J/ApJ/920/68 Machine learning predicted AGNs in HSC-Wide region (Chang+, 2021)
Identifying AGN Host Galaxies by Machine Learning with HSC+WISE.
Chang Y.-Y., Hsieh B.-C., Wang W.-H., Lin Y.-T., Lim C.-F., Toba Y.,
Zhong Y.,Chang S.-Y.
<Astrophys. J., 920, 68 (2021)>
=2021ApJ...920...68C 2021ApJ...920...68C
ADC_Keywords: Active gal. nuclei; Photometry, RI
Keywords: Astronomy data analysis ; Active galaxies ; Galaxies ; Surveys
Abstract:
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.
Description:
We use the Wide layer of optical photometry from the Hyper Suprime-Cam
(HSC) Subaru Strategic Program 7 (SSP). The HSC-SSP is an optical
imaging survey with five broadband filters (grizy-band) and four
narrowband filters.
The HSC-SSP wide layer covers six fields (XMM-LSS, GAMA09H, WIDE12H,
GAMA15H, HECTOMAP, and VVDS). The typical seeing is about 0.6" in the
i-band, and the astrometric uncertainty is about 40mas in rms.
File Summary:
--------------------------------------------------------------------------------
FileName Lrecl Records Explanations
--------------------------------------------------------------------------------
ReadMe 80 . This file
table7.dat 65 112609 AGN candidates in HSC-Wide region for 112609 objects
--------------------------------------------------------------------------------
See also:
J/ApJ/640/167 : AGNs and ULIRGs in the CDF-South (Alonso-Herrero+, 2006)
J/A+A/451/457 : X-ray properties of AGN in CDFS (Tozzi+, 2006)
J/MNRAS/391/369 : New z≥3.6 QSOs from FIRST-SDSS DR5 (Carballo+, 2008)
J/ApJ/690/1236 : COSMOS photometric redshift catalog (Ilbert+, 2009)
J/ApJ/728/58 : Swift-BAT survey of AGNs (Burlon+, 2011)
J/AJ/141/189 : Classifiers for star/galaxy separation (Vasconcellos+, 2011)
J/MNRAS/421/1569 : Properties of 18286 SDSS radio galaxies (Best+, 2012)
J/MNRAS/437/968 : AGN automatic photometric classification (Cavuoti+, 2014)
J/ApJ/782/41 : 231 AGN candidates from the 2FGL catalog (Doert+, 2014)
J/ApJS/219/8 : SFR for WISE + SDSS spectroscopic galaxies (Chang+, 2015)
J/ApJ/806/110 : ALESS survey; SMGs in the ECDF-S data (da Cunha+, 2015)
J/ApJ/819/62 : The COSMOS-Legacy Survey (CLS) catalog (Civano+, 2016)
J/ApJS/224/24 : The COSMOS2015 catalog (Laigle+, 2016)
J/ApJ/817/34 : C-COSMOS Legacy multiwavelength catalog (Marchesi+, 2016)
J/MNRAS/457/110 : Northern XMM-XXL field AGN catalog (Menzel+, 2016)
J/ApJ/820/8 : 3FGL sources stat. classifications (Saz Parkinson+, 2016)
J/MNRAS/476/3661 : Morphology of SDSS galaxies (Dominguez+, 2018)
J/A+A/619/A14 : Classification-aided zph estimation (Fotopoulou+, 2018)
J/A+A/611/A97 : Photo. quasar candidates in Stripe 82 (Pasquet-Itam+, 2018)
J/ApJS/243/15 : WERGS. II. SED fitting optical, IR & radio (Toba+, 2019)
J/A+A/651/A108 : AGN catalog from AKARI NEP Wide field (Poliszczuk+, 2021)
http://hsc.mtk.nao.ac.jp/ssp : HyperSuprimeCam Subaru Strategic Prog Public DR2
Byte-by-byte Description of file: table7.dat
--------------------------------------------------------------------------------
Bytes Format Units Label Explanations
--------------------------------------------------------------------------------
1- 17 I17 --- ID objid in HSC-SSP PDR2 (1)
19- 27 F9.5 deg RAdeg [149/152] Right ascension HSC-SSP PDR2 (J2000) (1)
29- 35 F7.5 deg DEdeg [1/4] declination in HSC-SSP PDR2 (J2000) (1)
37- 37 I1 --- XAGN [0/1] 1: X-ray selected AGNs predicted by ML
39- 39 I1 --- IRAGN [0/1] 1: Infrared selected AGNs predicted by ML
41- 41 I1 --- RAGN [0/1] 1: Radio selected AGNs predicted by ML
43- 49 F7.5 --- XAGNp [0.009/0.97] Probability of X-ray selected AGNs
51- 57 F7.5 --- IRAGNp [0.01/0.97] Probability of Infrared selected AGNs
59- 65 F7.5 --- RAGNp [0.01/0.91] Probability of Radio selected AGNs
--------------------------------------------------------------------------------
Note (1): Hyper SuprimeCam Subaru Strategic Program Public Data Release 2
(S19a Wide-layer data), http://hsc.mtk.nao.ac.jp/ssp/
--------------------------------------------------------------------------------
History:
From electronic version of the journal
(End) Prepared by [AAS], Coralie Fix [CDS], 10-Feb-2023