal, May 2007


The role of deep acceptor centers in the oxidation of acceptor-doped wide-band-gap perovskites ABO 3
journal, March 2017


Theoretical analysis of the structural deformation in Mn-doped BaTiO3
journal, February 2005


A Perovskite Oxide Optimized for Oxygen Evolution Catalysis from Molecular Orbital Principles
journal, October 2011


Dopant-mediated structural and magnetic properties of TbMnO 3
journal, July 2015

  • Sharma, Vinit; McDannald, A.; Staruch, M.
  • Applied Physics Letters, Vol. 107, Issue 1
  • DOI: 10.1063/1.4926369

Enhanced Photoelectrochemical Response of BaTiO 3 with Fe Doping: Experiments and First-Principles Analysis
journal, November 2011

  • Upadhyay, Sumant; Shrivastava, Jaya; Solanki, Anjana
  • The Journal of Physical Chemistry C, Vol. 115, Issue 49
  • DOI: 10.1021/jp202863a

Catalytic behavior of ABO3 perovskites in the oxidative coupling of methane
journal, June 2020


Electronic structure of doped LaMnO 3 perovskite studied by x-ray photoemission spectroscopy
journal, May 2001


Reversible Weight Change of Acceptor-Doped BaTiO3
journal, October 1981


Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set
journal, July 1996


Microstructural Investigations of Barium Titanate-Based Material for Base Metal Electrode Ceramic Multilayer Capacitor
journal, April 2001


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

Multifidelity Information Fusion with Machine Learning: A Case Study of Dopant Formation Energies in Hafnia
journal, April 2019

  • Batra, Rohit; Pilania, Ghanshyam; Uberuaga, Blas P.
  • ACS Applied Materials & Interfaces, Vol. 11, Issue 28
  • DOI: 10.1021/acsami.9b02174

Accuracy of ab initio methods in predicting the crystal structures of metals: A review of 80 binary alloys
journal, September 2005


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


Structure and magnetic properties of substitution of K for La in LaMnO3 perovskite
journal, May 2007


Ab initio molecular-dynamics simulation of the liquid-metal–amorphous-semiconductor transition in germanium
journal, May 1994


Defect studies of doped and undoped barium titanate using computer simulation techniques
journal, January 1986


Influence of foreign ions on the crystal structure of BaTiO3
journal, November 2000


Cationic surface segregation in doped LaMnO3
journal, February 2015


Processing of Laminated Barium Titanate Structures for Stress-Sensing Applications
journal, September 1995


A high-throughput infrastructure for density functional theory calculations
journal, June 2011


Effect of Fe doping on the electrical properties of BaTiO 3 crystalline materials at room temperature
journal, January 2020


Effect of strontium doping on structural and dielectric behaviour of barium titanate nanoceramics
journal, June 2018


Structural, spectroscopic and dielectric properties of Ca-doped BaTiO3
journal, February 2019

  • Khedhri, Mohamed Hassen; Abdelmoula, Najmeddine; Khemakhem, Hamadi
  • Applied Physics A, Vol. 125, Issue 3
  • DOI: 10.1007/s00339-019-2487-y

Machine-learned impurity level prediction for semiconductors: the example of Cd-based chalcogenides
journal, April 2020

  • Mannodi-Kanakkithodi, Arun; Toriyama, Michael Y.; Sen, Fatih G.
  • npj Computational Materials, Vol. 6, Issue 1
  • DOI: 10.1038/s41524-020-0296-7

Oxidation energies of transition metal oxides within the GGA + U framework
journal, May 2006


Design principles for oxygen-reduction activity on perovskite oxide catalysts for fuel cells and metal–air batteries
journal, June 2011

  • Suntivich, Jin; Gasteiger, Hubert A.; Yabuuchi, Naoaki
  • Nature Chemistry, Vol. 3, Issue 7, p. 546-550
  • DOI: 10.1038/nchem.1069

The influence of ionic radii on the incorporation of trivalent dopants into BaTiO3
journal, November 1988


Computer Simulation Studies of Strontium Titanate
journal, February 1995


Random Forests
journal, January 2001


Structural phase transition and T c distribution in Hf-doped LaMn O 3 investigated using perturbed-angular-correlation spectroscopy
journal, August 1996


Effect of SrTiO3 concentration and sintering temperature on microstructure and dielectric constant of Ba1−xSrxTiO3
journal, January 2004


Mott gapping in 3 d A B O 3 perovskites without Mott-Hubbard interelectronic repulsion energy U
journal, July 2019


Preparation and Properties of La and K Co-Doped BaTiO 3 Lead-Free Piezoelectric Ceramics
journal, January 2012


Intrinsic magnetism in BaTiO 3 with magnetic transition element dopants (Co, Cr, Fe) synthesized by sol-precipitation method
journal, April 2011

  • Liu, Hongxue; Cao, Baobao; O’Connor, Charles
  • Journal of Applied Physics, Vol. 109, Issue 7
  • DOI: 10.1063/1.3556768

Magnetic ordering in TbMn 0.5 Cr 0.5 O 3 studied by neutron diffraction and first-principles calculations
journal, July 2014

  • Staruch, M.; Sharma, V.; dela Cruz, C.
  • Journal of Applied Physics, Vol. 116, Issue 3
  • DOI: 10.1063/1.4890637

Atomistic Simulation of Dopant Incorporation in Barium Titanate
journal, February 2001


Python Materials Genomics (pymatgen): A robust, open-source python library for materials analysis
journal, February 2013


Comprehensive examination of dopants and defects in BaTiO 3 from first principles
journal, April 2013


Effects of donor concentration on the electrical properties of Nb-doped BaTiO3 thin films
journal, March 2005

  • Liu, Lifeng; Guo, Haizhong; Lü, Huibin
  • Journal of Applied Physics, Vol. 97, Issue 5
  • DOI: 10.1063/1.1858056