Type: Talk
Session: Galaxies Science from Dwarfs to Clusters
Author: Simona Mei

Abstract: LSST will provide galaxy cluster catalogs up to z~1 that can be used to constrain cosmological models. Machine learning based cluster detection algorithms can be applied directly on images to circumvent systematics due to photometric and photometric redshift catalogs. Simulations permit us to characterize the cluster selection function. In this work, we have applied the deep convolutional network YOLO for CLuster detection (YOLO-CL; Grishin, Mei, Ilic 2023) to LSST DESC DC2 simulations. The YOLO-CL cluster catalog is 100% and 94% complete for halo mass M_{200c} > 10^{14.6} M_sun at 0.2<z<0.8, and M_{200c} > 10^{14} M_sun and redshift z ~ 1, respectively, with only 6% false positive detections. We find that all the false positive detections are dark matter haloes that correspond to galaxy groups. The YOLO-CL selection function is almost flat with respect to the halo mass at 0.2 < z < 0.9. The overall performance of YOLO-CL is comparable or better than other cluster detection methods used for current and future optical and infrared surveys.