Uncovering material deformations via machine learning combined with four-dimensional scanning transmission electron microscopy

作     者：Chuqiao Shi Michael C.Cao Sarah M.Rehn Sang-Hoon Bae Jeehwan Kim Matthew RJones David A.Muller Yimo Han 

作者机构：Department of Materials Science and NanoEngineeringRice UniversityHoustonTXUSA School of Applied and Engineering PhysicsCornell UniversityIthacaNYUSA Department of ChemistryRice UniversityHoustonTXUSA Department of Mechanical Engineering and Materials ScienceWashington University in Saint LouisSaint LouisMOUSA Institute of Materials Science and EngineeringWashington University in Saint LouisSaint LouisMOUSA Department of Mechanical EngineeringMassachusetts Institute of TechnologyCambridgeMAUSA Kavli Institute for Nanoscale ScienceCornell UniversityIthacaNYUSA 

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：1072-1080页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 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] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：C.S.and Y.H.are supported by start-up funds provided by Rice University.Y.H.acknowledges the support from the Welch Foundation(C-2065-20210327) M.C.and D.A.M are supported by the NSF MRSEC program(DMR-1719875) S.M.R.would like to acknowledge financial support from a National Science Foundation Graduate Research Fellowship(No.1842494) 

主　　题：utilize purely overcome 

摘      要：Understanding lattice deformations is crucial in determining the properties of nanomaterials,which can become more prominent in future applications ranging from energy harvesting to electronic ***,it remains challenging to reveal unexpected deformations that crucially affect material properties across a large sample ***,we demonstrate a rapid and semi-automated unsupervised machine learning approach to uncover lattice deformations in *** method utilizes divisive hierarchical clustering to automatically unveil multi-scale deformations in the entire sample flake from the diffraction data using four-dimensional scanning transmission electron microscopy(4D-STEM).Our approach overcomes the current barriers of large 4D data analysis without a priori knowledge of the *** this purely data-driven analysis,we have uncovered different types of material deformations,such as strain,lattice distortion,bending contour,etc.,which can significantly impact the band structure and subsequent performance of nanomaterials-based *** envision that this data-driven procedure will provide insight into materials’intrinsic structures and accelerate the discovery of materials.