Enhancing Galaxy Classification with U-Net Variational Autoencoders. II. JWST High Redshift Galaxy Sample

TL;DR

This paper demonstrates that using a U-Net Variational Autoencoder to denoise JWST galaxy images improves morphological classification accuracy, revealing the prevalence of disk-like structures at high redshifts in early universe galaxies.

Contribution

The study introduces a VAE-based denoising method tailored for high-redshift galaxy images, enhancing morphological classification in JWST data.

Findings

Denoising with VAE improves image quality and classification accuracy.

Approximately 70-80% of classified disk-like galaxies are at z > 3.

The method reveals the potential abundance of disk structures in early universe galaxies.

Abstract

Building on our previous work, we apply a U-Net Variational Autoencoder (VAE) framework to denoise galaxy images from the James Webb Space Telescope (JWST) and enhance morphological classification. This study focuses on galaxies observed up to redshift approximately at 8, capturing them at early evolutionary stages where their faintness and structural complexity pose challenges for the traditional classification methods. By mitigating observational noise, our approach enables the identification of morphological features, particularly in distinguishing between disk and non-disk galaxy types. We evaluate the denoising performance using standard image quality metrics and demonstrate that the enhanced images lead to improved classification accuracy across multiple deep learning models. Our analysis of a sample of 292 galaxies up to z=7.69 shows 83 galaxies classified as disk-like by the GCNN model with high confidence, of those approximately 70-80 % are of redshifts greater than 3. These findings suggest that disk-like structures can be prevalent in the early universe. The results highlight the potential of VAE-based denoising as a robust pre-processing step for analyzing high-redshift galaxy populations in ongoing astronomical surveys.