Leveraging generative adversarial networks to create realistic scanning transmission electron microscopy images  

作　　者：Abid Khan Chia-Hao Lee Pinshane Y.Huang Bryan K.Clark 

机构地区：[1]Department of Physics,University of Illinois Urbana-Champaign,Urbana,IL 61801,USA [2]Department of Materials Science and Engineering,University of Illinois Urbana-Champaign,Urbana,IL 61801,USA [3]Materials Research Laboratory,University of Illinois Urbana-Champaign,Urbana,IL 61801,USA [4]Institute for Condensed Matter Theory and IQUIST and NCSA Center for Artificial Intelligence Innovation,University of Illinois Urbana-Champaign,Urbana,IL 61801,USA

出　　处：《npj Computational Materials》2023年第1期1492-1500,共9页计算材料学（英文）

基　　金：This work was carried out in part in the Materials Research Laboratory Central Facilities at the University of Illinois Urbana-Champaign;This research is also part of the Delta research computing project,which is supported by the National Science Foundation(award OCI 2005572),and the State of Illinois.Delta is a joint effort of the University of Illinois Urbana-Champaign and its National Center for Super-computing Applications.

摘　　要：The rise of automation and machine learning(ML)in electron microscopy has the potential to revolutionize materials research through autonomous data collection and processing.A significant challenge lies in developing ML models that rapidly generalize to large data sets under varying experimental conditions.We address this by employing a cycle generative adversarial network(CycleGAN)with a reciprocal space discriminator,which augments simulated data with realistic spatial frequency information.This allows the CycleGAN to generate images nearly indistinguishable from real data and provide labels for ML applications.We showcase our approach by training a fully convolutional network(FCN)to identify single atom defects in a 4.5 million atom data set,collected using automated acquisition in an aberration-corrected scanning transmission electron microscope(STEM).Our method produces adaptable FCNs that can adjust to dynamically changing experimental variables with minimal intervention,marking a crucial step towards fully autonomous harnessing of microscopy big data.

关 键 词：autonomous ADJUST network 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]