SILVERRUSH X: Machine Learning-aided Selection of 9318 LAEs at z = 2.2, 3.3, 4.9, 5.7, 6.6, and 7.0 from the HSC SSP and CHORUS Survey Data

Abstract We present a new catalog of 9318 Ly ? emitter (LAE) candidates at z = 2.2, 3.3, 4.9, 5.7, 6.6, and 7.0 that are photometrically selected by the SILVERRUSH program with machine learning technique from large area (up to 25.0 deg 2 ) imaging data six narrowband filters taken Subaru Strategic Program Hyper Suprime-Cam intensive program, Cosmic HydrOgen Reionization Unveiled Subaru. construct convolutional neural network distinguishes between real LAEs contaminants completeness 94% contamination rate 1%, enabling us efficiently remove LAE candidates. confirm our catalogs include 177 have been spectroscopically identified in programs previous studies, ensuring validity selection. In addition, we find object-matching rates results ?80%–100% bright NB magnitudes ?24 mag. also surface number densities consistent results. Our will be made public on project webpage.