[1]卢凯亮,畅东平,纪晓波,等.基于机器学习的钙钛矿锰氧化物材料设计[J].中国材料进展,2023,42(08):625-630.[doi:10.7502/j.issn.1674-3962.202107065]
　LU Kailiang,CHANG Dongping,JI Xiaobo,et al.Materials Design of Perovskite Manganates Based on Machine Learning[J].MATERIALS CHINA,2023,42(08):625-630.[doi:10.7502/j.issn.1674-3962.202107065]
点击复制

基于机器学习的钙钛矿锰氧化物材料设计()
分享到：

中国材料进展[ISSN:1674-3962/CN:61-1473/TG]

卷:
42
期数:
2023年第08期
页码:
625-630
栏目:
出版日期:
2023-08-31

文章信息/Info

Title:
Materials Design of Perovskite Manganates Based on Machine Learning
文章编号:
1674-3962(2023)08-0625-06
作者:
卢凯亮1; 畅东平1; 纪晓波2; 陆文聪1; 2
1.上海大学 材料基因组工程研究院，上海 200444 2.上海大学理学院，上海 200444
Author(s):
LU Kailiang1;  CHANG Dongping1;  JI Xiaobo2;  LU Wencong1; 2
1. Materials Genome Institute, Shanghai University, Shanghai 200444, China 2. Department of Chemistry, College of Sciences, Shanghai University,Shanghai 200444, China
关键词:
ABO3钙钛矿锰氧化物; 奈尔温度; 机器学习; 高通量筛选; 在线预报
Keywords:
ABO3 perovskite manganates;  Néel temperature;  machine learning;  high-throughput screening;  online prediction
分类号:
TP181;O482.52+5；TQ137.1+2
DOI:
10.7502/j.issn.1674-3962.202107065
文献标志码:
A
摘要:
ABO3钙钛矿锰氧化物因成本低廉和稳定性好，已成为反铁磁体中最热门的存储器材料。提高ABO3钙钛矿锰氧化物的奈尔温度（Néel temperature，TN），使之在室温下呈现反铁磁性，具有重要的意义。利用超多面体方法对特征变量的重要性进行排序，进而结合机器学习算法来筛选特征变量，并构建了极端梯度回归（XGBoost）机器学习模型，搭建了ABO3钙钛矿锰氧化物的TN在线预报平台。利用高通量筛选找到了TN预测值高于室温的候选材料（Sr0.7Ce0.1Sm0.2MnO3，308.5 K），其TN比已知最高的样本还高6.37%。该研究方法有助于实验工作者选择最有希望的材料来做实验，可以加快新材料的研发和性能突破。
Abstract:
ABO3 perovskite manganates has become the most popular memory material in anti-ferromagnets due to its low cost and good stability. It is of great significance to improve the Néel temperature (TN) of ABO3 perovskite manganates to make it antiferromagnetic at room temperature. In this work, hyper-polyhedron method is used to rank the importance of characteristic variables, and the machine learning algorithm is integrated to screen features.The online prediction platform was built for TN of ABO3 perovskite manganates. The XGBoost machine learning model was established to screen out the potential material（Sr0.7Ce0.1Sm0.2MnO3, 308.5 K） with the predicted TN higher than room temperature based on high-throughput screening. The TN of the potential material is 6.37% higher than the highest one known. This research method is helpful for experimental workers to select the most promising materials, which can be used to speed up the research and development of new materials with targeted performances.

参考文献/References:

\[1\]XIA W R, PEI Z P, LENG K H, et al. Nanoscale Research Letters\[J\], 2020, 15(1): 1-55. \[2\]YAMADA S, ABE N, SAGAYAMA H, et al. Physical Review Letters\[J\], 2019, 123(12): 1-6. \[3\]FAN J, XIE Y, YANG Y E, et al. Ceramics International\[J\], 2019, 45(7): 9179-9184. \[4\]WOLLAN E O, KOEHLER W C. Physical Review\[J\], 1955, 100(2): 545-563. \[5\]MORALES R, KOVYLINA M, SCHULLER I K, et al. Applied Physics Letters\[J\], 2014, 104(3): 101-105. \[6\]BODNAR S Y, MEJKAL L, TUREK I, et al. Nature Communications\[J\], 2018, 9(1): 1-7. \[7\]ZELEZNY J, WADLEY P, OLEJNIK K, et al. Nature Physics\[J\], 2018, 14(3): 220-228. \[8\]WU H, ZHU K, XU G, et al. Physica BCondensed Matter\[J\], 2012, 407(3), 770-773. \[9\]赵凤媛,叶益聪,张周然,等.稀有金属材料与工程\[J\],2023,52(4):1192-1200. ZHAO F Y, YE Y C, ZHANG Z R, et al. Rare Metal Materials and Engineering\[J\], 2023, 52(4): 1192-1200. \[10\]GAULTOIS M W, OLIYNYK A O, MAR A, et al. APL Materials\[J\], 2016, 4(5): 11-17. \[11\]XUE D Z, BALACHANDRAN P V, HOGDEN J, et al. Nature Communications\[J\], 2016, 7(5): 1-9. \[12\]LU S H, ZHOU Q H, OUYANG Y X, et al. Nature Communications\[J\], 2018, 9(3): 1-8. \[13\]王向东, 徐鹏程, 卢天, 等. 中国材料进展\[J\],2021, 40(4): 251-256. WANG X D, XU P C, LU T, et al. Materials China\[J\], 2021, 40(4): 251-256. \[14\]VILLARS P, BRANDENBURG K, BERNDT M, et al. Engineering Applications of Artificial Intelligence\[J\], 2000, 13(5): 497-505. \[15\]BAO X H, LU W C, LIU L, et al. Acta Pharmacologica Sinica\[J\], 2003(5): 90-94+98. \[16\]CHEN T, HE T, BENESTY M. XGBoost: Extreme Gradient Boosting\[J\]，2016(11):57-62. \[17\]TIPPING M E. Journal of Machine Learning Research\[J\], 2001, 1(3): 211-244. \[18\]OSTMANN A, ARBIZU P M. Marine Biodiversity\[J\], 2018, 48(2): 719-735. \[19\]徐潇, 卢凯亮, 蒋若宁, 等. 上海大学学报(自然科学版)\[J\], 2019, 25(1): 95-100. XU X, LU K L, JIANG R N, et al. Journal of Shanghai University(Natural Science)\[J\], 2019, 25(1): 95-100. \[20\]ZHANG Q, CHANG D P, ZHAI X Y, et al. Chemometrics and Intelligent Laboratory Systems\[J\], 2018, 177(3): 26-34. \[21\]DONG H, HE D, WANG F. Powder Technology\[J\], 2020, 375: 174-181. \[22\]SEKO A, TOGO A, HAYASHI H, et al. Physical Review Letters\[J\], 2015, 115(20): 205901. \[23\]MULLER K R, MIKA S, RATSCH G, et al. IEEE Transactions on Neural Networks\[J\], 2001, 12(2): 181-201.

备注/Memo

备注/Memo:
收稿日期：2021-07-30修回日期：2022-08-04 基金项目：云南省重大科技专项（202002AB080001-1）； 之江实验室科研攻关项目(2021PE0AC02) 第一作者：卢凯亮，男，1991年生，博士 通讯作者：陆文聪，男，1964年生，教授，博士生导师， Email:wclu@shu.edu.cn
更新日期/Last Update: 2023-07-28