中国物理B ›› 2020, Vol. 29 ›› Issue (11): 116103-.doi: 10.1088/1674-1056/abc0e3

所属专题: SPECIAL TOPIC — Machine learning in condensed matter physics

• • 上一篇    下一篇

Zhilong Song(宋志龙)1, Xiwen Chen(陈曦雯)1, Fanbin Meng(孟繁斌)1, Guanjian Cheng(程观剑)1, Chen Wang(王陈)1, Zhongti Sun(孙中体)1,†(), Wan-Jian Yin(尹万健)1,()   

  • 收稿日期:2020-07-06 修回日期:2020-08-24 接受日期:2020-10-14 出版日期:2020-11-05 发布日期:2020-11-03

Machine learning in materials design: Algorithm and application

Zhilong Song(宋志龙), Xiwen Chen(陈曦雯), Fanbin Meng(孟繁斌), Guanjian Cheng(程观剑), Chen Wang(王陈), Zhongti Sun(孙中体), and Wan-Jian Yin(尹万健)   

  1. College of Energy, Soochow Institute for Energy and Materials InnovationS (SIEMIS), and Jiangsu Provincial Key Laboratory for Advanced Carbon Materials and Wearable Energy Technologies, Soochow University, Suzhou 215006, China
  • Received:2020-07-06 Revised:2020-08-24 Accepted:2020-10-14 Online:2020-11-05 Published:2020-11-03
  • Contact: Corresponding author. E-mail: ztsun@suda.edu.cn Corresponding author. E-mail: wjyin@suda.edu.cn
  • Supported by:
    Project support by the National Natural Science Foundation of China (Grant Nos. 11674237 and 51602211), the National Key Research and Development Program of China (Grant No. 2016YFB0700700), the Priority Academic Program Development of Jiangsu Higher Education Institutions (PAPD), China, and China Post-doctoral Foundation (Grant No. 7131705619).

Abstract:

Traditional materials discovery is in ‘trial-and-error’ mode, leading to the issues of low-efficiency, high-cost, and unsustainability in materials design. Meanwhile, numerous experimental and computational trials accumulate enormous quantities of data with multi-dimensionality and complexity, which might bury critical ‘structure–properties’ rules yet unfortunately not well explored. Machine learning (ML), as a burgeoning approach in materials science, may dig out the hidden structure–properties relationship from materials bigdata, therefore, has recently garnered much attention in materials science. In this review, we try to shortly summarize recent research progress in this field, following the ML paradigm: (i) data acquisition → (ii) feature engineering → (iii) algorithm → (iv) ML model → (v) model evaluation → (vi) application. In section of application, we summarize recent work by following the ‘material science tetrahedron’: (i) structure and composition → (ii) property → (iii) synthesis → (iv) characterization, in order to reveal the quantitative structure–property relationship and provide inverse design countermeasures. In addition, the concurrent challenges encompassing data quality and quantity, model interpretability and generalizability, have also been discussed. This review intends to provide a preliminary overview of ML from basic algorithms to applications.

Key words: machine learning, materials design, structure-property relationship, active learning