Anomaly detection in the Zwicky Transient Facility DR3

TL;DR

This paper applies a machine learning-based anomaly detection pipeline to ZTF DR3 data, identifying potential scientific objects and bogus signals, demonstrating the value of combining algorithms with expert analysis in astronomical data filtering.

Contribution

It introduces a multi-stage anomaly detection pipeline applied to ZTF data, highlighting the integration of machine learning and human expertise for effective anomaly identification.

Findings

Identified 23 potentially scientifically interesting objects.

Developed a bi-dimensional relation to filter bogus light curves.

Provided a publicly available codebase for anomaly detection.

Abstract

We present results from applying the SNAD anomaly detection pipeline to the third public data release of the Zwicky Transient Facility (ZTF DR3). The pipeline is composed of 3 stages: feature extraction, search of outliers with machine learning algorithms and anomaly identification with followup by human experts. Our analysis concentrates in three ZTF fields, comprising more than 2.25 million objects. A set of 4 automatic learning algorithms was used to identify 277 outliers, which were subsequently scrutinised by an expert. From these, 188 (68%) were found to be bogus light curves -- including effects from the image subtraction pipeline as well as overlapping between a star and a known asteroid, 66 (24%) were previously reported sources whereas 23 (8%) correspond to non-catalogued objects, with the two latter cases of potential scientific interest (e. g. 1 spectroscopically confirmed RS Canum Venaticorum star, 4 supernovae candidates, 1 red dwarf flare). Moreover, using results from the expert analysis, we were able to identify a simple bi-dimensional relation which can be used to aid filtering potentially bogus light curves in future studies. We provide a complete list of objects with potential scientific application so they can be further scrutinised by the community. These results confirm the importance of combining automatic machine learning algorithms with domain knowledge in the construction of recommendation systems for astronomy. Our code is publicly available at https://github.com/snad-space/zwad