Saved in:
Bibliographic Details
Main Authors: Nellikunnummel, Nisar, Barbour, Andi, Wiegart, Lutz, Konstantinova, Tatiana, DeGennaro, Anthony
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.29975
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916061467639808
author Nellikunnummel, Nisar
Barbour, Andi
Wiegart, Lutz
Konstantinova, Tatiana
DeGennaro, Anthony
author_facet Nellikunnummel, Nisar
Barbour, Andi
Wiegart, Lutz
Konstantinova, Tatiana
DeGennaro, Anthony
contents We present a fully convolutional denoising autoencoder (FC-DAE) for denoising two-time intensity-intensity correlation functions ($C_2$) in X-ray photon correlation spectroscopy (XPCS). Unlike conventional denoising autoencoders that are typically restricted to fixed input sizes, the FC-DAE accepts inputs of arbitrary dimensions while preserving correlation structures across diverse dynamical regimes. The model is trained using experimentally derived $C_2$ data collected at NSLS-II beamlines, with data augmentation applied to expand the diversity of the dataset and reduce overfitting. The FC-DAE successfully recovers intricate dynamical features in low signal-to-noise conditions while maintaining structural fidelity. To assess reconstruction reliability, we employ quantitative metrics to evaluate structural fidelity and identify potential model-induced bias. Our results demonstrate that the FC-DAE provides robust denoising performance with high computational efficiency, enabling recovery of XPCS dynamics under photon-limited and low-dose measurement conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2605_29975
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Fully Convolutional Approach to Denoising Structural Dynamics Data from X-Ray Photon Correlation Spectroscopy
Nellikunnummel, Nisar
Barbour, Andi
Wiegart, Lutz
Konstantinova, Tatiana
DeGennaro, Anthony
Machine Learning
Signal Processing
We present a fully convolutional denoising autoencoder (FC-DAE) for denoising two-time intensity-intensity correlation functions ($C_2$) in X-ray photon correlation spectroscopy (XPCS). Unlike conventional denoising autoencoders that are typically restricted to fixed input sizes, the FC-DAE accepts inputs of arbitrary dimensions while preserving correlation structures across diverse dynamical regimes. The model is trained using experimentally derived $C_2$ data collected at NSLS-II beamlines, with data augmentation applied to expand the diversity of the dataset and reduce overfitting. The FC-DAE successfully recovers intricate dynamical features in low signal-to-noise conditions while maintaining structural fidelity. To assess reconstruction reliability, we employ quantitative metrics to evaluate structural fidelity and identify potential model-induced bias. Our results demonstrate that the FC-DAE provides robust denoising performance with high computational efficiency, enabling recovery of XPCS dynamics under photon-limited and low-dose measurement conditions.
title A Fully Convolutional Approach to Denoising Structural Dynamics Data from X-Ray Photon Correlation Spectroscopy
topic Machine Learning
Signal Processing
url https://arxiv.org/abs/2605.29975