Recent advances and applications of deep learning methods in materials science

被引:442
作者
Choudhary, Kamal [1 ,2 ,3 ]
DeCost, Brian [4 ]
Chen, Chi [5 ]
Jain, Anubhav [6 ]
Tavazza, Francesca [1 ]
Cohn, Ryan [7 ]
Park, Cheol Woo [8 ]
Choudhary, Alok [9 ]
Agrawal, Ankit [9 ]
Billinge, Simon J. L. [10 ,11 ]
Holm, Elizabeth [7 ]
Ong, Shyue Ping [5 ]
Wolverton, Chris [8 ]
机构
[1] NIST, Mat Sci & Engn Div, Gaithersburg, MD 20899 USA
[2] Theiss Res, La Jolla, CA 92037 USA
[3] DeepMaterials LLC, Silver Spring, MD 20906 USA
[4] NIST, Mat Measurement Sci Div, Gaithersburg, MD 20899 USA
[5] Univ Calif San Diego, Dept NanoEngn, San Diego, CA 92093 USA
[6] Lawrence Berkeley Natl Lab, Energy Technol Area, Berkeley, CA USA
[7] Carnegie Mellon Univ, Dept Mat Sci & Engn, Pittsburgh, PA 15213 USA
[8] Northwestern Univ, Dept Mat Sci & Engn, Evanston, IL 60208 USA
[9] Northwestern Univ, Dept Elect & Comp Engn, Evanston, IL 60208 USA
[10] Columbia Univ, Sch Engn & Appl Sci, Fu Fdn, Dept Appl Phys, New York, NY 10027 USA
[11] Columbia Univ, Sch Engn & Appl Sci, Fu Fdn, Appl Math & Data Sci Inst, New York, NY 10027 USA
基金
美国国家科学基金会;
关键词
CONVOLUTIONAL NEURAL-NETWORKS; STRUCTURE-PROPERTY LINKAGES; HIGH-CONTRAST COMPOSITES; QUANTITATIVE-ANALYSIS; RAMAN-SPECTROSCOPY; INFRARED-SPECTRA; WORD EMBEDDINGS; OPEN DATABASE; MACHINE; CHEMISTRY;
D O I
10.1038/s41524-022-00734-6
中图分类号
O64 [物理化学(理论化学)、化学物理学];
学科分类号
070304 ; 081704 ;
摘要
Deep learning (DL) is one of the fastest-growing topics in materials data science, with rapidly emerging applications spanning atomistic, image-based, spectral, and textual data modalities. DL allows analysis of unstructured data and automated identification of features. The recent development of large materials databases has fueled the application of DL methods in atomistic prediction in particular. In contrast, advances in image and spectral data have largely leveraged synthetic data enabled by high-quality forward models as well as by generative unsupervised DL methods. In this article, we present a high-level overview of deep learning methods followed by a detailed discussion of recent developments of deep learning in atomistic simulation, materials imaging, spectral analysis, and natural language processing. For each modality we discuss applications involving both theoretical and experimental data, typical modeling approaches with their strengths and limitations, and relevant publicly available software and datasets. We conclude the review with a discussion of recent cross-cutting work related to uncertainty quantification in this field and a brief perspective on limitations, challenges, and potential growth areas for DL methods in materials science.
引用
收藏
页数:26
相关论文
共 371 条
[1]  
Abadi, 2006, ARXIV160508695
[2]   A review of uncertainty quantification in deep learning: Techniques, applications and challenges [J].
Abdar, Moloud ;
Pourpanah, Farhad ;
Hussain, Sadiq ;
Rezazadegan, Dana ;
Liu, Li ;
Ghavamzadeh, Mohammad ;
Fieguth, Paul ;
Cao, Xiaochun ;
Khosravi, Abbas ;
Acharya, U. Rajendra ;
Makarenkov, Vladimir ;
Nahavandi, Saeid .
INFORMATION FUSION, 2021, 76 :243-297
[3]   Convolutional neural networks for vibrational spectroscopic data analysis [J].
Acquarelli, Jacopo ;
van Laarhoven, Twan ;
Gerretzen, Jan ;
Tran, Thanh N. ;
Buydens, Lutgarde M. C. ;
Marchiori, Elena .
ANALYTICA CHIMICA ACTA, 2017, 954 :22-31
[4]   Martensite Start Temperature Predictor for Steels Using Ensemble Data Mining [J].
Agrawal, Ankit ;
Saboo, Abhinav ;
Xiong, Wei ;
Olson, Greg ;
Choudhary, Alok .
2019 IEEE INTERNATIONAL CONFERENCE ON DATA SCIENCE AND ADVANCED ANALYTICS (DSAA 2019), 2019, :521-530
[5]   Deep materials informatics: Applications of deep learning in materials science [J].
Agrawal, Ankit ;
Choudhary, Alok .
MRS COMMUNICATIONS, 2019, 9 (03) :779-792
[6]   An online tool for predicting fatigue strength of steel alloys based on ensemble data mining [J].
Agrawal, Ankit ;
Choudhary, Alok .
INTERNATIONAL JOURNAL OF FATIGUE, 2018, 113 :389-400
[7]  
Agrawal A, 2016, INT CONF DAT MIN WOR, P1276, DOI [10.1109/ICDMW.2016.183, 10.1109/ICDMW.2016.0183]
[8]   A Fatigue Strength Predictor for Steels Using Ensemble Data Mining [J].
Agrawal, Ankit ;
Choudhary, Alok .
CIKM'16: PROCEEDINGS OF THE 2016 ACM CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, 2016, :2497-2500
[9]   Perspective: Materials informatics and big data: Realization of the "fourth paradigm" of science in materials science [J].
Agrawal, Ankit ;
Choudhary, Alok .
APL MATERIALS, 2016, 4 (05)
[10]   Exploration of data science techniques to predict fatigue strength of steel from composition and processing parameters [J].
Agrawal A. ;
Deshpande P.D. ;
Cecen A. ;
Basavarsu G.P. ;
Choudhary A.N. ;
Kalidindi S.R. .
Integrating Materials and Manufacturing Innovation, 2014, 3 (1) :90-108