PtyRANNOSAUR: Ptychography with Robust Artificial Neural Networks Optimized for Subangstrom Accuracy and Ultrafast Reconstruction
Nano Letters · 04.11.2026 · 26 (43) · 14949-14958
DOI: 10.1021/acs.nanolett.6c03513 ↗Kurz gefasst
Fachartikel in der Zeitschrift Nano Letters, online erschienen am 22.10.2026. Verfasst von Kieran Loehr und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Physics, University of Illinois Urbana-Champaign, Urbana, Illinois61801, United States. Die Arbeit nennt 89 Literaturangaben. Gefördert von: Air Force Office of Scientific Research, National Science Foundation (NSF).
Abstract (Originalsprache)
We present PtyRANNOSAUR, a data-driven neural network approach that reconstructs atomic-resolution electron ptychography data in seconds, 100–1000 times faster than iterative 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, significantly increasing the accessibility and usability of electron ptychography. In addition, the code handles spatial partial coherence, multiple scattering, and scan position errors, which are critical for the highest-quality electron ptychography reconstructions but have not been available without hours-long computations. By testing PtyRANNOSAUR on experimental and simulated data, we show that the neural networks accurately reconstruct atomic structures on a broad range of systems of materials and achieve high spatial resolutions of <0.5 Å, comparable to the best iterative reconstructions of the same data. These advances enable live, easy-to-use, state-of-the-art electron ptychography reconstructions. These features make it possible to conduct hundreds of electron ptychography reconstructions in minutes and should unlock new operational modes for nanocharacterization, such as in situ and high-throughput electron ptychography.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Physics, University of Illinois Urbana-Champaign, Urbana, Illinois61801, United States.
- The Grainger College of Engineering, University of Illinois Urbana-Champaign, Urbana, Illinois61801, United States.
- Department of Materials Science and Engineering, University of Illinois Urbana-Champaign, Urbana, Illinois61801, United States.
- The Anthony J. Leggett Institute for Condensed Matter Theory and IQUIST and NCSA Center for Artificial Intelligence Innovation, University of Illinois Urbana-Champaign, Urbana, Illinois61801, United States.
- Materials Research Laboratory, University of Illinois Urbana-Champaign, Urbana, Illinois61801, United States.
ORCID-Profile: Jeffrey Huang, Gillian Nolan, Pinshane Y Huang
Förderung
- Air Force Office of Scientific Research
- National Science Foundation (NSF)
Zitieren
APA
Loehr, K., Raja, R., Ding, X., Huang, J., Nolan, G., Bae, S. H., Clark, B. K., & Huang, P. Y. (2026). PtyRANNOSAUR: Ptychography with Robust Artificial Neural Networks Optimized for Subangstrom Accuracy and Ultrafast Reconstruction. Nano Letters, 26(43), 14949-14958. https://doi.org/10.1021/acs.nanolett.6c03513
Vancouver
Loehr K, Raja R, Ding X, Huang J, Nolan G, Bae SH, et al. PtyRANNOSAUR: Ptychography with Robust Artificial Neural Networks Optimized for Subangstrom Accuracy and Ultrafast Reconstruction. Nano Letters. 2026;26(43):14949-14958. doi:10.1021/acs.nanolett.6c03513
BibTeX
@article{Loehr2026,
author = {Loehr, Kieran and Raja, Rahim and Ding, Xiaochuan and Huang, Jeffrey and Nolan, Gillian and Bae, Sang Hyun and Clark, Bryan K and Huang, Pinshane Y},
title = {PtyRANNOSAUR: Ptychography with Robust Artificial Neural Networks Optimized for Subangstrom Accuracy and Ultrafast Reconstruction},
journal = {Nano Letters},
year = {2026},
volume = {26},
number = {43},
pages = {14949--14958},
doi = {10.1021/acs.nanolett.6c03513}
}
EUVIMED