One of the major challenges in the field of galaxy formation and evolution is to understand how early-type galaxy (ETG) star formation is quenched in the first epoch of their assembly. Euclid (https://www.esa.int/Science_Exploration/Space_Science/Euclid) imaging and spectroscopy observations give us the opportunity to answer this question as never before.

The context of this PhD thesis is to improve galaxy cluster detection in combined Euclid and Rubin/LSST data, using machine learning technique. The PhD student will start to work with the YOLO-CL network (Grishin, Mei, Ilic 2023), test the network on simulations and improve it for cluster detection and galaxy photometric redshift estimation.

 

We will discover new clusters and protoclusters at z>1.5, compare our discoveries with cosmological simulations.