AI-enabled Lorentz microscopy for quantitative imaging of nanoscale magnetic spin textures

Arthur R.C. McCray; Tao Zhou; Saugat Kandel; Amanda Petford-Long; Mathew J. Cherukara; Charudatta Phatak

doi:10.1038/s41524-024-01285-8

AI-enabled Lorentz microscopy for quantitative imaging of nanoscale magnetic spin textures

Arthur R.C. McCray, Tao Zhou, Saugat Kandel, Amanda Petford-Long, Mathew J. Cherukara, Charudatta Phatak^*

^*Corresponding author for this work

Materials Science and Engineering

Research output: Contribution to journal › Article › peer-review

Abstract

The manipulation and control of nanoscale magnetic spin textures are of rising interest as they are potential foundational units in next-generation computing paradigms. Achieving this requires a quantitative understanding of the spin texture behavior under external stimuli using in situ experiments. Lorentz transmission electron microscopy (LTEM) enables real-space imaging of spin textures at the nanoscale, but quantitative characterization of in situ data is extremely challenging. Here, we present an AI-enabled phase-retrieval method based on integrating a generative deep image prior with an image formation forward model for LTEM. Our approach uses a single out-of-focus image for phase retrieval and achieves significantly higher accuracy and robustness to noise compared to existing methods. Furthermore, our method is capable of isolating sample heterogeneities from magnetic contrast, as shown by application to simulated and experimental data. This approach allows quantitative phase reconstruction of in situ data and can also enable near real-time quantitative magnetic imaging.

Original language	English (US)
Article number	111
Journal	npj Computational Materials
Volume	10
Issue number	1
DOIs	https://doi.org/10.1038/s41524-024-01285-8
State	Published - Dec 2024

Funding

This work was supported by the U.S. Department of Energy, Office of Science, Office of Basic Energy Sciences, Materials Sciences and Engineering Division. This work was performed, in part, at the Center for Nanoscale Materials and the Advanced Photon Source, both U.S. Department of Energy Office of Science User Facilities, and supported by the U.S. Department of Energy, Office of Science, under Contract No. DE-AC02-06CH11357. M.J.C also acknowledges support from Argonne LDRD 2021-0090 - AutoPtycho: Autonomous, Sparse-sampled Ptychographic Imaging. We gratefully acknowledge the computing resources provided on Swing, a high-performance computing cluster operated by the Laboratory Computing Resource Center at Argonne National Laboratory. We would like to acknowledge Yue Li for her help in acquiring the experimental data.

ASJC Scopus subject areas

Modeling and Simulation
General Materials Science
Mechanics of Materials
Computer Science Applications

Access to Document

10.1038/s41524-024-01285-8

Cite this

@article{ddda94a842814a26b12cd70d15c55ed0,

title = "AI-enabled Lorentz microscopy for quantitative imaging of nanoscale magnetic spin textures",

abstract = "The manipulation and control of nanoscale magnetic spin textures are of rising interest as they are potential foundational units in next-generation computing paradigms. Achieving this requires a quantitative understanding of the spin texture behavior under external stimuli using in situ experiments. Lorentz transmission electron microscopy (LTEM) enables real-space imaging of spin textures at the nanoscale, but quantitative characterization of in situ data is extremely challenging. Here, we present an AI-enabled phase-retrieval method based on integrating a generative deep image prior with an image formation forward model for LTEM. Our approach uses a single out-of-focus image for phase retrieval and achieves significantly higher accuracy and robustness to noise compared to existing methods. Furthermore, our method is capable of isolating sample heterogeneities from magnetic contrast, as shown by application to simulated and experimental data. This approach allows quantitative phase reconstruction of in situ data and can also enable near real-time quantitative magnetic imaging.",

author = "McCray, {Arthur R.C.} and Tao Zhou and Saugat Kandel and Amanda Petford-Long and Cherukara, {Mathew J.} and Charudatta Phatak",

note = "Publisher Copyright: {\textcopyright} UChicago Argonne, LLC, Operator of Argonne National Laboratory 2024 2024.",

year = "2024",

month = dec,

doi = "10.1038/s41524-024-01285-8",

language = "English (US)",

volume = "10",

journal = "npj Computational Materials",

issn = "2057-3960",

publisher = "Nature Publishing Group",

number = "1",

}

TY - JOUR

T1 - AI-enabled Lorentz microscopy for quantitative imaging of nanoscale magnetic spin textures

AU - McCray, Arthur R.C.

AU - Zhou, Tao

AU - Kandel, Saugat

AU - Petford-Long, Amanda

AU - Cherukara, Mathew J.

AU - Phatak, Charudatta

PY - 2024/12

Y1 - 2024/12

N2 - The manipulation and control of nanoscale magnetic spin textures are of rising interest as they are potential foundational units in next-generation computing paradigms. Achieving this requires a quantitative understanding of the spin texture behavior under external stimuli using in situ experiments. Lorentz transmission electron microscopy (LTEM) enables real-space imaging of spin textures at the nanoscale, but quantitative characterization of in situ data is extremely challenging. Here, we present an AI-enabled phase-retrieval method based on integrating a generative deep image prior with an image formation forward model for LTEM. Our approach uses a single out-of-focus image for phase retrieval and achieves significantly higher accuracy and robustness to noise compared to existing methods. Furthermore, our method is capable of isolating sample heterogeneities from magnetic contrast, as shown by application to simulated and experimental data. This approach allows quantitative phase reconstruction of in situ data and can also enable near real-time quantitative magnetic imaging.

AB - The manipulation and control of nanoscale magnetic spin textures are of rising interest as they are potential foundational units in next-generation computing paradigms. Achieving this requires a quantitative understanding of the spin texture behavior under external stimuli using in situ experiments. Lorentz transmission electron microscopy (LTEM) enables real-space imaging of spin textures at the nanoscale, but quantitative characterization of in situ data is extremely challenging. Here, we present an AI-enabled phase-retrieval method based on integrating a generative deep image prior with an image formation forward model for LTEM. Our approach uses a single out-of-focus image for phase retrieval and achieves significantly higher accuracy and robustness to noise compared to existing methods. Furthermore, our method is capable of isolating sample heterogeneities from magnetic contrast, as shown by application to simulated and experimental data. This approach allows quantitative phase reconstruction of in situ data and can also enable near real-time quantitative magnetic imaging.

UR - http://www.scopus.com/inward/record.url?scp=85194878082&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85194878082&partnerID=8YFLogxK

U2 - 10.1038/s41524-024-01285-8

DO - 10.1038/s41524-024-01285-8

M3 - Article

AN - SCOPUS:85194878082

SN - 2057-3960

VL - 10

JO - npj Computational Materials

JF - npj Computational Materials

IS - 1

M1 - 111

ER -

AI-enabled Lorentz microscopy for quantitative imaging of nanoscale magnetic spin textures

Abstract

Funding

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this