Automatic identification of crystal structures and interfaces via artificial-intelligence-based electron microscopy

作     者：Andreas Leitherer Byung Chul Yeo Christian H.Liebscher Luca M.Ghiringhelli 

作者机构：The NOMAD Laboratory at the Fritz-Haber-Institut of the Max-Planck-Gesellschaft and IRIS-Adlershof of the Humboldt-Universität zu BerlinBerlinGermany Department of Energy Resources EngineeringPukyong National UniversityBusan 48513Republic of Korea Max-Planck-Institut für Eisenforschung40237 DüsseldorfGermany Physics Department and IRIS AdlershofHumboldt-Universität zu BerlinBerlinGermany Present address:Department of Materials Science and EngineeringFriedrich-Alexander Universität Erlangen-NürnbergErlangenGermany 

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

年 卷 期：2023年第9卷第1期

页      面：489-499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：L.M.G.acknowledges funding from the European Union’s Horizon 2020 research and innovation program,under grant agreements No.951786(NOMAD CoE)and No.740233(TEC1p) Furthermore,the authors acknowledge the Max Planck Computing and Data facility(MPCDF)for computational resources and support,which enabled neural-network training on 1 GPU(Tesla Volta V10032GB)on the Talos machine learning cluster B.C.Y.acknowledges funding from the National Research Foundation(NRF)of Korea under Project Number 2021M3A7C2090586 

主　　题：materials crystal estimates 

摘      要：Characterizing crystal structures and interfaces down to the atomic level is an important step for designing advanced *** electron microscopy routinely achieves atomic resolution and is capable to resolve complex arrangements of atoms with picometer ***,we present AI-STEM,an automatic,artificial-intelligence based method,for accurately identifying key characteristics from atomic-resolution scanning transmission electron microscopy(STEM)images of polycrystalline *** method is based on a Bayesian convolutional neural network(BNN)that is trained only on simulated ***-STEM automatically and accurately identifies crystal structure,lattice orientation,and location of interface regions in synthetic and experimental *** model is trained on cubic and hexagonal crystal structures,yielding classifications and uncertainty estimates,while no explicit information on structural patterns at the interfaces is included during *** work combines principles from probabilistic modeling,deep learning,and information theory,enabling automatic analysis of experimental,atomic-resolution images.