Unsupervised Discovery of High-Redshift Galaxy Populations with Variational Autoencoders

TL;DR

This paper demonstrates an unsupervised approach using variational autoencoders to identify and classify high-redshift galaxy populations from JWST spectra without prior labels, enabling automated discovery in large surveys.

Contribution

It introduces a novel unsupervised method employing variational autoencoders for discovering galaxy populations in high-redshift spectroscopic data, advancing automated astrophysical classification.

Findings

Successfully identified distinct galaxy classes in JWST spectra

Demonstrated capability for automated discovery in large datasets

Revealed new galaxy types without prior labeling

Abstract

We apply variational autoencoders to automatically discover galaxy populations using publicly available high-redshift \textit{JWST} spectra without prior classification knowledge. Our unsupervised method identifies distinct astrophysical classes of unique and exciting galaxy types, demonstrating automated discovery capabilities for large spectroscopic surveys.