Please wait a minute...
材料导报  2020, Vol. 34 Issue (23): 23100-23108    https://doi.org/10.11896/cldb.19110175
  无机非金属及其复合材料 |
机器学习在材料信息学中的应用综述
牛程程1, 李少波1,2, 胡建军2,3, 但雅波2, 曹卓2, 李想2
1 贵州大学现代制造技术教育部重点实验室,贵阳 550025
2 贵州大学机械工程学院,贵阳 550025
3 美国南卡罗来纳大学计算机科学与工程系,哥伦比亚 29208, 美国
Application of Machine Learning in Material Informatics: a Survey
NIU Chengcheng1, LI Shaobo1,2, HU Jianjun2,3, DAN Yabo2, CAO Zhuo2, LI Xiang2
1 Key Laboratory of Advanced Manufacturing Technology (Ministry of Education), Guizhou University, Guiyang 550025, China
2 School of Mechanical Engineering, Guizhou University, Guiyang 550025, China
3 Department of Computer Science and Engineering, University of South Carolina, SC 29208, USA
下载:  全 文 ( PDF ) ( 2675KB ) 
输出:  BibTeX | EndNote (RIS)      
摘要 面对巨大的材料设计空间,基于理论研究、实验分析以及计算仿真的传统方法已经跟不上高性能新材料的发展需求。近年来,材料数据库与机器学习的结合带动了材料信息学的进步,推动了材料科学的发展。当前,运用数据驱动的机器学习算法建立材料性能预测模型,然后将其应用于材料筛选与新材料开发的研究引起了学者们的广泛关注。利用机器学习框架搭建材料研究设计平台对材料大数据资源进行分析与预测,成为开发新型材料的重要手段。
将机器学习运用于材料科学面临一系列困难,包括根据预测对象确定材料特征的计算或自动抽取,不同精度的实验与计算数据的获取与预处理;选取或者开发合适的机器学习预测模型和训练算法;估计预测效果与预测性能的可靠性;处理材料机器学习问题所独有的小数据、异构数据、非平衡数据等特性。目前研究的焦点是针对不同的材料性能,收集相关的数据集,基于物理原理构造特征表示来训练机器学习模型,并将机器学习的最新技术用于材料信息学。
现阶段机器学习已经被应用于光伏、热电、半导体、有机材料等几乎所有的材料设计领域。通过采用机器学习算法训练材料性能的预测模型,并将其用于筛选现有材料数据库或者搜索新的材料,大大加快了新材料发现的过程。目前,国内外科学家借助统计推理与机器学习算法开展了一系列的研究,开发了适合预测不同材料属性的多种材料表征方法,应用了包括深度学习、贝叶斯网络等最新机器学习与人工智能方法,在多类功能材料设计领域取得了突破性的成果。
本文主要介绍了机器学习方法在材料性能预测中的相关研究与应用,包括目前最常用的材料数据库资源,多种适用的机器学习算法及应用实例,以及机器学习在材料性能预测中遇到的常见问题。最后对国内外的材料信息学发展现状进行了概括,并对其未来发展进行了展望。
服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
牛程程
李少波
胡建军
但雅波
曹卓
李想
关键词:  材料信息学  材料科学  材料性能  机器学习  大数据    
Abstract: In the face of huge material design space, the traditional methods based on theoretical research, experimental analysis and computational simulation cannot keep up with the development of new materials with high performance. In recent years, the combination of material database and machine learning has led to the progress of material informatics and the development of material science. At present, the use of data-driven machine learning algorithms to establish material performance prediction models, and then apply them to materials screening and new material deve-lopment research has attracted widespread attention from scholars. Using the machine learning framework to build the material research and design platform to analyze and predict the material big data resources has become an important means to develop new materials.
Machine learning is applied to a series of difficulties faced by materials science, including the calculation or automatic extraction of material characteristics according to the predicted objects, the acquisition and preprocessing of experimental and computational data with different precision, the selection or development of appropriate machine learning prediction models and training algorithms, estimating the reliability of prediction effect and predictive performance, and deal with material machine learning problems with the unique characteristics of small data, heterogeneous data and unbalanced data. At present, the focus of research is to collect relevant data sets, construct feature representations based on physical principles to train machine learning models and apply the latest techniques of machine learning to material informatics for different material properties.
Machine learning has been used in photovoltaic, thermoelectric, semiconductor, organic materials and other materials design fields. The process of new material discovery is greatly accelerated by using machine learning algorithm to train the prediction model of material performance and to screen existing material database or search new material. At present, scientists at home and abroad have carried out a series of research with the help of statistical reasoning and machine learning algorithms, developed a variety of material characterization methods suitable for predicting the properties of different materials, and applied the latest machine learning and artificial intelligence methods, including deep learning, Bayesian network, etc. Breakthrough achievements have been made in the field of multi-functional material design.
This paper mainly introduces the related research and application of machine learning methods in material performance prediction, including the most commonly used material database resources, various applicable machine learning algorithms and application examples, and the common problems encountered by machine learning in material performance prediction. Finally, the development status of material informatics at home and abroad is summarized and the future development is prospected.
Key words:  materials informatics    material science    material properties    machine learning    big data
               出版日期:  2020-12-10      发布日期:  2020-12-24
ZTFLH:  TP181  
  TB302  
基金资助: 国家自然科学基金(51741101)
通讯作者:  jianjunh@cse.sc.edu   
作者简介:  牛程程,2017年6月毕业于山东交通学院,获得工学学士学位。现为贵州大学现代制造技术教育部重点实验室硕士研究生,在胡建军教授的指导下进行研究。目前主要研究领域为材料信息学。
胡建军,贵州大学机械学院特聘教授、博士研究生导师;美国南卡罗来纳大学计算机科学与工程系终身副教授。分别于1995年和1998年获得武汉理工大学机械工程学士与硕士学位。2004年获得密歇根州立大学计算机科学专业博士学位。2004年至2007年在普渡大学和南加州大学担任博士后研究员。主要研究方向:机器学习、材料信息学、生物信息学、智能制造。获得美国国家自然科学基金委 Career Award以及国家自然科学基金项目《基于机器学习与图像处理算法的高通量组合材料实验相图生成与物相辨识方法研究》资助。已发表SCI论文60余篇。学术服务兼任 Nature Scientific Report, PLOS ONE和 BMC Bioinformatics的副编辑。
引用本文:    
牛程程, 李少波, 胡建军, 但雅波, 曹卓, 李想. 机器学习在材料信息学中的应用综述[J]. 材料导报, 2020, 34(23): 23100-23108.
NIU Chengcheng, LI Shaobo, HU Jianjun, DAN Yabo, CAO Zhuo, LI Xiang. Application of Machine Learning in Material Informatics: a Survey. Materials Reports, 2020, 34(23): 23100-23108.
链接本文:  
http://www.mater-rep.com/CN/10.11896/cldb.19110175  或          http://www.mater-rep.com/CN/Y2020/V34/I23/23100
1 Ceder G, Morgan D, Fischer C, et al. MRS Bulletin,2006,31,981.
2 Saad Y, Gao D, Ngo T, et al. Physical Review B,2012,85,1092.
3 Gaultois M W, Oliynyk A O, Mar A, et al. Apllied Materials,2016,4(5),053213.
4 Wang Z, Wang M, Yong Q L, et al. Materials China,2017,36(2),132(in Chinese).
王卓,王礞,雍歧龙,等.中国材料进展,2017,36(2),132.
5 Phil D L, Jennifer W, Yoshua B, et al. Nature,2017,552(7683),23.
6 Ferguson A L. Journal of Physics-Condensed Matter,2018,30(4),043002.
7 Mannodi-Kanakkithodi A, Tran H, Ramprasad R. Chemistry of Mate-rials,2017,29,9001.
8 Pilania G, Mannodi-Kanakkithodi A, Uberuaga B P, et al. Scientific Reports,2016,6,19375.
9 Kim C, Huan T D, Krishnan S, et al. Scientific Data,2017,4,170057.
10 Legrain F, Carrete J, Roekeghem A V, et al. Chemistry of Materials,2017,29,6220.
11 Kim C, Pilania G, Ramprasad R. Journal of Physical Chemistry C,2016,120,14575.
12 Raccuglia P, Elbert K C, Adler P D, et al. Nature,2016,533,73.
13 Xue D Z, Balachandran P V, Yuan R H, et al. Proceedings of the National Academy of Sciences of the United States of America,2016,113,13301.
14 Wilson D R, Mishra B, Rui Y, et al. Molecular Therapy,2017,25,21.
15 Pankajakshan P, Sanyal S, Noord O E D, et al. Chemistry of Materials,2017,29(10),04229.
16 Seko A, Takahashi A, Tanaka I. Physical Review B,2015,92(5),054113.
17 Deml A M, Hayre R O, Wolverton C, et al. Physical Review B,2016,93,085142.
18 Lee J, Seko A, Shitara K, et al. Physics,2015,89,611.
19 Agrawal A, Choudhary A. Apllied Materials,2016,4,1.
20 Greeley J, Jaramillo T F, Bonde J, et al. Nature Materials,2006,5,909.
21 Sun S, Zhang T Y. In: The Chinese Congress of Theoretical and Applied Mechanics(CCTAM 2015). Shanghai,2015,pp.332(in Chinese).
孙升,张统一.中国力学大会-2015,上海,2015,pp.332.
22 Wang H, Xiang Y, Xiang X D, et al. Science & Technology Review,2015,33(10),13(in Chinese).
汪洪,向勇,项晓东,等.科技导报,2015,33(10),13.
23 Wang H Z, Wang H, Ding H, et al. Science & Technology Review,2015,33(10),31(in Chinese).
王海舟,汪洪,丁洪,等.科技导报,2015,33(10),31.
24 Xiang X D, Wang H, Xiang Y, et al. Science & Technology Review,2015,33(10),64(in Chinese).
项晓东,汪洪,向勇,等.科技导报,2015,33(10),64.
25 Pan D, Qi X G, Liu L L, et al. Journal of the Chinese Ceramic Society,2018,46(4),479(in Chinese).
潘都,戚兴国,刘丽露,等.硅酸盐学报,2018,46(4),479.
26 Xiao R J, Li H, Chen L Q. Acta Physica Sinica,2018,67(12),291(in Chinese).
肖睿娟,李泓,陈立泉.物理学报,2018,67(12),291.
27 Chen L Q. Battery Bimonthly,2002,32(s1),32(in Chinese).
陈立泉.电池,2002,32(s1),32.
28 Lookman T, Balachandran P V, Xue D Z, et al. Current Opinion in Solid State & Materials Science,2017,21,121.
29 Seko A, Togo A, Tanaka I. Nanoinformatics, Springer, Singapore,2018.
30 Elton D C, Boukouvalas Z, Butrico M S, et al. Scientific Reports,2018,8,9059.
31 Wang M Z, Wu J X, Lin L, et al. ACS Nano,2016,10,10317.
32 Mannodi-Kanakkithodi A, Pilania G, Ramprasad R. Computational Materials Science,2016,125,123.
33 Aryal S, Sakidja R, Barsoum M W, et al, Physica Status Solidi B-Basic Solid State Physics,2014,251,1480.
34 Faber F A, Lindmaa A, Von Lilienfeld O A, et al. Physical Review Letters,2016,117(13),135502.
35 Meredig B, Agrawal A, Kirklin S, et al. Physical Review B,2014,89(9),094104.
36 Seko A, Maekawa T, Tsuda K, et al. Physical Review B,2014,89,054303.
37 Seko A, Togo A, Hayashi H, et al. Physical Review Letters,2015,115(20),205901.
38 Li Z, Ma X F, Xin H L. Catalysis Today,2017,280,232.
39 Hong W T, Welsch R E, Shao-Horn Y. Journal of Physical Chemistry C,2016,120,78.
40 Pilania G, Whittle K R, Jiang C, et al. Chemistry of Materials,2017,29,2574.
41 Konno T, Kurokawa H, Nabeshima F, et al. arXiv preprint arXiv,2018,1812,01995.
42 Stanev V, Oses C, Kusne A G, et al. NPJ Computational Materials,2018,4,29.
43 Mannodi-Kanakkithodi A, Pilania G, Huan T D, et al. Scientific Reports,2016,6,20952.
44 Mueller T, Kusne A G, Ramprasad R. Machine Learning in Materials Science: Recent Progress and Emerging Applications, Reviews in Computational Chemistry, USA,2016.
45 Chmiela S, Tkatchenko A, Sauceda H E, et al. Science Advances,2016,3(5),1603015.
46 Rupp M, Tkatchenko A, Muller K R, et al. Physical Review Letters,2012,108(5),58301.
47 Kirklin S, Meredig B, Wolverton C. Advanced Energy Materials,2013,3,252.
48 Behler J, Martonak R, Donadio D, et al. Physical Review Letters,2008,100(18),185501.
49 Behler J. Journal of Physics Condensed Matter An Institute of Physics Journal,2014,26,183001.
50 Bartok A P, Payne M C, Kondor R, et al. Physical Review Letters,2010,104(13),136403.
51 Bartok A P, Csanyi G. International Journal of Quantum Chemistry,2016,115(16),1051.
52 Zhao J C. Chinese Journal of Nature,2014,36,89.
53 Xiao J M, Wang H, Ouyang C Y. Journal of Jiangxi Normal University(Natural Science Edition),2015,39(1),73(in Chinese).
肖建茂,汪浩,欧阳楚英.江西师范大学学报(自然科学版),2015,39(1),73.
54 Jain A, Ong S P, Hautier G, et al. Apllied Materials,2013,1,1049.
55 Curtarolo S, Setyawan W, Hart G L W, et al. Computational Materials Science,2012,58,218.
56 Curtarolo S, Setyawan W, Wang S D, et al. Computational Materials Science,2012,58,227.
57 Taylor R H, Rose F, Toher C, et al. Computational Materials Science,2014,93,178.
58 Kalidindi S R, Graef M D. Annual Review of Materials Research,2015,45,171.
59 Dompablo M E A Y D, Ven A V D, Ceder G. Physical Review B,2002,66,340.
60 Jain A, Hautier G, Moore C J, et al. Computational Materials Science,2011,50,2295.
61 Wu Y, Lazic P, Hautier G, et al. Energy & Environmental Science,2012,6,157.
62 Yang L, Ceder G. Physical Review B,2013,88(22),330.
63 Pilania G, Kim C, Ramprasad R. Chemistry of Materials,2016,28,1304.
64 Ward L, Agrawal A, Choudhary A, et al. NPJ Computational Materials,2016,2,201628.
65 Fan R E, Chang K W, Hsieh C J, et al. Journal of Machine Learning Research,2008,9,1871.
66 Seko A, Takahashi A, Tanaka I. Physical Review B,2014,90,024101.
67 Gross S M, Tibshirani R. Computational Statistics & Data Analysis,2016,101,226.
68 Schutt K T, Glawe H, Brockherde F, et al. Physical Review B,2014,89(20),118.
69 Ravi D, Wong C, Deligianni F, et al. LEEE Journal of Biomedical and Health Informatics,2017,21,4.
70 Park W B, Chung J, Jung J, et al. Iucrj,2017,4,486.
71 Xu Y J, Pei J F, Lai L H. Journal of Chemical Information and Mode-ling,2017,57,2672.
72 Fan M, Hu J, Cao R, et al. Sci Rep,2017,7(1),18040.
73 Azimi S M, Britz D, Engstler M, et al. Scientific Reports,2018,8(1),2128.
74 Cecen A, Dai H, Yabansu Y C,et al. Acta Materialia,2017,146,76.
75 Ma X, Li Z, Achenie L E, et al. The Journal of Physical Chemistry Letters,2015,6,3528.
76 Chang C C, Lin C J. ACM Transactions on Intelligent Systems and Technology,2011,2,1.
77 Lee K K, Harris C J, Gunn S R, et al. Control Sensitivity SVM for Imba-lanced Data A Case Study on Automotive Material, Springer, Vienna,2001.
78 Farid Kianifard. Technometrics,2004,32,352.
79 Montgomery D C, Peck E A. Introduction to linear regression analysis, Wiley, USA,1982.
80 Friedman J, Hastie T, Tibshirani R. Annals of Statistics,2000,28,337.
81 Weinberger K Q, Saul L K. Journal of Machine Learning Research,2009,10,207.
82 Peterson L E. Scholarpedia,2009,4,1883.
83 Quinlan J R. Machine Learning,1986,1,81.
84 Breiman L. Machine Learning,2001,45,5.
85 Cutler A, Cutler D R, Stevens J R. Machine Learning,2004,45,157.
86 Yosinski J, Clune J, Bengio Y, et al.In: NIPS’14: Proceedings of the 27th International Conference on Neural Information Processing Systems. Cambridge, MA, USA,2014.
87 Chow T W S, Yong F. IEEE Transactions on Industrial Electronics,1998,45,151.
88 Xie T, Gong D L, Zhang W L, et al. Superconductor Science & Technology,2017,30(9),095002.
89 Feng J, Zhou Z H. ArXiv,2018,1709,09018.
90 Ghiringhelli L M, Vybiral J, Ahmetcik E, et al. New Journal of Physics,2017,19,023017.
91 Baraniuk R G. IEEE Signal Processing Magazine,2007,24(4),118.
92 Moreno-Torres J G, Saez J A, Herrera F. IEEE Trans Neural Netw Learn Syst,2012,23,1304.
93 Meredig B, Antono E, Church C, et al. Molecular Systems Design & Engineering,2018,3,819.
94 Jha D, Ward L, Paul A, et al. Scientific Reports,2018,8,17493.
95 Evans J D, Coudert F. Chemistry of Materials,2017,29(18),7833.
96 Zhang Y, Ling C. NPJ Computer Materials,2018,4,25.
97 Hawkins D M. Cheminform,2004,35,1.
98 Wolpert D H, Macready W G. IEEE Transactions on Evolutionary Computation,1997,1,67.
99 Chicco D. Biodata Mining,2017,10(1),35.
100 Zhu H, Tsang E C C, Zhu J. Soft Computing,2018,22,3477.
101 Karpatne A, Watkins W, Read J, et al. ArXiv preprint arXiv,2017,1710,11431.
102 Lemaitre G, Nogueira F, Aridas C K. Journal of Machine Learning Research,2017,18,1.
103 Hand D J. Machine Learning,2009,77,103.
104 Kajita S, Ohba N, Jinnouchi R, et al. Scientific Reports,2017,7,16991.
105 Guyon I, Elisseeff A. Journal of Machine Learning Research,2003,3,1157.
106 Li G Z, Yang J, Liu G P, et al. In: 8th Pacific Rim International Conference on Artificial Intelligence (PRICAI-04), Auckland, New Zea-land,2004,pp.292.
107 Cai J, Luo J, Wang S,et al. Neurocomputing,2018,300,70.
108 Li J, Cheng K, Wang S, et al. ACM Computing Surveys (CSUR),2018,50,94.
109 Sendek A D, Yang Q, Cubuk E D, et al. Energy & Environmental Science,2017,10,306.
110 Hautier G, Fischer C C, Jain A, et al. Chemistry of Materials,2010,22,3762.
111 Meredig B, Agrawal B, Kirklin S, et al. Physical Review B,2014,89,82.
112 Qu X, Jain A, Rajput N N, et al. Computational Materials Science,2015,103,56.
113 Schütter C, Husch T, Viswanathan V, et al. Journal of Power Source,2016,326,541.
114 Su Y, Liang W. Hot Working Technology,2018,47(21),145(in Chinese).
苏燕,梁武.热加工工艺,2018,47(21),145.
115 Sun G M, Liu H, He C F, et al. Journal of Beijing University of Technology,2019,45(2),119(in Chinese).
孙光民,刘浩,何存富,等.北京工业大学学报,2019,45(2),119.
116 Xu Y L, Wang X M, Li X, et al. Scientia Sinica Technologica,2019,49(1),44(in Chinese).
徐永林,王香蒙,李鑫,等.中国科学:技术科学,2019,49(1),44.
117 Zhai X, Chen M, Lu W. Computational Materials Science,2018,151,41.
118 Jiang X, Yin H Q, Zhang C, et al. Computational Materials Science,2018,143,295.
119 Bunn J K, Han S, Zhang Y, et al. Journal of Materials Research,2015,30,879.
120 Bunn J K, Hu J, Hattrick-Simpers J R. JOM,2016,68(8),2116.
121 Xiong Z, He Y, Hattrick-Simpers J R, et al. ACS Combinatorial Science,2017,19(3),137.
122 Li S, Xiong Z, Hu J. Materials Science and Technology,2018,34,315.
123 Atilgan E, Hu J. In: Proceedings of the Companion Publication of the 2015 Annual Conference on Genetic and Evolutionary Computation. Madrid,2015,pp.1349.
124 Atilgan E, Hu J. Bulletin of Materials Science,2018,41,1.
125 Cao Z, Dan Y, Xiong Z, et al. Crystals,2019,9,191.
[1] 康靓, 米晓希, 王海莲, 吴璐, 孙凯, 汤爱涛. 人工神经网络在材料科学中的研究进展[J]. 材料导报, 2020, 34(21): 21172-21179.
[2] 高淑玲, 王文昌. 应变硬化水泥基复合材料性能与应用研究进展[J]. 材料导报, 2019, 33(21): 3620-3629.
[3] 何诗华,严捍东. 国内节能型剪力墙技术研究和应用现状分析[J]. 《材料导报》期刊社, 2018, 32(11): 1910-1915.
[4] 朱麟,刘新宝,辛甜,潘成飞,刘剑秋. 基于微观组织演化的P91钢长时蠕变寿命预测*[J]. 材料导报编辑部, 2017, 31(10): 137-140.
[1] Wei ZHOU, Xixi WANG, Yinlong ZHU, Jie DAI, Yanping ZHU, Zongping SHAO. A Complete Review of Cobalt-based Electrocatalysts Applying to Metal-Air Batteries and Intermediate-Low Temperature Solid Oxide Fuel Cells[J]. Materials Reports, 2018, 32(3): 337 -356 .
[2] Yanzhen WANG, Mingming CHEN, Chengyang WANG. Preparation and Electrochemical Properties Characterization of High-rate SiO2/C Composite Materials[J]. Materials Reports, 2018, 32(3): 357 -361 .
[3] Yimeng XIA, Shuai WU, Feng TAN, Wei LI, Qingmao WEI, Chungang MIN, Xikun YANG. Effect of Anionic Groups of Cobalt Salt on the Electrocatalytic Activity of Co-N-C Catalysts[J]. Materials Reports, 2018, 32(3): 362 -367 .
[4] Dongyong SI, Guangxu HUANG, Chuanxiang ZHANG, Baolin XING, Zehua CHEN, Liwei CHEN, Haoran ZHANG. Preparation and Electrochemical Performance of Humic Acid-based Graphitized Materials[J]. Materials Reports, 2018, 32(3): 368 -372 .
[5] Huanchun WU, Fei XUE, Chengtao LI, Kewei FANG, Bin YANG, Xiping SONG. Fatigue Crack Initiation Behaviors of Nuclear Power Plant Main Pipe Stainless Steel in Water with High Temperature and High Pressure[J]. Materials Reports, 2018, 32(3): 373 -377 .
[6] Miaomiao ZHANG,Xuyan LIU,Wei QIAN. Research Development of Polypyrrole Electrode Materials in Supercapacitors[J]. Materials Reports, 2018, 32(3): 378 -383 .
[7] Qingshun GUAN,Jian LI,Ruyuan SONG,Zhaoyang XU,Weibing WU,Yi JING,Hongqi DAI,Guigan FANG. A Survey on Preparation and Application of Aerogels Based on Nanomaterials[J]. Materials Reports, 2018, 32(3): 384 -390 .
[8] Yunzi LIU,Wei ZHANG,Zhanyong SONG. Technological Advances in Preparation and Posterior Treatment of Metal Nanoparticles-based Conductive Inks[J]. Materials Reports, 2018, 32(3): 391 -397 .
[9] Bingwei LUO,Dabo LIU,Fei LUO,Ye TIAN,Dongsheng CHEN,Haitao ZHOU. Research on the Two Typical Infrared Detection Materials Serving at Low Temperatures: a Review[J]. Materials Reports, 2018, 32(3): 398 -404 .
[10] Lanyan LIU,Jun SONG,Bowen CHENG,Wenchi XUE,Yunbo ZHENG. Research Progress in Preparation of Lignin-based Carbon Fiber[J]. Materials Reports, 2018, 32(3): 405 -411 .
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed