We investigate the performance of machine-learning techniques in classifying active galactic nuclei (AGNs), including X-ray-selected AGNs (XAGNs), infrared-selected AGNs (IRAGNs), and radio-selected AGNs (RAGNs). Using the known physical parameters in the Cosmic Evolution Survey (COSMOS) field, we are able to create quality training samples in the region of the Hyper Suprime-Cam (HSC) survey. We compare several Python packages (e.g., scikit-learn, Keras, and XGBoost) and use XGBoost to identify AGNs and show the performance (e.g., accuracy, precision, recall, F1 score, and AUROC). Our results indicate that the performance is high for bright XAGN and IRAGN host galaxies. The combination of the HSC (optical) information with the Wide-field Infrared Survey Explorer band 1 and band 2 (near-infrared) information performs well to identify AGN hosts. For both type 1 (broad-line) XAGNs and type 1 (unobscured) IRAGNs, the performance is very good by using optical-to-infrared information. These results can apply to the five-band data from the wide regions of the HSC survey and future all-sky surveys.
Radio-loud active galactic nuclei (RLAGNs) are rare among AGN populations. Lacking high-resolution and high-frequency observations, their structure and evolution stages are not well understood at high redshifts. In this work, we report ALMA 237 GHz continuum observation at 0${_{.}^{\prime\prime}}$23 resolution and VLA 44 GHz continuum observation at 0${_{.}^{\prime\prime}}$8 resolution of the radio continuum emission from a high-redshift radio and hyper-luminous infrared galaxy at z = 1.92. The new observations confirm the South-East (SE) and North-West (NW) hotspots identified by previous low-resolution VLA observations at 4.7 and 8.2 GHz and identify a radio core undetected in all previous observations. The SE hotspot has a higher flux density than the NW one does by a factor of 6, suggesting that there can be a Doppler boosting effect in the SE one. In this scenario, we estimate the advance speed of the jet head, ranging from ∼0.1c–0.3c, which yields a mildly relativistic case. The projected linear distance between the two hotspots is ∼13 kpc, yielding a linear size (≤20 kpc) of a Compact-Steep-Spectrum (CSS) source. Combined with new high-frequency (νobs ≥ 44 GHz) and archived low-frequency observations (νobs ≤ 8.2 GHz), we find that injection spectra of both NW and SE hotspots can be fitted with a continuous injection (CI) model. Based on the CI model, the synchrotron ages of NW and SE hotspots have an order of 105 yr, consistent with the order of magnitude 103–105 yr observed in CSS sources associated with radio AGNs at an early evolution stage. The CI model also favors the scenario in which the double hotspots have experienced a quiescent phase, suggesting that this RLAGN may have transient or intermittent activities.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.