view article
Figure 8
Convolutional autoencoder architecture consisting of a symmetric encoder and decoder, which was trained for XAS data denoising. During encoding, the input spectrum is mapped to a latent representation that captures the dominant spectral features shared across the dataset, while uncorrelated noise is largely suppressed. The decoder then reconstructs a denoised spectrum from this latent representation.

Journal logoJOURNAL OF
SYNCHROTRON
RADIATION
ISSN: 1600-5775
Volume 33| Part 3| May 2026| Pages 658-682
https://doi.org/10.1107/S1600577526001712
Follow J. Synchrotron Rad.
Sign up for e-alerts
E-alerts
Follow J. Synchrotron Rad. on Twitter
Twitter
Follow us on facebook
Facebook
Sign up for RSS feeds
RSS