Enabling dynamic 3D coherent diffraction imaging via adaptive latent space tuning of generative autoencoders

Abstract Coherent diffraction imaging (CDI) is an advanced non-destructive 3D X-ray imaging technique for measuring a sample’s electron density. The main challenge of CDI is loss of phase information in diffraction intensity measurements, resulting in lengthy iterative reconstruction processes that...

Full description

Saved in:
Bibliographic Details
Main Authors: Alexander Scheinker, Reeju Pokharel
Format: Article
Language:English
Published: Nature Portfolio 2024-12-01
Series:npj Computational Materials
Online Access:https://doi.org/10.1038/s41524-024-01482-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846112426761650176
author Alexander Scheinker
Reeju Pokharel
author_facet Alexander Scheinker
Reeju Pokharel
author_sort Alexander Scheinker
collection DOAJ
description Abstract Coherent diffraction imaging (CDI) is an advanced non-destructive 3D X-ray imaging technique for measuring a sample’s electron density. The main challenge of CDI is loss of phase information in diffraction intensity measurements, resulting in lengthy iterative reconstruction processes that can return non-unique solutions, which pose challenges for experiments attempting to track dynamic sample evolution through multiple states. As the increased brightness of fourth-generation light sources enables faster sample measurements and drives operando experiments with Bragg CDI, there is a growing need for faster reconstruction techniques that can keep pace. We have developed an adaptive generative autoencoder approach for uniquely tracking a sample’s electron density as it dynamically evolves. Our approach adaptively tunes the low-dimensional latent embedding of a generative autoencoder, enabling a computationally efficient manner to account for time-varying shifting distributions in real-time. Analytic proof of convergence is provided as well as numerical demonstration of sample tracking with noisy measurements.
format Article
id doaj-art-945a8e67a2904660b35f96d008445253
institution Kabale University
issn 2057-3960
language English
publishDate 2024-12-01
publisher Nature Portfolio
record_format Article
series npj Computational Materials
spelling doaj-art-945a8e67a2904660b35f96d0084452532024-12-22T12:36:45ZengNature Portfolionpj Computational Materials2057-39602024-12-0110111510.1038/s41524-024-01482-5Enabling dynamic 3D coherent diffraction imaging via adaptive latent space tuning of generative autoencodersAlexander Scheinker0Reeju Pokharel1Applied Electrodynamics, Los Alamos National LaboratoryMaterial Science and Technology, Los Alamos National LaboratoryAbstract Coherent diffraction imaging (CDI) is an advanced non-destructive 3D X-ray imaging technique for measuring a sample’s electron density. The main challenge of CDI is loss of phase information in diffraction intensity measurements, resulting in lengthy iterative reconstruction processes that can return non-unique solutions, which pose challenges for experiments attempting to track dynamic sample evolution through multiple states. As the increased brightness of fourth-generation light sources enables faster sample measurements and drives operando experiments with Bragg CDI, there is a growing need for faster reconstruction techniques that can keep pace. We have developed an adaptive generative autoencoder approach for uniquely tracking a sample’s electron density as it dynamically evolves. Our approach adaptively tunes the low-dimensional latent embedding of a generative autoencoder, enabling a computationally efficient manner to account for time-varying shifting distributions in real-time. Analytic proof of convergence is provided as well as numerical demonstration of sample tracking with noisy measurements.https://doi.org/10.1038/s41524-024-01482-5
spellingShingle Alexander Scheinker
Reeju Pokharel
Enabling dynamic 3D coherent diffraction imaging via adaptive latent space tuning of generative autoencoders
npj Computational Materials
title Enabling dynamic 3D coherent diffraction imaging via adaptive latent space tuning of generative autoencoders
title_full Enabling dynamic 3D coherent diffraction imaging via adaptive latent space tuning of generative autoencoders
title_fullStr Enabling dynamic 3D coherent diffraction imaging via adaptive latent space tuning of generative autoencoders
title_full_unstemmed Enabling dynamic 3D coherent diffraction imaging via adaptive latent space tuning of generative autoencoders
title_short Enabling dynamic 3D coherent diffraction imaging via adaptive latent space tuning of generative autoencoders
title_sort enabling dynamic 3d coherent diffraction imaging via adaptive latent space tuning of generative autoencoders
url https://doi.org/10.1038/s41524-024-01482-5
work_keys_str_mv AT alexanderscheinker enablingdynamic3dcoherentdiffractionimagingviaadaptivelatentspacetuningofgenerativeautoencoders
AT reejupokharel enablingdynamic3dcoherentdiffractionimagingviaadaptivelatentspacetuningofgenerativeautoencoders