Searching for Anomalies in the ZTF Catalog of Periodic Variable Stars

TL;DR

This paper introduces an unsupervised machine learning method combining a convolutional variational autoencoder and isolation forest to identify anomalous periodic variable stars in the ZTF catalog, revealing irregular variability and potential new stellar phenomena.

Contribution

The study presents a novel unsupervised approach using deep learning and anomaly detection to find unusual periodic variables in large astronomical datasets.

Findings

Identified anomalies likely include highly variable Red Giants and AGB stars.

Detected anomalies possibly representing Young Stellar Objects.

Most anomalies are concentrated in the Milky Way galactic disk.

Abstract

Periodic variables illuminate the physical processes of stars throughout their lifetime. Wide-field surveys continue to increase our discovery rates of periodic variable stars. Automated approaches are essential to identify interesting periodic variable stars for multi-wavelength and spectroscopic follow-up. Here, we present a novel unsupervised machine learning approach to hunt for anomalous periodic variables using phase-folded light curves presented in the Zwicky Transient Facility Catalogue of Periodic Variable Stars by \citet{Chen_2020}. We use a convolutional variational autoencoder to learn a low dimensional latent representation, and we search for anomalies within this latent dimension via an isolation forest. We identify anomalies with irregular variability. Most of the top anomalies are likely highly variable Red Giants or Asymptotic Giant Branch stars concentrated in the Milky Way galactic disk; a fraction of the identified anomalies are more consistent with Young Stellar Objects. Detailed spectroscopic follow-up observations are encouraged to reveal the nature of these anomalies.