THE PROPERTIES OF Hα EMISSION-LINE GALAXIES AT z=2.24

Using deep narrowband H(2)S1 and K-s-band imaging data obtained with CFHT/WIRCam, we identify a sample of 56 H alpha emission-line galaxies (ELGs) at z = 2.24 with the 5 sigma depths of H(2)S1 = 22.8 and K-s = 24.8 (AB) over a 383 arcmin(2) area in the Extended Chandra Deep Field South. A detailed analysis is carried out with existing multi-wavelength data in this field. Three of the 56 H alpha ELGs are detected in Chandra 4 Ms X-ray observations and two of them are classified as active galactic nuclei. The rest-frame UV and optical morphologies revealed by HST/ACS and WFC3 deep images show that nearly half of the H alpha ELGs are either merging systems or have a close companion, indicating that the merging/interacting processes play a key role in regulating star formation at cosmic epoch z = 2-3. About 14% are too faint to be resolved in the rest-frame UV morphology due to high dust extinction. We estimate dust extinction from spectral energy distributions. We find that dust extinction is generally correlated with Ha luminosity and stellar mass. Our results suggest that H alpha ELGs are representative of star-forming galaxies. Applying extinction corrections to individual objects, we examine the intrinsic Ha luminosity function (LF) at z = 2.24, obtaining a best-fit Schechter function characterized by a faint-end slope of alpha similar or equal to -1.3. This is shallower than the typical slope of a z-1.6 in previous works based on constant extinction correction. We demonstrate that this difference is mainly due to the different extinction corrections. The proper extinction correction is thus the key to recovering the intrinsic LF as the extinction globally increases with H alpha luminosity. Moreover, we find that our H alpha LF mirrors the stellar mass function of star-forming galaxies at the same cosmic epoch. This finding indeed reflects the tight correlation between star formation rate and stellar mass for star-forming galaxies, i.e., the so-called main sequence.