应用机器学习加速新材料的研发

被引:15
作者
吴炜 [1 ,2 ]
孙强 [1 ,2 ]
机构
[1] 北京大学工学院材料系
[2] 北京大学应用物理与技术研究中心
关键词
新材料; 机器学习; 材料计算模拟;
D O I
暂无
中图分类号
TB305 [材料重量计算]; TP181 [自动推理、机器学习];
学科分类号
摘要
材料不仅是国民经济的基础,而且也是高新技术的载体.超越常规手段、应用新方法加速新材料的研发已成为全世界的研究热点.随着数据驱动方法取得的巨大成功,机器学习受到了日益高度的关注.它结合计算机科学、数据库理论、统计学、计算数学和工程学,不仅能展现出更快的计算速度和可靠的预测能力,大幅度提升材料计算效率,而且还能有效地处理一些难以运用传统模拟计算方法解决的体系和问题,这为研发具有特殊功能和特殊结构的新材料以满足日益提升的新技术的要求提供了契机.本文将简要概述机器学习的基本原理,介绍机器学习模型中的几种典型算法以及机器学习在新材料研究中的应用进展,并对机器学习在材料科学领域中的未来的发展前景做出展望.
引用
收藏
页码:58 / 70
页数:13
相关论文
共 37 条
  • [1] 数据挖掘:概念与技术[M]. 机械工业出版社 , (美) 韩家炜等, 2006
  • [2] Jumping NLP Curves: A Review of Natural Language Processing Research
    Cambria, Erik
    White, Bebo
    [J]. IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE, 2014, 9 (02) : 48 - 57
  • [3] Use machine learning to find energy materials
    De Luna, Phil
    Wei, Jennifer
    Bengio, Yoshua
    Aspuru-Guzik, Alan
    Sargent, Edward
    [J]. NATURE, 2017, 552 (7683) : 23 - 25
  • [4] Machine-Learning Methods Enable Exhaustive Searches for Active Bimetallic Facets and Reveal Active Site Motifs for CO2 Reduction
    Ulissi, Zachary W.
    Tang, Michael T.
    Xiao, Jianping
    Liu, Xinyan
    Torelli, Daniel A.
    Karamad, Mohammadreza
    Cummins, Kyle
    Hahn, Christopher
    Lewis, Nathan S.
    Jaramillo, Thomas F.
    Chan, Karen
    Norskov, Jens K.
    [J]. ACS CATALYSIS, 2017, 7 (10): : 6600 - 6608
  • [5] Machine learning and genetic algorithm prediction of energy differences between electronic calculations of graphene nanoflakes
    Fernandez, Michael
    Bilic, Ante
    Barnard, Amanda S.
    [J]. NANOTECHNOLOGY, 2017, 28 (38)
  • [6] Including crystal structure attributes in machine learning models of formation energies via Voronoi tessellations
    Ward, Logan
    Liu, Ruoqian
    Krishna, Amar
    Hegde, Vinay I.
    Agrawal, Ankit
    Choudhary, Alok
    Wolverton, Chris
    [J]. PHYSICAL REVIEW B, 2017, 96 (02)
  • [7] Deep learning for computational chemistry
    Goh, Garrett B.
    Hodas, Nathan O.
    Vishnu, Abhinav
    [J]. JOURNAL OF COMPUTATIONAL CHEMISTRY, 2017, 38 (16) : 1291 - 1307
  • [8] Material synthesis and design from first principle calculations and machine learning[J] . Keisuke Takahashi,Yuzuru Tanaka.Computational Materials Science . 2016
  • [9] A structural approach to relaxation in glassy liquids[J] . S. S. Schoenholz,E. D. Cubuk,D. M. Sussman,E. Kaxiras,A. J. Liu.Nature Physics . 2016 (5)
  • [10] Machine-learning-assisted materials discovery using failed experiments
    Raccuglia, Paul
    Elbert, Katherine C.
    Adler, Philip D. F.
    Falk, Casey
    Wenny, Malia B.
    Mollo, Aurelio
    Zeller, Matthias
    Friedler, Sorelle A.
    Schrier, Joshua
    Norquist, Alexander J.
    [J]. NATURE, 2016, 533 (7601) : 73 - +