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

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

doi:10.1038/s41524-024-01208-7

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

Journal Article · 28 January 2024 · npj Computational Materials

DOI: https://doi.org/10.1038/s41524-024-01208-7 · OSTI ID:2283107

;

; Diao, Jiecheng; Liu, Jialun;

; Boesenberg, Ulrike; Lu, Wei;

;

; Assefa, Tadesse;

; Cao, Yue;

; Sheyfer, Dina;

; Marks, Samuel D.;

Abstract 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.

View Journal Article

Cite

Export

Save

Research Organization:: Argonne National Laboratory (ANL), Argonne, IL (United States); Brookhaven National Laboratory (BNL), Upton, NY (United States); Univ. of Wisconsin, Madison, WI (United States)

Sponsoring Organization:: Gordon and Betty Moore Foundation (GBMF); National Science Foundation (NSF); USDOE; USDOE Office of Science (SC), Basic Energy Sciences (BES). Materials Sciences & Engineering Division (MSE)

Grant/Contract Number:: AC02-06CH11357; FG02-04ER46147; SC0012704

OSTI ID:: 2283107

Report Number(s):: BNL--225260-2024-JAAM; 24; PII: 1208

Journal Information:: npj Computational Materials, Journal Name: npj Computational Materials Journal Issue: 1 Vol. 10; ISSN 2057-3960

Publisher:: Nature Publishing GroupCopyright Statement

Country of Publication:: United Kingdom

Language:: English

References (39)

U-Net: Convolutional Networks for Biomedical Image Segmentation Ronneberger, Olaf; Fischer, Philipp; Brox, Thomas Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III https://doi.org/10.1007/978-3-319-24574-4_28	book	November 2015
Phase recovery, MaxCut and complex semidefinite programming Waldspurger, Irène; d’Aspremont, Alexandre; Mallat, Stéphane Mathematical Programming, Vol. 149, Issue 1-2 https://doi.org/10.1007/s10107-013-0738-9	journal	December 2013
Domain Texture of the Orthorhombic Phase of La2−xBaxCuO4 Robinson, Ian; Assefa, Tadesse A.; Cao, Yue Journal of Superconductivity and Novel Magnetism https://doi.org/10.1007/s10948-019-05252-z	journal	August 2019
Analytical theory of intensity fluctuations in SASE Hua Yu, Li; Krinsky, S. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 407, Issue 1-3 https://doi.org/10.1016/S0168-9002(98)00032-1	journal	April 1998
A New Microscopic Principle Gabor, D. Nature, Vol. 161, Issue 4098 https://doi.org/10.1038/161777a0	journal	May 1948
Extending the methodology of X-ray crystallography to allow imaging of micrometre-sized non-crystalline specimens Miao, Jianwei; Charalambous, Pambos; Kirz, Janos Nature, Vol. 400, Issue 6742 https://doi.org/10.1038/22498	journal	July 1999
Phase recovery and holographic image reconstruction using deep learning in neural networks Rivenson, Yair; Zhang, Yibo; Günaydın, Harun Light: Science & Applications, Vol. 7, Issue 2 https://doi.org/10.1038/lsa.2017.141	journal	October 2017
Spontaneous breaking of rotational symmetry in copper oxide superconductors Wu, J.; Bollinger, A. T.; He, X. Nature, Vol. 547, Issue 7664 https://doi.org/10.1038/nature23290	journal	July 2017
Conduction at domain walls in oxide multiferroics Seidel, J.; Martin, L. W.; He, Q. Nature Materials, Vol. 8, Issue 3 https://doi.org/10.1038/nmat2373	journal	January 2009
Stress breaks universal aging behavior in a metallic glass Das, Amlan; Derlet, Peter M.; Liu, Chaoyang Nature Communications, Vol. 10, Issue 1 https://doi.org/10.1038/s41467-019-12892-1	journal	November 2019
Three-dimensional coherent X-ray diffraction imaging via deep convolutional neural networks Wu, Longlong; Yoo, Shinjae; Suzana, Ana F. npj Computational Materials, Vol. 7, Issue 1 https://doi.org/10.1038/s41524-021-00644-z	journal	October 2021
AutoPhaseNN: unsupervised physics-aware deep learning of 3D nanoscale Bragg coherent diffraction imaging Yao, Yudong; Chan, Henry; Sankaranarayanan, Subramanian npj Computational Materials, Vol. 8, Issue 1 https://doi.org/10.1038/s41524-022-00803-w	journal	June 2022
Real-time coherent diffraction inversion using deep generative networks Cherukara, Mathew J.; Nashed, Youssef S. G.; Harder, Ross J. Scientific Reports, Vol. 8, Issue 1 https://doi.org/10.1038/s41598-018-34525-1	journal	November 2018
AI-enabled high-resolution scanning coherent diffraction imaging Cherukara, Mathew J.; Zhou, Tao; Nashed, Youssef Applied Physics Letters, Vol. 117, Issue 4 https://doi.org/10.1063/5.0013065	journal	July 2020
X-ray diffraction from low-dimensional structures Fewster, P. F. Semiconductor Science and Technology, Vol. 8, Issue 11 https://doi.org/10.1088/0268-1242/8/11/001	journal	November 1993
Electrical-Resistivity Model for Polycrystalline Films: the Case of Arbitrary Reflection at External Surfaces Mayadas, A. F.; Shatzkes, M. Physical Review B, Vol. 1, Issue 4 https://doi.org/10.1103/PhysRevB.1.1382	journal	February 1970
X-Ray Intensity Fluctuation Spectroscopy Observations of Critical Dynamics in Fe3Al Brauer, S.; Stephenson, G.; Sutton, M. Physical Review Letters, Vol. 74, Issue 11 https://doi.org/10.1103/PhysRevLett.74.2010	journal	March 1995
Movable Aperture Lensless Transmission Microscopy: A Novel Phase Retrieval Algorithm Faulkner, H. M. L.; Rodenburg, J. M. Physical Review Letters, Vol. 93, Issue 2 https://doi.org/10.1103/PhysRevLett.93.023903	journal	July 2004
Domain fluctuations in a ferroelectric low-strain BaTiO 3 thin film Li, Jianheng; Zhong, Louie; Jangid, Rahul Physical Review Materials, Vol. 4, Issue 11 https://doi.org/10.1103/PhysRevMaterials.4.114409	journal	November 2020
Domain wall nanoelectronics Catalan, G.; Seidel, J.; Ramesh, R. Reviews of Modern Physics, Vol. 84, Issue 1 https://doi.org/10.1103/RevModPhys.84.119	journal	February 2012
Materials Imaging and Dynamics (MID) instrument at the European X-ray Free-Electron Laser Facility Madsen, A.; Hallmann, J.; Ansaldi, G. Journal of Synchrotron Radiation, Vol. 28, Issue 2 https://doi.org/10.1107/S1600577521001302	journal	February 2021
Complex imaging of phase domains by deep neural networks Wu, Longlong; Juhas, Pavol; Yoo, Shinjae IUCrJ, Vol. 8, Issue 1 https://doi.org/10.1107/S2052252520013780	journal	January 2021
Deep Ptych: Subsampled Fourier Ptychography Using Generative Priors Shamshad, Fahad; Abbas, Farwa; Ahmed, Ali ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) https://doi.org/10.1109/ICASSP.2019.8682179	conference	May 2019
Ptychnet: CNN based fourier ptychography Kappeler, Armin; Ghosh, Sushobhan; Holloway, Jason 2017 IEEE International Conference on Image Processing (ICIP) https://doi.org/10.1109/ICIP.2017.8296574	conference	September 2017
Phase Retrieval via Wirtinger Flow: Theory and Algorithms Candes, Emmanuel J.; Li, Xiaodong; Soltanolkotabi, Mahdi IEEE Transactions on Information Theory, Vol. 61, Issue 4 https://doi.org/10.1109/TIT.2015.2399924	journal	April 2015
PhaseMax: Convex Phase Retrieval via Basis Pursuit Goldstein, Tom; Studer, Christoph IEEE Transactions on Information Theory, Vol. 64, Issue 4 https://doi.org/10.1109/TIT.2018.2800768	journal	April 2018
DOLPHIn—Dictionary Learning for Phase Retrieval Tillmann, Andreas M.; Eldar, Yonina C.; Mairal, Julien IEEE Transactions on Signal Processing, Vol. 64, Issue 24 https://doi.org/10.1109/TSP.2016.2607180	journal	December 2016
Phase Retrieval via Matrix Completion Candès, Emmanuel J.; Eldar, Yonina C.; Strohmer, Thomas SIAM Review, Vol. 57, Issue 2 https://doi.org/10.1137/151005099	journal	January 2015
Incommensurate Lattice Distortion in the High Temperature Tetragonal Phase of La _{2- x} (Sr,Ba) _x CuO ₄ Wakimoto, Shuichi; Kimura, Hiroyuki; Fujita, Masaki Journal of the Physical Society of Japan, Vol. 75, Issue 7 https://doi.org/10.1143/JPSJ.75.074714	journal	July 2006
Grain Growth in Thin Films Thompson, C. V. Annual Review of Materials Science, Vol. 20, Issue 1 https://doi.org/10.1146/annurev.ms.20.080190.001333	journal	August 1990
Phase retrieval algorithms: a comparison Fienup, J. R. Applied Optics, Vol. 21, Issue 15 https://doi.org/10.1364/AO.21.002758	journal	January 1982
Schulz-Snyder Phase Retrieval Algorithm as an Alternating Minimization Algorithm Oktem, Figen S.; Blahut, Richard E. Imaging and Applied Optics https://doi.org/10.1364/COSI.2011.CMC3	conference	January 2011
Phase retrieval via spatial light modulator phase modulation in 4f optical setup: numerical inverse imaging with sparse regularization for phase and amplitude Katkovnik, Vladimir; Astola, Jaakko Journal of the Optical Society of America A, Vol. 29, Issue 1 https://doi.org/10.1364/JOSAA.29.000105	journal	December 2011
Ptychographic characterisation of polymer compound refractive lenses manufactured by additive technology Lyubomirskiy, M.; Koch, F.; Abrashitova, K. A. Optics Express, Vol. 27, Issue 6 https://doi.org/10.1364/OE.27.008639	journal	January 2019
Deep neural networks in single-shot ptychography Wengrowicz, Omri; Peleg, Or; Zahavy, Tom Optics Express, Vol. 28, Issue 12 https://doi.org/10.1364/OE.393961	journal	January 2020
Recovering the phase and amplitude of X-ray FEL pulses using neural networks and differentiable models Ratner, D.; Christie, F.; Cryan, J. P. Optics Express, Vol. 29, Issue 13 https://doi.org/10.1364/OE.432488	journal	January 2021
Reconstruction of an object from the modulus of its Fourier transform Fienup, J. R. Optics Letters, Vol. 3, Issue 1, p. 27-29 https://doi.org/10.1364/OL.3.000027	journal	January 1978
Lensless computational imaging through deep learning Sinha, Ayan; Lee, Justin; Li, Shuai Optica, Vol. 4, Issue 9 https://doi.org/10.1364/OPTICA.4.001117	journal	January 2017
Adam: A Method for Stochastic Optimization Kingma, Diederik P.; Ba, Jimmy arXiv https://doi.org/10.48550/arXiv.1412.6980	preprint	January 2014

Similar Records

Exploring Physics of Ferroelectric Domain Walls in Real Time: Deep Learning Enabled Scanning Probe Microscopy

Journal Article · 2022 · Advanced Science · OSTI ID:1885605

Liu, Yongtao; Kelley, Kyle P.; Funakubo, Hiroshi; +2 more

Complex imaging of phase domains by deep neural networks

Journal Article · 2020 · IUCrJ · OSTI ID:1712507

Wu, Longlong; Juhas, Pavol; Yoo, Shinjae; +1 more

Deep Learning with Reflection High-Energy Electron Diffraction Images to Predict Cation Ratio in Sr_2xTi_2(1–x)O₃ Thin Films

Journal Article · 2025 · Nano Letters · OSTI ID:2573380

Harris, Sumner B.; Gemperline, Patrick T.; Rouleau, Christopher M.; +2 more

Related Subjects

77 NANOSCIENCE AND NANOTECHNOLOGY

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

Citation Formats

References (39)

Similar Records

Related Subjects