An Active Galactic Nucleus Recognition Model based on Deep Neural Network

Abstract

To understand the cosmic accretion history of supermassive black holes, separating the radiation from active galactic nuclei (AGNs) and star-forming galaxies (SFGs) is critical. However, a reliable solution on photometrically recognising AGNs still remains unsolved. In this work, we present a novel AGN recognition method based on Deep Neural Network (Neural Net; NN). The main goals of this work are (i) to test if the AGN recognition problem in the North Ecliptic Pole Wide (NEPW) field could be solved by NN; (ii) to shows that NN exhibits an improvement in the performance compared with the traditional, standard spectral energy distribution (SED) fitting method in our testing samples; and (iii) to publicly release a reliable AGN/SFG catalogue to the astronomical community using the best available NEPW data, and propose a better method that helps future researchers plan an advanced NEPW database. Finally, according to our experimental result, the NN recognition accuracy is around 80.29% - 85.15%, with AGN completeness around 85.42% - 88.53% and SFG completeness around 81.17% - 85.09%.

12 pages, 12 figures

References in corpus (39)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• The Demography of Massive Dark Objects in Galaxy Centres
• The Galaxy Evolution Explorer: A Space Ultraviolet Survey Mission
• Evolutionary models for very-low-mass stars and brown dwarfs with dusty atmospheres
• COSMOS Photometric Redshifts with 30-bands for 2-deg2
• Spectral Energy Distributions and Multiwavelength Selection of Type 1 Quasars
• SparsePak: A Formatted Fiber Field Unit for The WIYN Telescope Bench Spectrograph. I. Design, Construction, and Calibration
• Mid-Infrared Selection of Active Galaxies
• Obscured and unobscured active galactic nuclei in the Spitzer Space Telescope First Look Survey
• ANNz: estimating photometric redshifts using artificial neural networks
• Red and Reddened Quasars in the Sloan Digital Sky Survey
• Why does deep and cheap learning work so well?
• L2 Regularization for Learning Kernels
• The SDSS-III Baryon Oscillation Spectroscopic Survey: Quasar Target Selection for Data Release Nine
• A New Diagnostic of Active Galactic Nuclei: Revealing Highly-Absorbed Systems at Redshift>0.3
• The Chandra Deep Field North Survey. VI. The Nature of the Optically Faint X-ray Source Population
• Deep Extragalactic Surveys around the Ecliptic Poles with AKARI (ASTRO-F)
• Widespread and Hidden Active Galactic Nuclei in Star-Forming Galaxies at Redshift > 0.3
• AEGIS: Demographics of X-ray and Optically Selected AGNs
• Variability selected high-redshift quasars on SDSS Stripe 82
• An Optical Source Catalog of the North Ecliptic Pole Region
• The North Ecliptic Pole Wide survey of AKARI: a near- and mid-infrared source catalog
• Optical - Near-Infrared catalogue for the AKARI North Ecliptic Pole Deep Field
• Chandra survey in the AKARI North Ecliptic Pole Deep Field. I. X-ray data, point-like source catalog, sensitivity maps, and number counts
• Optical Images and Source Catalog of AKARI North Ecliptic Pole Wide Survey Field
• North Ecliptic Pole Wide Field Survey of AKARI: Survey Strategy and Data Characteristics
• Spitzer Observations of the North Ecliptic Pole
• The Herschel-PACS North Ecliptic Pole Survey
• J and H-band Imaging of AKARI North Ecliptic Pole Survey Field
• An extinction free AGN selection by 18-band SED fitting in mid-infrared in the AKARI NEP deep field
• Identification of AKARI infrared sources by Deep HSC Optical Survey: Construction of New Band-Merged Catalogue in the NEP-Wide field
• Extinction-free Census of AGNs in the $AKARI$/IRC North Ecliptic Pole Field from 23-band Infrared Photometry from Space Telescopes
• Machine Learning Classifiers for Intermediate Redshift Emission Line Galaxies
• CFHT MegaPrime/MegaCam $u$-band source catalogue of the $AKARI$ North Ecliptic Pole Wide field
• The mass--metallicity relation AKARI-FMOS infrared galaxies at $z\sim 0.88$ in the AKARI North Ecliptic Pole Deep Survey Field
• Spectral classification of emission-line galaxies from the Sloan Digital Sky Survey. II. A supplementary diagnostic for AGNs using the Dn(4000) index
• Photometric Redshift Analysis using Supervised Learning Algorithms and Deep Learning
• AGN selection in the AKARI NEP deep field with the fuzzy SVM algorithm
• X-ray - Infrared relation of AGNs and search for highly obscured accretion in the AKARI NEP Field

Cited by in corpus (6)

• Deep learning approach for identification of HII regions during reionization in 21-cm observations
• MillimeterDL: Deep Learning Simulations of the Microwave Sky
• Machine learning technique for morphological classification of galaxies from SDSS. II. The image-based morphological catalogs of galaxies at 0.02<z<0.1
• Consistent analysis of the AGN LF in X-ray and MIR in the XMM-LSS field
• Optically-detected galaxy cluster candidates in the $AKARI$ North Ecliptic Pole field based on photometric redshift from Subaru Hyper Suprime-Cam
• Identifying AGN host galaxies by Machine Learning with HSC+WISE