cs.LGMay 28, 2026

A Fully Convolutional Approach to Denoising Structural Dynamics Data from X-Ray Photon Correlation Spectroscopy

Authors: Nisar NellikunnummelAndi BarbourLutz WiegartTatiana KonstantinovaAnthony DeGennaro

Organizations: Brookhaven National Laboratory, Upton, NY 11973, USA · Currently at: Amazon · Currently at: GE Aerospace Research

Abstract

We present a fully convolutional denoising autoencoder (FC-DAE) for denoising two-time intensity-intensity correlation functions (C2C_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 C2C_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.

Explore similar work

CardsList
  1. A Practical Noise2Noise Denoising Pipeline for High-Throughput Raman Spectroscopy

    May 18, 2026David Martin-Calle, Cesar Alvarez Llamas, Vincent Motto- Ros +3RamanImage Denoising