Finding New Perovskite Halides via Machine Learning

被引:154
作者
Pilania, Ghanshyam [1 ]
Balachandran, Prasanna V. [2 ]
Kim, Chiho [3 ]
Lookman, Turab [2 ]
机构
[1] Los Alamos Natl Lab, Div Mat Sci & Technol, Los Alamos, NM USA
[2] Los Alamos Natl Lab, Div Theoret, Los Alamos, NM USA
[3] Univ Connecticut, Inst Mat Sci, Dept Mat Sci & Engn, Storrs, CT USA
关键词
perovskites; informatics; support vector machines; formability; materials discovery; FORMABILITY; DESIGN; STABILITY; CHEMISTRY;
D O I
10.3389/fmats.2016.00019
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Advanced materials with improved properties have the potential to fuel future technological advancements. However, identification and discovery of these optimal materials for a specific application is a non-trivial task, because of the vastness of the chemical search space with enormous compositional and configurational degrees of freedom. Materials informatics provides an efficient approach toward rational design of new materials, via learning from known data to make decisions on new and previously unexplored compounds in an accelerated manner. Here, we demonstrate the power and utility of such statistical learning (or machine learning, henceforth referred to as ML) via building a support vector machine (SVM) based classifier that uses elemental features (or descriptors) to predict the formability of a given ABX(3) halide composition (where A and B represent monovalent and divalent cations, respectively, and X is F, Cl, Br, or I anion) in the perovskite crystal structure. The classification model is built by learning from a dataset of 185 experimentally known ABX(3) compounds. After exploring a wide range of features, we identify ionic radii, tolerance factor, and octahedral factor to be the most important factors for the classification, suggesting that steric and geometric packing effects govern the stability of these halides. The trained and validated models then predict, with a high degree of confidence, several novel ABX(3) compositions with perovskite crystal structure.
引用
收藏
页数:7
相关论文
共 39 条
[1]  
[Anonymous], 2012, Model ensembles,'' inMachine Learning: The Art and Scienceof Algorithms That Make Sense of Data
[2]  
[Anonymous], 2015, MAT GEN APPR
[3]   Adaptive Strategies for Materials Design using Uncertainties [J].
Balachandran, Prasanna V. ;
Xue, Dezhen ;
Theiler, James ;
Hogden, John ;
Lookman, Turab .
SCIENTIFIC REPORTS, 2016, 6
[4]   Materials Prediction via Classification Learning [J].
Balachandran, Prasanna V. ;
Theiler, James ;
Rondinelli, James M. ;
Lookman, Turab .
SCIENTIFIC REPORTS, 2015, 5
[5]   BOND VALENCES - SIMPLE STRUCTURAL MODEL FOR INORGANIC-CHEMISTRY [J].
BROWN, ID .
CHEMICAL SOCIETY REVIEWS, 1978, 7 (03) :359-376
[6]   Recharging lithium battery research with first-principles methods [J].
Ceder, G. ;
Hautier, G. ;
Jain, A. ;
Ong, S. P. .
MRS BULLETIN, 2011, 36 (03) :185-191
[7]  
Cherkassky V, 1997, IEEE Trans Neural Netw, V8, P1564, DOI 10.1109/TNN.1997.641482
[8]   Uncertainty Relations from Simple Entropic Properties [J].
Coles, Patrick J. ;
Colbeck, Roger ;
Yu, Li ;
Zwolak, Michael .
PHYSICAL REVIEW LETTERS, 2012, 108 (21)
[9]  
Curtarolo S, 2013, NAT MATER, V12, P191, DOI [10.1038/NMAT3568, 10.1038/nmat3568]
[10]   AFLOWLIB.ORG: A distributed materials properties repository from high-throughput ab initio calculations [J].
Curtarolo, Stefano ;
Setyawan, Wahyu ;
Wang, Shidong ;
Xue, Junkai ;
Yang, Kesong ;
Taylor, Richard H. ;
Nelson, Lance J. ;
Hart, Gus L. W. ;
Sanvito, Stefano ;
Buongiorno-Nardelli, Marco ;
Mingo, Natalio ;
Levy, Ohad .
COMPUTATIONAL MATERIALS SCIENCE, 2012, 58 :227-235