Preparing for Rubin-LSST: Detecting brightest cluster galaxies with machine learning in the LSST DP0.2 simulation

¹ The Oskar Klein Centre, Department of Astronomy, Stockholm University, Albanova University Centre 106 91 Stockholm, Sweden
² The Oskar Klein Centre, Department of Physics, Stockholm University, AlbaNova University Centre 106 91 Stockholm, Sweden
³ Sorbonne Université, CNRS, UMR 7095, Institut d’Astrophysique de Paris 98bis Bd Arago 75014 Paris, France

^★ Corresponding author: This email address is being protected from spambots. You need JavaScript enabled to view it.

Received: 20 March 2025
Accepted: 10 December 2025

Abstract

The Rubin Legacy Survey of Space and Time (LSST) is expected to deliver its first data release early 2027. The upcoming survey will provide us with images of galaxy clusters in the optical to the near-infrared at an unrivalled coverage, depth, and uniformity. The study of galaxy clusters provides information on the effect of environmental processes on galactic formation, which directly translates to the formation of the brightest cluster galaxy (BCG). These massive galaxies present traces of the whole merger history of their host clusters, which can take the shape of intra-cluster light (ICL) that surrounds them, tidal streams, or simply the accumulated stellar mass that has been acquired over the past 10 billion years as they have cannibalised other galaxies in their surroundings. In an era where new data are being generated faster than humans can process them, new methods involving machine learning have been emerging more frequently in recent years. With the aim of preparing for the future LSST data release, which will enable the observation of more than 20 000 clusters and BCGs, we present different methods based on machine learning (i.e. neural networks, NNs) to detect the BCGs of known clusters on LSST-like optical images. This study was carried out on the basis of the simulated LSST Data Preview images. We find that the use of NNs allowed us to accurately identify the BCG in up to 95% of clusters in our sample. Compared to more conventional red sequence extraction methods, NNs appear to be faster, more efficient and consistent, and do not require much pre-processing (if any).