数据+人工智能是材料基因工程的核心

汪洪; 项晓东; 张澜庭

doi:10.3981/j.issn.1000-7857.2018.14.003

科技导报 >

2018 , Vol. 36 >Issue 14: 15 - 21

DOI: https://doi.org/10.3981/j.issn.1000-7857.2018.14.003

科技评论

数据+人工智能是材料基因工程的核心

汪洪 ,
项晓东 ,
张澜庭

展开

1. 上海交通大学材料基因组联合研究中心, 上海 200240;
2. 上海交通大学材料科学与工程学院, 上海 200240;
3. 南方科技大学材料科学与工程系, 深圳 518055

汪洪,教授,研究方向为材料基因工程,电子信箱:hongwang2@sjtu.edu.cn

收稿日期: 2018-05-15

修回日期: 2018-06-19

网络出版日期: 2018-07-27

基金资助

国家重点研发计划项目（2017YFB0701900）；上海市科学技术委员会研发平台专项（16DZ2260602）

收起

Data + AI: The core of materials genomic engineering

WANG Hong ,
XIANG Xiaodong ,
ZHANG Lanting

Expand

1. Materials Genome Initiative Center, Shanghai Jiao Tong University, Shanghai 200240, China;
2. School of Materials Science and Engineering, Shanghai Jiao Tong University, Shanghai 200240, China;
3. Department of Materials Science and Engineering, Southern University of Science and Technology, Shenzhen 518055, China

Received date: 2018-05-15

Revised date: 2018-06-19

Online published: 2018-07-27

Fold

摘要

材料基因工程的工作模式，可大致总结为实验驱动、计算驱动和数据驱动3种。以"数据+人工智能"为标志的数据驱动模式围绕数据产生与数据处理展开，代表了材料基因工程的核心理念与发展方向。材料研究由"试错法"向科学第四范式的根本转变，将更快、更准、更省地获得成分-结构-工艺-性能间的关系。在数据密集型科学时代，快速获取大量材料数据的能力成为关键，而基于高通量实验与高通量计算的"数据工厂"是满足材料基因工程数据需求的重要平台。

关键词： 材料基因工程; 数据驱动; 高通量实验; 高通量计算

本文引用格式

汪洪 , 项晓东 , 张澜庭 . 数据+人工智能是材料基因工程的核心[J]. 科技导报, 2018 , 36(14) : 15 -21 . DOI: 10.3981/j.issn.1000-7857.2018.14.003

Abstract

The working models of the Materials Genomic Engineering can be roughly classified into those of the experiment-driven, the computation-driven and the data-driven. The last kind of model is consistent with the fourth paradigm of scientific approach of a fundamental change from "trial and error" to "data-intensive". Such a paradigm shift allows one to acquire the composition-structureprocess-performance relationship, as the basis for the rational design of materials, in a faster, cheaper and more accurate way. It represents the core concept and the future direction of the MGI. In this data-centric scientific era, the ability to quickly obtain a large amount of materials data becomes essential. Thus, the "data foundries"-the centralized materials data generation facilities based on high-throughput experiments and high-throughput computations are the key infrastructures for meeting the future data needs. It is contemplated that the data and the artificial intelligence will become the foundation for building the materials science of the future.

Key words： materials genome engineering; data-driven; high-throughput experiments; high-throughput computation

参考文献

[1] 汪洪, 向勇, 项晓东, 等. 材料基因组——材料研发新模式[J]. 科技导报, 2015, 33(10):13-19. Wang Hong, Xiang Yong, Xiang Xiaodong, et al. Materials genome enables research and development revolution[J]. Science & Technology Review, 2015, 33(10):13-19.
[2] National Science and Technology Council. Materials genome initiative for global competitiveness[R/OL].[2018-03-31]. https://www.mgi.gov/sites/default/files/documents/materials_genome_initiative-final.pdf.
[3] National Science and Technology Council. MGI strategic plan[R/OL].[2018-03-31]. https://www.mgi.gov/sites/default/files/documents/mgi_strategic_plan_-_dec_2014.pdf.
[4] 刘梓葵. 关于材料基因组的基本观点及展望[J]. 科学通报, 2013, 58(35):3618-3622. Liu Zikui. Perspective on materials genome[J]. Chinese Science Bulletin, 2014, 58(35):3618-3622.
[5] Green E D, Watson J D, Collins F S. Human Genome Project:Twenty-five years of big biology[J]. Nature, 2015, 526(7571):29-31.
[6] Xiang X D, Sun X, Briceño G, et al. A combinatorial approach to materials discovery[J]. Science, 1995, 268(5218):1738-1740.
[7] Xing H, Zhao B B, Wang Y J, et al. Rapid construction of FeCo-Ni composition-phase map by combinatorial materials chip approach[J]. ACS Combinatorial Science, 2018, 20:127-131.
[8] Buitrago S A, Regalado E L, Pereira T, et al. Organic chemistry, Nanomole-scale high-throughput chemistry for the synthesis of complex molecules[J]. Science, 2015, 347(6217):49-53.
[9] Perera D, Tucker J W, Brahmbhatt S, et al. A platform for automated nanomole-scale reaction screening and micromole-scale synthesis in flow[J]. Science, 2018, 359(6374):429-434.
[10] Gesmundo N J, Sauvagnat B, Curran P J, et al. Cernak, nanoscale synthesis and affinity ranking[J]. Nature, 2018, 557(7704):228-232.
[11] Ceder G,Persson K. The stuff of dreams[J]. Scientific American, 2013, 6:36-40.
[12] Allison J, Li M, Wolverton C, Su X M. Virtual aluminum castings:An industrial application of ICME[J]. JOM, 58(11):28-35.
[13] Olson G B, Kuehmann C J. Materials genomics:From CALPHAD to flight[J]. Scripta Materialia, 2014, 70(1):25-30.
[14] Mitchell T. Machine learning and data mining[J]. Communications of the ACM, 1999, 42(11):30-36.
[15] Liu Y, Zhao T L, Ju W W, et al. Materials discovery and design using machine learining[J]. Journal of Materiomics, 2017, 3(3):159-177.
[16] Raccuglia P, Elbert K C, Adler P D F, et al. Machine-learning-assisted materials discovery using failed experiments[J]. Nature, 2013, 533(7601):73-76.
[17] Xue D, Balachandran P V, Hogden J, et al. Accelerated search for materials with targeted properties by adaptive design[J]. Nature Communications, 2016, 7:11241.
[18] Xue D, Balachandran P V, Yuan R, et al. Accelerated search for BaTiO₃-based piezoelectrics with vertical morphotropic phase boundary using Bayesian learning[J]. Proceedings of the National Academy of Sciences, 2016, 113(47):13301-13306.
[19] Xue D, Yuan R, Zhou Y, et al. An informatics approach to transformation temperatures of NiTi-based shape memory alloys[J]. Acta Materialia, 2017, 125:532-541.
[20] Ren F, Ward L, Williams T, et al. Accelerated discovery of metallic glasses through iteration of machine learning and high-throughput experiments[J]. Science Advances, 2018, 4:eaaq1566.
[21] Segler M H S, Preuss M, Waller M P. Planning chemical syntheses with deep neural networks and symbolic AI[J]. Nature, 2018, 555(7698):604.
[22] Mueller T, Kusne A G, Ramprasad R. Machine learning in materials science:Recent progress and emerging aplications[M]//ParrillKenny A L, Lipkowitz B. Reviews in Computational Chemistry. Hoboken:John Wiley & Sons, Inc, 2016:186-273.
[23] Hey T, Tansley S, Tolle K. 第四范式:数据密集型科学发现[M].潘教峰, 张晓林, 译. 北京:科学出版社, 2012. Hey T, Tansley S, Tolle K. The fourth paradigm:Data-intensive scientific discovery microsoft research[M]. Pan Jiaofeng, Zhang Xiaolin, trans. Beijing:Science Press, 2012.
[24] Bell G, Hey T, Alex S. Beyond the data deluge[J]. Science, 2009, 323(5919):1297-1298.
[25] The large synoptic survey telescope[EB/OL].[2018-05-01]. https://www.lsst.org/lsst.
[26] 郭守敬望远镜(LAMOST,大天区面积多目标光纤光谱天文望远镜)[EB/OL].[2013-04-26]. http://www.lamost.org/public/survey. Guo Shoujing Telescope (LAMOST, large sky area multitarget fiber spectral astronomical telescope)[2013-04-26]. http://www.lamost.org/public/survey.
[27] GenBank[EB/OL].[2018-03-31]. https://en.wikipedia.org/wiki/GenBank.
[28] Materials data facility[EB/OL].[2018-03-31]. https://www.materialsdatafacility.org.
[29] Pauling file[EB/OL].[2018-03-31] http://paulingfile.com.
[30] Granta design[EB/OL].[2018-03-31] http://www.grantadesign.com.
[31] NIMS Materials Database (MatNavi)[EB/OL].[2014-12-11]. http://mits.nims.go.jp/index_en.html.
[32] 国家材料环境腐蚀平台数据共享服务[EB/OL].[2018-03-31]. http://www.ecorr.org/pingtai/.
[33] 国家材料科学数据共享网[EB/OL].[2018-03-31] http://matsec.ustb.edu.cn/index.jsp.
[34] Wilkinson M D, Dumontier M, Aalbersberg I J, et al. The FAIR guiding principles for scientific data management and stewardship[J]. Scientific Data, 2016(3):167-172.
[35] Building a materials data infrastructure:Opening new pathways to discovery and innovation in science and engineering[EB/OL].[2018-03-31]. http://www.tms.org/Publications/Studies/Materials_Data_Infrastructure/Materials_Data_Infrastructure.aspx?hkey=d228f86c-e269-49a2-a638-395285b760e4.
[36] 中华人民共和国国家质量监督检查检疫总局, 中国国家标准化管理委员会. GB/T 32843-2016科技资源标识[S]. 北京:中国标准出版社, 2016. General Administration of Quality Supervision, Inspection and Quaranitne of People's Republic of China, China National Standardization Management Committee. GB/T 32843-2016 Identification of scientific and technological resources[M]. Beijing:China Standard Press, 2016.
[37] Puchala B, Tarcea G, Marquis E A, et al. The materials commons:A collaboration platform and information repository for the global materials community[J]. JOM, 2016, 68(8):2035-2044.
[38] Dima A, Bhaskarla S, Becker C, et al. Informatics infrastructure for the materials genome initiative[J]. JOM, 2016, 68(8):2053-2064.
[39] Michel K, Meredig B. Beyond bulk single crystals:A data format for all materials structure-property-processing relationships[J]. MRS Bulletin, 2016, 41(8):617-623.
[40] DeepMind wants to find the next miracle material-experts just don't know how they'll pull it off[EB/OL].[2017-10-25]. https://qz.com/1110469/if-deepmind-is-going-to-find-thenext-miracle-material-experts-dont-know-how-theyll-pullit-off.
[41] Citrine informatics Inc[EB/OL].[2018-04-09]. https://citrine.io/news.

Options

文章导航

摘要

本文引用格式

Abstract

参考文献

联系我们

访问统计

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献

联系我们

访问统计