pith. sign in

arxiv: 2606.27587 · v1 · pith:IJ7CNW6Cnew · submitted 2026-06-25 · ❄️ cond-mat.mtrl-sci

PtyRANNOSAUR: Ptychography with Robust Artificial Neural Networks Optimized for Sub-Angstrom Accuracy and Ultrafast Reconstruction

Kieran Loehr , Rahim Raja , Xiaochuan Ding , Jeffrey Huang , Gillian Nolan , Sang hyun Bae , Bryan K. Clark , Pinshane Y. Huang This is my paper

Pith reviewed 2026-06-29 01:15 UTC · model grok-4.3

classification ❄️ cond-mat.mtrl-sci
keywords ptychographyneural networkselectron microscopyatomic resolution4D-STEMreconstructionconvolutional autoencodersmaterials characterization
0
0 comments X

The pith

Neural networks map 4D electron microscopy data to accurate atomic phase images in seconds.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents PtyRANNOSAUR, a neural network method using convolutional autoencoders to reconstruct ptychography data from 4D-STEM experiments. It trains models on large databases of crystal structures for specific experimental conditions like voltage and thickness. This yields reconstructions that match the resolution of traditional iterative methods but run 10 to 100 times faster. The approach handles real-world complications such as partial coherence and position errors without needing extra tuning. A sympathetic reader would care because it makes high-resolution imaging of materials practical in near real time.

Core claim

PtyRANNOSAUR demonstrates that convolutional autoencoders, trained on crystal structure databases and tailored to experimental parameters, can reconstruct atomic structures from experimental and simulated ptychography data with resolutions below 0.5 angstroms, matching the best iterative methods while being substantially faster.

What carries the argument

Convolutional autoencoders that directly map 4D-scanning transmission electron microscopy data to 2D phase images.

If this is right

  • Reconstructions of atomic structures become available in seconds rather than minutes or hours.
  • High-quality results are obtained across a broad range of materials without hyperparameter adjustment.
  • The method accounts for spatial partial coherence, multiple scattering, and scan position errors.
  • Sub-angstrom resolution is achieved on both simulated and experimental datasets.
  • Near-live state-of-the-art ptychography becomes feasible for materials analysis.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Such networks could extend to other diffraction-based imaging techniques beyond electron ptychography.
  • Training databases might be expanded to include more complex or defective structures for broader applicability.
  • Integration into microscope software could allow real-time feedback during experiments.

Load-bearing premise

Models trained solely on simulated crystal structures will generalize accurately to real experimental data for a wide range of parameters.

What would settle it

An experimental dataset from a material outside the training distribution where the neural network reconstruction resolution falls significantly below 0.5 angstroms while iterative methods succeed.

Figures

Figures reproduced from arXiv: 2606.27587 by Bryan K. Clark, Gillian Nolan, Jeffrey Huang, Kieran Loehr, Pinshane Y. Huang, Rahim Raja, Sang hyun Bae, Xiaochuan Ding.

Figure 1
Figure 1. Figure 1: Experimental reconstructions using (a-d) PtyRANNOSAUR’s neural network approach and [PITH_FULL_IMAGE:figures/full_fig_p005_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Schematic for training and generating ptychography reconstructions of local patches of objects [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Neural network reconstructions from Model 10 on simulated validation materials. (a,b) SSIM [PITH_FULL_IMAGE:figures/full_fig_p008_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: PtyRANNOSAUR robust performance with parameter variations. (a-d) Reconstruction loss for [PITH_FULL_IMAGE:figures/full_fig_p009_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Stitching algorithms for combining PtyRANNOSAUR output patches into a full phase image. [PITH_FULL_IMAGE:figures/full_fig_p011_5.png] view at source ↗
read the original abstract

We present PtyRANNOSAUR, a data-driven neural network code that reconstructs atomic resolution electron ptychography data in seconds, 10-100x faster than standard methods. PtyRANNOSAUR uses convolutional autoencoders to map 4D-scanning transmission electron microscopy data to 2D phase images. Each model is trained on a large database of crystal structures and is tailored for a range of experimental parameters, such as accelerating voltage, convergence angle, defocus, and sample thickness. This approach yields high quality reconstructions without requiring any fine-tuning of hyperparameters. In addition, the code handles spatial partial coherence, multiple scattering, and scan position errors, which are critical for state-of-the-art electron ptychography reconstructions. By testing PtyRANNOSAUR on experimental and simulated data, we show that the neural networks accurately reconstruct atomic structures of a broad range of materials systems and can achieve high resolutions of $<0.5$ {\AA}, comparable to the best iterative reconstructions of the same data. These advances enable near-live, state-of-the-art electron ptychography reconstructions.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. The paper presents PtyRANNOSAUR, a data-driven neural network using convolutional autoencoders to reconstruct 2D phase images from 4D-STEM ptychography data. Models are trained on large databases of crystal structures tailored to experimental parameters (accelerating voltage, convergence angle, defocus, sample thickness). The method claims to handle spatial partial coherence, multiple scattering, and scan position errors, achieving high-quality reconstructions in seconds (10-100x faster than standard methods) with resolutions <0.5 Å on experimental and simulated data for a broad range of materials, comparable to best iterative reconstructions, without hyperparameter fine-tuning.

Significance. Should the claims be verified through detailed quantitative validation, this work has the potential to significantly impact the field by enabling ultrafast, near-live atomic-resolution ptychography. The ability to match iterative method performance while being orders of magnitude faster, and the robustness across materials and conditions, would represent a substantial advance in electron microscopy techniques for materials characterization.

major comments (1)
  1. Abstract: The central claim that networks trained exclusively on simulated crystal structures generalize to experimental 4D-STEM data at <0.5 Å resolution without fine-tuning rests on an untested extrapolation, as experimental data include unmodeled noise correlations, scan jitter, and sample imperfections not guaranteed in the training set. The abstract does not specify whether multiple scattering and partial coherence were injected with realistic experimental statistics.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their detailed review and constructive feedback. We address the major comment below and will make revisions to improve clarity.

read point-by-point responses

  1. Referee: Abstract: The central claim that networks trained exclusively on simulated crystal structures generalize to experimental 4D-STEM data at <0.5 Å resolution without fine-tuning rests on an untested extrapolation, as experimental data include unmodeled noise correlations, scan jitter, and sample imperfections not guaranteed in the training set. The abstract does not specify whether multiple scattering and partial coherence were injected with realistic experimental statistics.

    Authors: We appreciate this observation. The training simulations do incorporate multiple scattering via multislice calculations using realistic sample thicknesses and potentials, spatial partial coherence via a Gaussian probe coherence function whose width is matched to experimental source-size measurements, and scan position errors via random displacements drawn from distributions calibrated to typical experimental drift. These choices are detailed in the methods and supplementary information and are specific to each experimental parameter set. Crucially, the resulting networks were applied without retraining or hyperparameter adjustment to multiple experimental 4D-STEM datasets spanning different materials, achieving sub-0.5 Å resolution and quantitative agreement with iterative reconstructions performed on the identical data. This constitutes direct experimental validation of generalization. We nevertheless agree that the abstract would benefit from a concise statement clarifying the realistic injection of these effects; we will revise the abstract accordingly. revision: yes

Circularity Check

0 steps flagged

No circularity; performance claims benchmarked against independent iterative reconstructions

full rationale

The paper trains convolutional autoencoders on a database of simulated crystal structures (with varied voltage, convergence angle, defocus, thickness) and reports reconstruction quality via direct comparison to separate iterative ptychography results on the same experimental and simulated 4D-STEM datasets. No equation, training target, or performance metric is defined in terms of the network output itself; the <0.5 Å resolution claim and handling of multiple scattering/partial coherence are evaluated against external iterative benchmarks rather than by construction. No self-citations, ansatzes, or fitted-input-as-prediction patterns appear in the provided text.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract does not enumerate explicit free parameters, mathematical axioms, or newly postulated physical entities; the central claim rests on the unstated assumption that a finite database of simulated crystals plus fixed experimental-parameter ranges will generalize to real experimental data without per-sample retraining.

pith-pipeline@v0.9.1-grok · 5762 in / 1161 out tokens · 34247 ms · 2026-06-29T01:15:47.653673+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

114 extracted references · 82 canonical work pages

  1. [1]

    2410.17377 , archivePrefix=

    Ryuma Nakahata and Shehtab Zaman and Mingyuan Zhang and Fake Lu and Kenneth Chiu , year=. 2410.17377 , archivePrefix=

    arXiv

  2. [2]

    and Zhou, Tao and Nashed, Youssef and Enfedaque, Pablo and Hexemer, Alex and Harder, Ross J

    Cherukara, Mathew J. and Zhou, Tao and Nashed, Youssef and Enfedaque, Pablo and Hexemer, Alex and Harder, Ross J. and Holt, Martin V. , title =. Applied Physics Letters , volume =. 2020 , month =. doi:10.1063/5.0013065 , url =

    work page doi:10.1063/5.0013065 2020

  3. [3]

    and Cardona, Cristina Garcia and Kamilov, Ulugbek S

    Gan, Weijie and Zhai, Qiuchen and McCann, Michael T. and Cardona, Cristina Garcia and Kamilov, Ulugbek S. and Wohlberg, Brendt , journal=. 2024 , volume=

    2024

  4. [4]

    Deep-Learning Electron Diffractive Imaging , author =. Phys. Rev. Lett. , volume =. 2023 , month =. doi:10.1103/PhysRevLett.130.016101 , url =

    work page doi:10.1103/physrevlett.130.016101 2023

  5. [5]

    and Rodenburg, John M

    Maiden, Andrew M. and Rodenburg, John M. , title =. Ultramicroscopy , year =

  6. [6]

    Ptychography

    Rodenburg, John and Maiden, Andrew. Ptychography. Springer Handbook of Microscopy. 2019. doi:10.1007/978-3-030-00069-1_17

    work page doi:10.1007/978-3-030-00069-1_17 2019

  7. [7]

    Nellist, P. D. and McCallum, B. C. and Rodenburg, J. M. , title=. Nature , year=. doi:10.1038/374630a0 , url=

    work page doi:10.1038/374630a0

  8. [8]

    and Park, Jiwoong and Gruner, Sol M

    Jiang, Yi and Chen, Zhen and Han, Yimo and Deb, Pratiti and Gao, Hui and Xie, Saien and Purohit, Prafull and Tate, Mark W. and Park, Jiwoong and Gruner, Sol M. and Elser, Veit and Muller, David A. , title=. Nature , year=. doi:10.1038/s41586-018-0298-5 , url=

    work page doi:10.1038/s41586-018-0298-5

  9. [9]

    J. R. Fienup , journal =. Reconstruction of an object from the modulus of its Fourier transform , volume =. 1978 , url =. doi:10.1364/OL.3.000027 , abstract =

    work page doi:10.1364/ol.3.000027 1978

  10. [10]

    Microscopy and Microanalysis , volume =

    Friedrich, Thomas and Yu, Chu-Ping and Verbeeck, Johan and Van Aert, Sandra , title =. Microscopy and Microanalysis , volume =. 2023 , month =. doi:10.1093/micmic/ozac002 , url =

    work page doi:10.1093/micmic/ozac002 2023

  11. [11]

    Scientific Reports , year=

    Hoidn, Oliver and Mishra, Aashwin Ananda and Mehta, Apurva , title=. Scientific Reports , year=. doi:10.1038/s41598-023-48351-7 , url=

    work page doi:10.1038/s41598-023-48351-7

  12. [12]

    and Zhou, Tao and Kandel, Saugat and Bicer, Tekin and Liu, Zhengchun and Judge, William and Ching, Daniel J

    Babu, Anakha V. and Zhou, Tao and Kandel, Saugat and Bicer, Tekin and Liu, Zhengchun and Judge, William and Ching, Daniel J. and Jiang, Yi and Veseli, Sinisa and Henke, Steven and Chard, Ryan and Yao, Yudong and Sirazitdinova, Ekaterina and Gupta, Geetika and Holt, Martin V. and Foster, Ian T. and Miceli, Antonino and Cherukara, Mathew J. , title=. Nature...

    work page doi:10.1038/s41467-023-41496-z

  13. [13]

    Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops , month =

    Belardi, Christian and Lee, Chia-Hao and Wang, Yingheng and Lovelace, Justin and Weinberger, Kilian and Muller, David and Gomes, Carla , title =. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops , month =. 2025 , pages =

    2025

  14. [14]

    2025 , eprint=

    Atomic-Scale Heterogeneity of Hydrogen in Metal Hydrides Revealed by Electron Ptychography , author=. 2025 , eprint=

    2025

  15. [15]

    Microscopy and Microanalysis , volume =

    Mukherjee, Debangshu and Sankaran, Ramanan and Boebinger, Matthew J , title =. Microscopy and Microanalysis , volume =. 2025 , month =. doi:10.1093/mam/ozaf048.038 , url =

    work page doi:10.1093/mam/ozaf048.038 2025

  16. [16]

    McCray, Arthur R. C. and Ribet, Stephanie M. and Varnavides, Georgios and Ophus, Colin , title =. Journal of Microscopy , volume =. doi:https://doi.org/10.1111/jmi.13407 , url =. https://onlinelibrary.wiley.com/doi/pdf/10.1111/jmi.13407 , abstract =

    work page doi:10.1111/jmi.13407

  17. [17]

    Science Advances , volume =

    Wenfeng Yang and Haozhi Sha and Jizhe Cui and Rong Yu , title =. Science Advances , volume =. 2026 , doi =. https://www.science.org/doi/pdf/10.1126/sciadv.aec9348 , abstract =

    work page doi:10.1126/sciadv.aec9348 2026

  18. [18]

    , title =

    Zhu, Dong and Wang, Chunyang and Zou, Peichao and Zhang, Rui and Wang, Shefang and Song, Bohang and Yang, Xiaoyu and Low, Ke-Bin and Xin, Huolin L. , title =. Nano Letters , volume =. 2023 , doi =

    2023

  19. [19]

    and Yang, Jindou and Wang, Hailiang and Stach, Eric A

    Ortega Ortiz, Erika V. and Yang, Jindou and Wang, Hailiang and Stach, Eric A. , title=. The Journal of Physical Chemistry C , year=. doi:10.1021/acs.jpcc.5c04916 , url=

    work page doi:10.1021/acs.jpcc.5c04916

  20. [20]

    2026 , issn =

    Semi-supervised spatiotemporal segmentation of in situ transmission electron microscopy for nanoparticle dynamics , journal =. 2026 , issn =. doi:https://doi.org/10.1016/j.mtphys.2026.102033 , url =

    work page doi:10.1016/j.mtphys.2026.102033 2026

  21. [21]

    Xin , keywords =

    Siming Zheng and Chunyang Wang and Xin Yuan and Huolin L. Xin , keywords =. Super-compression of large electron microscopy time series by deep compressive sensing learning , journal =. 2021 , issn =. doi:https://doi.org/10.1016/j.patter.2021.100292 , url =

    work page doi:10.1016/j.patter.2021.100292 2021

  22. [22]

    , title=

    Kong, Lingli and Ji, Zhengran and Xin, Huolin L. , title=. Scientific Reports , year=. doi:10.1038/s41598-022-25870-3 , url=

    work page doi:10.1038/s41598-022-25870-3

  23. [23]

    , title=

    Lin, Ruoqian and Zhang, Rui and Wang, Chunyang and Yang, Xiao-Qing and Xin, Huolin L. , title=. Scientific Reports , year=. doi:10.1038/s41598-021-84499-w , url=

    work page doi:10.1038/s41598-021-84499-w

  24. [24]

    Nguyen and Yi Jiang and Chia-Hao Lee and Priti Kharel and Yue Zhang and Arend M

    Kayla X. Nguyen and Yi Jiang and Chia-Hao Lee and Priti Kharel and Yue Zhang and Arend M. van der Zande and Pinshane Y. Huang , title =. Science , volume =. 2024 , doi =. https://www.science.org/doi/pdf/10.1126/science.adl2029 , abstract =

    work page doi:10.1126/science.adl2029 2024

  25. [25]

    Open Research Europe , VOLUME =

    Madsen, J and Susi, T , TITLE =. Open Research Europe , VOLUME =. 2021 , NUMBER =

    2021

  26. [26]

    and Sheikh, H.R

    Zhou Wang and Bovik, A.C. and Sheikh, H.R. and Simoncelli, E.P. , journal=. Image quality assessment: from error visibility to structural similarity , year=

  27. [27]

    Jain, Anubhav and Ong, Shyue Ping and Hautier, Geoffroy and Chen, Wei and Richards, William Davidson and Dacek, Stephen and Cholia, Shreyas and Gunter, Dan and Skinner, David and Ceder, Gerbrand and Persson, Kristin a. , doi =. APL Materials , number =

  28. [28]

    and Natraj, Anusree and Pelkowski, Chloe E

    Kharel, Priti and Carmichael, Patrick T. and Natraj, Anusree and Pelkowski, Chloe E. and Bae, Sang hyun and Dichtel, William R. and Huang, Pinshane Y. , title =. Journal of the American Chemical Society , volume =. 2025 , doi =

    2025

  29. [29]

    IEEE International Conference on Cybernetics and Society, 1975 , address=

    The phase correlation image alignment method , author=. IEEE International Conference on Cybernetics and Society, 1975 , address=

    1975

  30. [30]

    PeerJ , issn =

    scikit-image: image processing in Python , author =. PeerJ , issn =

  31. [31]

    Ptychoscopy: a user friendly experimental design tool for ptychography

    Skoupy, Radim and M \"u ller, Elisabeth and Pennycook, Timothy J and Guizar-Sicairos, Manuel and Fabbri, Emiliana and Poghosyan, Emiliya. Ptychoscopy: a user friendly experimental design tool for ptychography. Sci. Rep

  32. [32]

    Thurman and James R

    Manuel Guizar-Sicairos and Samuel T. Thurman and James R. Fienup , journal =. Efficient subpixel image registration algorithms , volume =. 2008 , url =

    2008

  33. [33]

    New Journal of Physics , abstract =

    Thibault, P and Guizar-Sicairos, M , title =. New Journal of Physics , abstract =. 2012 , month =. doi:10.1088/1367-2630/14/6/063004 , url =

    work page doi:10.1088/1367-2630/14/6/063004 2012

  34. [34]

    O'Leary, C. M. and Allen, C. S. and Huang, C. and Kim, J. S. and Liberti, E. and Nellist, P. D. and Kirkland, A. I. , title =. Applied Physics Letters , volume =. 2020 , month =. doi:10.1063/1.5143213 , url =

    work page doi:10.1063/1.5143213 2020

  35. [35]

    Microscopy and Microanalysis , volume =

    Strauch, Achim and Weber, Dieter and Clausen, Alexander and Lesnichaia, Anastasiia and Bangun, Arya and März, Benjamin and Lyu, Feng Jiao and Chen, Qing and Rosenauer, Andreas and Dunin-Borkowski, Rafal and Müller-Caspary, Knut , title =. Microscopy and Microanalysis , volume =. 2021 , month =. doi:10.1017/S1431927621012423 , url =

    work page doi:10.1017/s1431927621012423 2021

  36. [36]

    Wakonig, Klaus and Stadler, Hans-Christian and Odstr c il, Michal and Tsai, Esther H. R. and Diaz, Ana and Holler, Mirko and Usov, Ivan and Raabe, J \" o rg and Menzel, Andreas and Guizar-Sicairos, Manuel. PtychoShelves , a versatile high-level framework for high-performance analysis of ptychographic data. Journal of Applied Crystallography. 2020. doi:10....

    work page doi:10.1107/s1600576720001776 2020

  37. [37]

    Pennycook and Gerardo T

    Timothy J. Pennycook and Gerardo T. Martinez and Peter D. Nellist and Jannik C. Meyer , keywords =. High dose efficiency atomic resolution imaging via electron ptychography , journal =. 2019 , issn =. doi:https://doi.org/10.1016/j.ultramic.2018.10.005 , url =

    work page doi:10.1016/j.ultramic.2018.10.005 2019

  38. [38]

    2013 , publisher=

    Principles of optics: electromagnetic theory of propagation, interference and diffraction of light , author=. 2013 , publisher=

    2013

  39. [39]

    2025 , eprint=

    Deep generative priors for robust and efficient electron ptychography , author=. 2025 , eprint=

    2025

  40. [40]

    Microscopy and Microanalysis , publisher=

    Lee, Chia-Hao and Zeltmann, Steven E and Yoon, Dasol and Ma, Desheng and Muller, David A , year=. Microscopy and Microanalysis , publisher=. doi:10.1093/mam/ozaf070 , number=

    work page doi:10.1093/mam/ozaf070

  41. [41]

    Electron Ptychography Images Hydrogen Atom Superlattices and

    Shi, Zixiao and Li, Qihao and Mishra, Himani and Ma, Desheng and Abru. Electron Ptychography Images Hydrogen Atom Superlattices and. Journal of the American Chemical Society , volume =. 2025 , doi =

    2025

  42. [42]

    and Han, Yu , title =

    Li, Guanxing and Xu, Ming and Tang, Wen-Qi and Liu, Ying and Chen, Cailing and Zhang, Daliang and Liu, Lingmei and Ning, Shoucong and Zhang, Hui and Gu, Zhi-Yuan and Lai, Zhiping and Muller, David A. and Han, Yu , title =. Nature Communications , year =. doi:10.1038/s41467-025-56215-z , url =

    work page doi:10.1038/s41467-025-56215-z

  43. [43]

    ACS Central Science , year=

    Li, Guanxing and Zhang, Hui and Han, Yu , title=. ACS Central Science , year=. doi:10.1021/acscentsci.2c01137 , url=

    work page doi:10.1021/acscentsci.2c01137

  44. [44]

    Odstrcil and P

    M. Odstrcil and P. Baksh and S. A. Boden and R. Card and J. E. Chad and J. G. Frey and W. S. Brocklesby , journal =. Ptychographic coherent diffractive imaging with orthogonal probe relaxation , volume =. 2016 , url =. doi:10.1364/OE.24.008360 , abstract =

    work page doi:10.1364/oe.24.008360 2016

  45. [45]

    Probe retrieval in ptychographic coherent diffractive imaging , journal =

    Pierre Thibault and Martin Dierolf and Oliver Bunk and Andreas Menzel and Franz Pfeiffer , keywords =. Probe retrieval in ptychographic coherent diffractive imaging , journal =. 2009 , issn =. doi:https://doi.org/10.1016/j.ultramic.2008.12.011 , url =

    work page doi:10.1016/j.ultramic.2008.12.011 2009

  46. [46]

    Nature , year=

    Thibault, Pierre and Menzel, Andreas , title=. Nature , year=. doi:10.1038/nature11806 , url=

    work page doi:10.1038/nature11806

  47. [47]

    Muller and Steven E

    Desheng Ma and Guanxing Li and David A. Muller and Steven E. Zeltmann , keywords =. Information in. Ultramicroscopy , volume =. 2026 , issn =. doi:https://doi.org/10.1016/j.ultramic.2026.114351 , url =

    work page doi:10.1016/j.ultramic.2026.114351 2026

  48. [48]

    Microscopy and Microanalysis , volume =

    Gilgenbach, Colin and Chen, Xi and LeBeau, James M , title =. Microscopy and Microanalysis , volume =. 2024 , month =. doi:10.1093/mam/ozae055 , url =

    work page doi:10.1093/mam/ozae055 2024

  49. [49]

    van der Zande and Elif Ertekin and Pinshane Y

    Yichao Zhang and Ballal Ahammed and Sang Hyun Bae and Chia-Hao Lee and Jeffrey Huang and Mohammad Abir Hossain and Tawfiqur Rakib and Arend M. van der Zande and Elif Ertekin and Pinshane Y. Huang , title =. Science , volume =. 2025 , doi =. https://www.science.org/doi/pdf/10.1126/science.adw7751 , abstract =

    work page doi:10.1126/science.adw7751 2025

  50. [50]

    Sample preparation by focused ion beam micromachining for transmission electron microscopy imaging in front-view , journal =

    Michael Jublot and Michael Texier , keywords =. Sample preparation by focused ion beam micromachining for transmission electron microscopy imaging in front-view , journal =. 2014 , issn =. doi:https://doi.org/10.1016/j.micron.2013.10.007 , url =

    work page doi:10.1016/j.micron.2013.10.007 2014

  51. [51]

    Microscopy and Microanalysis , volume =

    Denzer, Bridget R and Gilgenbach, Colin and LeBeau, James M , title =. Microscopy and Microanalysis , volume =. 2025 , month =. doi:10.1093/mam/ozaf102 , url =

    work page doi:10.1093/mam/ozaf102 2025

  52. [52]

    Science , volume =

    Hui Zhang and Guanxing Li and Jiaxing Zhang and Daliang Zhang and Zhen Chen and Xiaona Liu and Peng Guo and Yihan Zhu and Cailing Chen and Lingmei Liu and Xinwen Guo and Yu Han , title =. Science , volume =. 2023 , doi =. https://www.science.org/doi/pdf/10.1126/science.adg3183 , abstract =

    work page doi:10.1126/science.adg3183 2023

  53. [53]

    and Ophus, Colin and Jones, Lewys and Petford-Long, Amanda and Kalinin, Sergei V

    Spurgeon, Steven R. and Ophus, Colin and Jones, Lewys and Petford-Long, Amanda and Kalinin, Sergei V. and Olszta, Matthew J. and Dunin-Borkowski, Rafal E. and Salmon, Norman and Hattar, Khalid and Yang, Wei-Chang D. and Sharma, Renu and Du, Yingge and Chiaramonti, Ann and Zheng, Haimei and Buck, Edgar C. and Kovarik, Libor and Penn, R. Lee and Li, Dongshe...

    work page doi:10.1038/s41563-020-00833-z

  54. [54]

    Schmidhuber, Deep learning in neural networks: An overview, Neural networks 61 (2015) 85–117.doi:10.1016/j.neunet.2014.09.003

    Jürgen Schmidhuber , keywords =. Deep learning in neural networks: An overview , journal =. 2015 , issn =. doi:https://doi.org/10.1016/j.neunet.2014.09.003 , url =

    work page doi:10.1016/j.neunet.2014.09.003 2015

  55. [55]

    and Mukherjee, Debangshu and Roccapriore, Kevin and Blaiszik, Benjamin J

    Kalinin, Sergei V. and Mukherjee, Debangshu and Roccapriore, Kevin and Blaiszik, Benjamin J. and Ghosh, Ayana and Ziatdinov, Maxim A. and Al-Najjar, Anees and Doty, Christina and Akers, Sarah and Rao, Nageswara S. and Agar, Joshua C. and Spurgeon, Steven R. , title=. npj Computational Materials , year=. doi:10.1038/s41524-023-01142-0 , url=

    work page doi:10.1038/s41524-023-01142-0

  56. [56]

    and Friedrich, T

    Lobato, I. and Friedrich, T. and Van Aert, S. , title=. npj Computational Materials , year=. doi:10.1038/s41524-023-01188-0 , url=

    work page doi:10.1038/s41524-023-01188-0

  57. [57]

    Ondry and Viraj Bodiwala and Peter Ercius and A

    Xingzhi Wang and Chang Yan and Justin C. Ondry and Viraj Bodiwala and Peter Ercius and A. Paul Alivisatos , keywords =. An artificial intelligence’s interpretation of complex high-resolution in situ transmission electron microscopy data , journal =. 2024 , issn =. doi:https://doi.org/10.1016/j.matt.2023.10.023 , url =

    work page doi:10.1016/j.matt.2023.10.023 2024

  58. [58]

    and Morgan, Dane , title=

    Li, Wei and Field, Kevin G. and Morgan, Dane , title=. npj Computational Materials , year=. doi:10.1038/s41524-018-0093-8 , url=

    work page doi:10.1038/s41524-018-0093-8

  59. [59]

    Deep reinforcement learning for data-driven adaptive scanning in ptychography , journal=

    Schloz, Marcel and M. Deep reinforcement learning for data-driven adaptive scanning in ptychography , journal=. 2023 , month=. doi:10.1038/s41598-023-35740-1 , url=

    work page doi:10.1038/s41598-023-35740-1 2023

  60. [60]

    , title=

    Gilgenbach, Colin and Zhu, Menglin and LeBeau, James M. , title=. npj Computational Materials , year=. doi:10.1038/s41524-026-01956-8 , url=

    work page doi:10.1038/s41524-026-01956-8

  61. [61]

    and Ophus, Colin and Voyles, Paul M

    Kalinin, Sergei V. and Ophus, Colin and Voyles, Paul M. and Erni, Rolf and Kepaptsoglou, Demie and Grillo, Vincenzo and Lupini, Andrew R. and Oxley, Mark P. and Schwenker, Eric and Chan, Maria K. Y. and Etheridge, Joanne and Li, Xiang and Han, Grace G. D. and Ziatdinov, Maxim and Shibata, Naoya and Pennycook, Stephen J. , title=. Nature Reviews Methods Pr...

    work page doi:10.1038/s43586-022-00095-w

  62. [62]

    and Wilk, Glen and Chen, Ta-Kun and Hou, Vincent D.-H

    Karapetyan, Shake and Zeltmann, Steven E. and Wilk, Glen and Chen, Ta-Kun and Hou, Vincent D.-H. and Muller, David A. , title =. Nature Communications , year =. doi:10.1038/s41467-026-69733-1 , url =

    work page doi:10.1038/s41467-026-69733-1

  63. [63]

    Ching and Steven Henke and Mathew J

    Ming Du and Tao Zhou and Junjing Deng and Daniel J. Ching and Steven Henke and Mathew J. Cherukara , journal =. Predicting ptychography probe positions using single-shot phase retrieval neural network , volume =. 2024 , url =. doi:10.1364/OE.524317 , abstract =

    work page doi:10.1364/oe.524317 2024

  64. [64]

    , title =

    Chen, Zhen and Odstrcil, Michal and Jiang, Yi and Han, Yimo and Chiu, Ming-Hui and Li, Lain-Jong and Muller, David A. , title =. Nature Communications , year =. doi:10.1038/s41467-020-16688-6 , url =

    work page doi:10.1038/s41467-020-16688-6

  65. [65]

    Holtz and Michal Odstrčil and Manuel Guizar-Sicairos and Isabelle Hanke and Steffen Ganschow and Darrell G

    Zhen Chen and Yi Jiang and Yu-Tsun Shao and Megan E. Holtz and Michal Odstrčil and Manuel Guizar-Sicairos and Isabelle Hanke and Steffen Ganschow and Darrell G. Schlom and David A. Muller , title =. Science , volume =. 2021 , doi =. https://www.science.org/doi/pdf/10.1126/science.abg2533 , abstract =

    work page doi:10.1126/science.abg2533 2021

  66. [66]

    and Stolt, Matthew J

    Chen, Zhen and Turgut, Emrah and Jiang, Yi and Nguyen, Kayla X. and Stolt, Matthew J. and Jin, Song and Ralph, Daniel C. and Fuchs, Gregory D. and Muller, David A. , title=. Nature Nanotechnology , year=. doi:10.1038/s41565-022-01224-y , url=

    work page doi:10.1038/s41565-022-01224-y

  67. [67]

    Nature , year=

    Miao, Jianwei , title=. Nature , year=. doi:10.1038/s41586-024-08278-z , url=

    work page doi:10.1038/s41586-024-08278-z

  68. [68]

    , title=

    Wang, Peng and Zhang, Fucai and Gao, Si and Zhang, Mian and Kirkland, Angus I. , title=. Scientific Reports , year=. doi:10.1038/s41598-017-02778-x , url=

    work page doi:10.1038/s41598-017-02778-x

  69. [69]

    2024 , eprint=

    Imaging interstitial atoms with multislice electron ptychography , author=. 2024 , eprint=

    2024

  70. [70]

    Esther H. R. Tsai and Ivan Usov and Ana Diaz and Andreas Menzel and Manuel Guizar-Sicairos , journal =. X-ray ptychography with extended depth of field , volume =. 2016 , url =. doi:10.1364/OE.24.029089 , abstract =

    work page doi:10.1364/oe.24.029089 2016

  71. [71]

    Electron Ptychography Images Hydrogen Atom Superlattices and

    Shi, Zixiao and Li, Qihao and Mishra, Himani and Ma, Desheng and Abru. Electron Ptychography Images Hydrogen Atom Superlattices and. Journal of the American Chemical Society , year=. doi:10.1021/jacs.5c13741 , url=

    work page doi:10.1021/jacs.5c13741

  72. [72]

    , title=

    Van den Broek, Wouter and Koch, Christoph T. , title=. Physical Review B , year=. doi:10.1103/PhysRevB.87.184108 , url=

    work page doi:10.1103/physrevb.87.184108

  73. [73]

    Maiden and M.J

    A.M. Maiden and M.J. Humphry and M.C. Sarahan and B. Kraus and J.M. Rodenburg , keywords =. An annealing algorithm to correct positioning errors in ptychography , journal =. 2012 , issn =. doi:https://doi.org/10.1016/j.ultramic.2012.06.001 , url =

    work page doi:10.1016/j.ultramic.2012.06.001 2012

  74. [74]

    T. M. Godden and R. Suman and M. J. Humphry and J. M. Rodenburg and A. M. Maiden , journal =. Ptychographic microscope for three-dimensional imaging , volume =. 2014 , url =. doi:10.1364/OE.22.012513 , abstract =

    work page doi:10.1364/oe.22.012513 2014

  75. [75]

    and Nellist, Peter D

    Gao, Si and Wang, Peng and Zhang, Fucai and Martinez, Gerardo T. and Nellist, Peter D. and Pan, Xiaoqing and Kirkland, Angus I. , title=. Nature Communications , year=. doi:10.1038/s41467-017-00150-1 , url=

    work page doi:10.1038/s41467-017-00150-1

  76. [76]

    A. M. Maiden and M. J. Humphry and J. M. Rodenburg , journal =. Ptychographic transmission microscopy in three dimensions using a multi-slice approach , volume =. 2012 , url =. doi:10.1364/JOSAA.29.001606 , abstract =

    work page doi:10.1364/josaa.29.001606 2012

  77. [77]

    Nature , year =

    Dong, Zehao and Huo, Mengwu and Li, Jie and Li, Jingyuan and Li, Pengcheng and Sun, Hualei and Gu, Lin and Lu, Yi and Wang, Meng and Wang, Yayu and Chen, Zhen , title =. Nature , year =. doi:10.1038/s41586-024-07482-1 , publisher =

    work page doi:10.1038/s41586-024-07482-1

  78. [78]

    2026 , eprint=

    Towards single-shot coherent imaging via overlap-free ptychography , author=. 2026 , eprint=

    2026

  79. [79]

    Ptychographic atomic electron tomography: Towards three-dimensional imaging of individual light atoms in materials , author =. Phys. Rev. B , volume =. 2020 , month =. doi:10.1103/PhysRevB.102.174101 , url =

    work page doi:10.1103/physrevb.102.174101 2020

  80. [80]

    Nature Communications , year=

    Dong, Zehao and Zhang, Yang and Chiu, Chun-Chien and Lu, Sicheng and Zhang, Jianbing and Liu, Yu-Chen and Liu, Suya and Yang, Jan-Chi and Yu, Pu and Wang, Yayu and Chen, Zhen , title=. Nature Communications , year=. doi:10.1038/s41467-025-56499-1 , url=

    work page doi:10.1038/s41467-025-56499-1

Showing first 80 references.