Ultrafast Bragg coherent diffraction imaging of epitaxial thin films using deep complex-valued neural networks  

作　　者：Xi Yu Longlong Wu Yuewei Lin Jiecheng Diao Jialun Liu Jörg Hallmann Ulrike Boesenberg Wei Lu Johannes Möller Markus Scholz Alexey Zozulya Anders Madsen Tadesse Assefa Emil S.Bozin Yue Cao Hoydoo You Dina Sheyfer Stephan Rosenkranz Samuel D.Marks Paul G.Evans David A.Keen Xi He Ivan Božović Mark P.M.Dean Shinjae Yoo Ian K.Robinson 

机构地区：[1]Computational Science Initiative,Brookhaven National Laboratory,Upton,NY 11973,USA [2]Condensed Matter Physics and Materials Science Department,Brookhaven National Laboratory,Upton,NY 11973,USA [3]London Centre for Nanotechnology,University College London,London WC1H 0AH,UK [4]European X-Ray Free-Electron Laser Facility,Holzkoppel 4,22869 Schenefeld,Germany [5]Linac Coherent Light Source,SLAC National Accelerator Laboratory,Menlo Park,CA 94025,USA [6]Materials Science Division,Argonne National Laboratory,Lemont,IL 60439,USA [7]X-ray Science Division,Argonne National Laboratory,Lemont,IL 60439,USA [8]Department of Materials Science and Engineering,University of Wisconsin,Madison,WI 53706,USA [9]ISIS Facility,Rutherford Appleton Laboratory,Harwell Campus,Didcot,Oxfordshire OX110QX,UK [10]Department of Chemistry,Yale University,New Haven,CT 06520,USA

出　　处：《npj Computational Materials》2024年第1期3002-3010,共9页计算材料学(英文)

基　　金：supported by the U.S.Department of Energy,Office of Science,Office of Basic Energy Sciences,under Contract No.DE-SC0012704;supported by EPSRC.Work at Argonne National Laboratory was supported by the U.S.Department of Energy,Office of Science,Office of Basic Energy Sciences,Materials Science and Engineering Division;X.H.was supported by the Gordon and Betty Moore Foundation’s EPiQS Initiative through Grant No.GBMF9074;S.D.M.and P.G.E.gratefully acknowledge support from the U.S.DOE Office of Science under grant no.DE-FG02-04ER46147;from the US NSF through the University of Wisconsin Materials Research Science and Engineering Center(DMR-2309000 and DMR-1720415).

摘　　要：Domain wall structures form spontaneously due to epitaxial misfit during thin film growth.Imaging the dynamics of domains and domain walls at ultrafast timescales can provide fundamental clues to features that impact electrical transport in electronic devices.Recently,deep learning based methods showed promising phase retrieval(PR)performance,allowing intensity-only measurements to be transformed into snapshot real space images.While the Fourier imaging model involves complex-valued quantities,most existing deep learning based methods solve the PR problem with real-valued based models,where the connection between amplitude and phase is ignored.To this end,we involve complex numbers operation in the neural network to preserve the amplitude and phase connection.Therefore,we employ the complex-valued neural network for solving the PR problem and evaluate it on Bragg coherent diffraction data streams collected from an epitaxial La_(2-x)Sr_(x)CuO_(4)(LSCO)thin film using an X-ray Free Electron Laser(XFEL).Our proposed complex-valued neural network based approach outperforms the traditional real-valued neural network methods in both supervised and unsupervised learning manner.Phase domains are also observed from the LSCO thin film at an ultrafast timescale using the complex-valued neural network.

关 键 词：VALUED COHERENT EPITAXIAL 

分 类 号：O48[理学—固体物理]