Machine-learning-based prediction of cubic perovskite formation energy and magnetism

被引：0

作者：

Chen J. ^{[1
,2
]}

Song Y. ^{[1
,2
]}

Li S. ^{[1
,2
]}

Que Z. ^{[1
,2
]}

Zhang W. ^{[1
,2
]}

机构：

[1] Key Laboratory of Genetic Engineering of Flexible Electronic Materials of Hunan Province, Changsha

[2] School of Physics and Electronic Science, Changsha University of Science and Technology, Changsha

来源：

Zhongguo Kexue Jishu Kexue/Scientia Sinica Technologica | 2024年 / 54卷 / 02期

关键词：

cubic perovskites; formation energy; machine learning; magnetic classification; magnetic moment; material descriptor;

D O I：

10.1360/SST-2023-0104

中图分类号：

学科分类号：

摘要：

Perovskite materials have garnered considerable attention due to their excellent properties. Thus, the accurate prediction of their physical properties is paramount. In this study, we developed an element attribute matrix descriptor via element attribute addition or phase division to improve the prediction efficiency of formation energy and magnetism of cubic perovskite. For this purpose, we trained three machine-learning models, namely extra tree, gradient boosting, and multi-layer perceptron, based on 18928 cubic perovskite data. Subsequent evaluation was conducted to evaluate the predictive efficiency of formation energy, volume-normalized magnetic moment, and magnetic classification. The results revealed that the efficiency of the developed descriptor was far higher than that of element attribute statistics and force-field inspired descriptors. The R2 fractions for the prediction of formation energy and magnetization were found to be 97% and 80%, respectively. In addition, the AUC of magnetic/non-magnetic classification reached 93%, with the accuracy exceeding 90%. Thus, this paper provides an important reference for the prediction of perovskite materials based on machine learning by constructing a simple and effective material descriptor. © 2024 Chinese Academy of Sciences. All rights reserved.

引用

页码：247 / 256

页数：9

共 48 条

[1]

Pena M A, Fierro J L G., Chemical structures and performance of perovskite oxides, Chem Rev, 101, pp. 1981-2018, (2001)

[2]

Sariful Sheikh M, Ghosh D, Dutta A, Et al., Lead free double perovskite oxides Ln2NiMnO6 (Ln = La, Eu, Dy, Lu), a new promising material for photovoltaic application, Mater Sci Eng-B, 226, pp. 10-17, (2017)

[3]

Hirasawa M, Ishihara T, Goto T, Et al., Magnetoabsorption of the lowest exciton in perovskite-type compound (CH3NH3)PbI3, Phys B-Condensed Matter, 201, pp. 427-430, (1994)

[4]

De Wolf S, Holovsky J, Moon S J, Et al., Organometallic halide perovskites: Sharp optical absorption edge and its relation to photovoltaic performance, J Phys Chem Lett, 5, pp. 1035-1039, (2014)

[5]

Eperon G E, Leijtens T, Bush K A, Et al., Perovskite-perovskite tandem photovoltaics with optimized band gaps, Science, 354, pp. 861-865, (2016)

[6]

Suresh Kumar N, Chandra Babu Naidu K., A review on perovskite solar cells (PSCs), materials and applications, J Materiom, 7, pp. 940-956, (2021)

[7]

Green M A, Dunlop E D, Hohl-Ebinger J, Et al., Solar cell efficiency tables (Version 55), Prog Photovolt Res Appl, 28, pp. 3-15, (2019)

[8]

Heimbrook A, Higgins K, Kalinin S V, Et al., Exploring the physics of cesium lead halide perovskite quantum dots via Bayesian inference of the photoluminescence spectra in automated experiment, Nanophotonics, 10, pp. 1977-1989, (2020)

[9]

Li L, Tian G, Chang W, Et al., A novel double-perovskite LiLaMgTeO6:Mn4+ far-red phosphor for indoor plant cultivation white LEDs: Crystal and electronic structure, and photoluminescence properties, J Alloys Compd, 832, (2020)

[10]

Wang N, Liu W, Zhang Q., Perovskite-based nanocrystals: Synthesis and applications beyond solar cells, Small Methods, 2, (2018)

← 1 2 3 4 5 →