Machine learning substitutional defect formation energies in ABO3 perovskites

被引:26
|
作者
Sharma, Vinit [1 ,2 ]
Kumar, Pankaj [3 ]
Dev, Pratibha [3 ]
Pilania, Ghanshyam [4 ]
机构
[1] Univ Tennessee, Joint Inst Computat Sci, Knoxville, TN 37996 USA
[2] Oak Ridge Natl Lab, Natl Inst Computat Sci, POB 2009, Oak Ridge, TN 37831 USA
[3] Howard Univ, Dept Phys & Astron, Washington, DC 20059 USA
[4] Los Alamos Natl Lab, Mat Sci & Technol Div, Los Alamos, NM 87545 USA
基金
美国国家科学基金会;
关键词
DENSITY-FUNCTIONAL THEORY; DOPED LAMNO3 PEROVSKITE; COMPUTER-SIMULATION; DIELECTRIC-CONSTANT; MAGNETIC-PROPERTIES; IONIC-RADII; BATIO3; 1ST-PRINCIPLES; TEMPERATURE; TRANSITION;
D O I
10.1063/5.0015538
中图分类号
O59 [应用物理学];
学科分类号
摘要
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. We have developed a framework that itself is general and can be potentially applied to other material classes.
引用
收藏
页数:10
相关论文
共 50 条
  • [41] What about the role of B elements in the CMR properties of ABO3 perovskites?
    Raveau, B
    Martin, C
    Maignan, A
    JOURNAL OF ALLOYS AND COMPOUNDS, 1998, 275 : 461 - 467
  • [42] Local instability above tc in abo3 perovskites with discontinuous phase transitions
    Roleder, K.
    Szot, K.
    Gorny, M.
    Ujma, Z.
    Kajewski, D.
    Jankowska-Sumara, I.
    Majchrowski, A.
    ACTA CRYSTALLOGRAPHICA A-FOUNDATION AND ADVANCES, 2011, 67 : C334 - C334
  • [43] Recent Status and Developments of Vacancies Modulation in the ABO3 Perovskites for Catalytic Applications
    Mi, Jinxing
    Chen, Jianjun
    Chen, Xiaoping
    Liu, Xiaoqing
    Li, Junhua
    CHEMISTRY-A EUROPEAN JOURNAL, 2023, 29 (08)
  • [44] Phase stability and dielectric constant of ABO3 perovskites from first principles
    Kersch, Alfred
    Fischer, Dominik
    JOURNAL OF APPLIED PHYSICS, 2009, 106 (01)
  • [45] Perspectives and scope of ABO3 type multiferroic rare-earth perovskites
    Khan, Huma
    Ahmad, Tokeer
    CHINESE JOURNAL OF PHYSICS, 2024, 91 : 199 - 219
  • [46] Predictions of new ABO3 perovskite compounds by combining machine learning and density functional theory
    Balachandran, Prasanna V.
    Emery, Antoine A.
    Gubernatis, James E.
    Lookman, Turab
    Wolverton, Chris
    Zunger, Alex
    PHYSICAL REVIEW MATERIALS, 2018, 2 (04):
  • [47] Machine Learning Prediction of Defect Formation Energies in a-SiO2
    Milardovich, Diego
    Jech, Markus
    Waldhoer, Dominic
    Waltl, Michael
    Grasser, Tibor
    2020 INTERNATIONAL CONFERENCE ON SIMULATION OF SEMICONDUCTOR PROCESSES AND DEVICES (SISPAD 2020), 2020, : 339 - 342
  • [48] Machine learning prediction of defect formation energies in a-SiO2
    Technische Universität Wien, Institute for Microelectronics, Gußhausstraße 27-29, Vienna
    1040, Austria
    不详
    1040, Austria
    Int Conf Simul Semicond Process Dev Proc SISPAD, 2020, (339-342):
  • [49] Prediction of nature of band gap of perovskite oxides (ABO3) using a machine learning approach
    Priyanga, G. Sudha
    Mattur, Manoj N.
    Nagappan, N.
    Rath, Smarak
    Thomas, Tiju
    JOURNAL OF MATERIOMICS, 2022, 8 (05) : 937 - 948
  • [50] Ab initio approach to the ferroelectric properties of the ABO3 perovskites:: The case of KNbO3
    Baranek, P
    Dovesi, R
    FERROELECTRICS, 2002, 268 : 155 - 162