Recent advances and applications of deep learning methods in materials science

作     者：Kamal Choudhary Brian DeCost Chi Chen Anubhav Jain Francesca Tavazza Ryan Cohn Cheol Woo Park Alok Choudhary Ankit Agrawal Simon J.L.Billinge Elizabeth Holm Shyue Ping Ong Chris Wolverton 

作者机构：Materials Science and Engineering DivisionNational Institute of Standards and TechnologyGaithersburgMD20899USA Theiss ResearchLa JollaCA92037USA DeepMaterials LLCSilver SpringMD20906USA Material Measurement Science DivisionNational Institute of Standards and TechnologyGaithersburgMD20899USA Department of NanoEngineeringUniversity of California San DiegoSan DiegoCA92093USA Energy Technologies AreaLawrence Berkeley National LaboratoryBerkeleyCAUSA Department of Materials Science and EngineeringCarnegie Mellon UniversityPittsburghPA15213USA Department of Materials Science and EngineeringNorthwestern UniversityEvanstonIL60208USA Department of Electrical and Computer EngineeringNorthwestern UniversityEvanstonIL60208USA Department of Applied Physics and Applied Mathematics and the Data Science InstituteFu Foundation School of Engineering and Applied SciencesColumbia UniversityNew YorkNY10027USA 

出 版 物：《npj Computational Materials》 (计算材料学（英文）)

年 卷 期：2022年第8卷第1期

页      面：548-573页

核心收录：

学科分类：08[工学] 0805[工学-材料科学与工程（可授工学、理学学位）] 080502[工学-材料学] 

基　　金：Contributions from K.C.were supported by the financial assistance award 70NANB19H117 from the U.S.Department of Commerce National Institute of Standards and Technology E.A.H.and R.C.(CMU)were supported by the National Science Foundation under grant CMMI-1826218 the Air Force D3OM2S Center of Excellence under agreement FA8650-19-2-5209 A.J.,C.C.,and S.P.O.were supported by the Materials Project,funded by the U.S.Department of Energy,Office of Science,Office of Basic Energy Sciences,Materials Sciences and Engineering Division under contract no,DE-AC02-05-CH11231 Materials Project program KC23MP.S.J.L.B.was supported by the U.S.National Science Foundation through grant DMREF-1922234 A.A.and A.C.were supported by NIST award 70NANB19H005 NSF award CMMI-2053929 

主　　题：learning limitations textual 

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 *** allows analysis of unstructured data and automated identification of *** recent development of large materials databases has fueled the application of DL methods in atomistic prediction 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 *** 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 *** 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 *** 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.