2022A&A...666A.171D


Query : 2022A&A...666A.171D

2022A&A...666A.171D - Astronomy and Astrophysics, volume 666A, 171 (2022/10-1)

ULISSE: A tool for one-shot sky exploration and its application for detection of active galactic nuclei.

DOORENBOS L., TORBANIUK O., CAVUOTI S., PAOLILLO M., LONGO G., BRESCIA M., SZNITMAN R. and MARQUEZ-NEILA P.

Abstract (from CDS):


Context. Modern sky surveys are producing ever larger amounts of observational data, which makes the application of classical approaches for the classification and analysis of objects challenging and time consuming. However, this issue may be significantly mitigated by the application of automatic machine and deep learning
Methods.
Aims. We propose ULISSE, a new deep learning tool that, starting from a single prototype object, is capable of identifying objects that share common morphological and photometric properties, and hence of creating a list of candidate lookalikes. In this work, we focus on applying our method to the detection of active galactic nuclei (AGN) candidates in a Sloan Digital Sky Survey galaxy sample, because the identification and classification of AGN in the optical band still remains a challenging task in extragalactic astronomy. Methods. Intended for the initial exploration of large sky surveys, ULISSE directly uses features extracted from the ImageNet dataset to perform a similarity search. The method is capable of rapidly identifying a list of candidates, starting from only a single image of a given prototype, without the need for any time-consuming neural network training.
Results. Our experiments show ULISSE is able to identify AGN candidates based on a combination of host galaxy morphology, color, and the presence of a central nuclear source, with a retrieval efficiency ranging from 21% to 65% (including composite sources) depending on the prototype, where the random guess baseline is 12%. We find ULISSE to be most effective in retrieving AGN in early-type host galaxies, as opposed to prototypes with spiral- or late-type properties.
Conclusions. Based on the results described in this work, ULISSE could be a promising tool for selecting different types of astro-physical objects in current and future wide-field surveys (e.g., Euclid, LSST etc.) that target millions of sources every single night.

Abstract Copyright: © L. Doorenbos et al. 2022

Journal keyword(s): methods: statistical - catalogs - galaxies: active - techniques: image processing

Simbad objects: 13

goto Full paper

goto View the references in ADS

Number of rows : 13
N Identifier Otype ICRS (J2000)
RA
ICRS (J2000)
DEC
Mag U Mag B Mag V Mag R Mag I Sp type #ref
1850 - 2024
#notes
1 Mrk 609 Sy2 03 25 25.3590639624 -06 08 37.947546528   14.72 14.12 10.9   ~ 199 0
2 LEDA 1539380 G 07 52 19.8038883864 +17 42 10.385012916           ~ 3 0
3 SDSS J083114.54+524224.7 EmG 08 31 14.5392915648 +52 42 24.829940268           ~ 11 0
4 Z 150-14 Sy2 08 40 02.336 +29 49 02.73   20.00 19.62     ~ 193 1
5 LEDA 2124782 G 11 05 11.0796901728 +38 21 29.319700176           ~ 6 0
6 2MASX J11592857+4235430 EmG 11 59 28.6222176888 +42 35 42.795897036           ~ 4 0
7 MCG+05-31-036 AGN 12 57 54.3651088944 +27 29 26.392988076   16.38   15.02   ~ 49 1
8 NGC 5231 Sy2 13 35 48.2437115688 +02 59 56.044488912   14.25 16.15     ~ 77 1
9 LEDA 48418 G 13 40 59.8020664632 +30 20 58.076993976   15.705       ~ 12 0
10 Z 49-26 G 15 11 05.13336 +05 31 12.7308   15.7       ~ 12 0
11 2MASX J15112156+0722508 LIN 15 11 21.5281179720 +07 22 50.657694384   15       ~ 10 0
12 2MASS J15362130+2229135 Sy1 15 36 21.3056423640 +22 29 13.583676336   18.67 17.91     ~ 9 0
13 MCG+07-34-146 GiC 16 46 07.0044876048 +42 27 37.459823940   15       ~ 8 0

To bookmark this query, right click on this link: simbad:objects in 2022A&A...666A.171D and select 'bookmark this link' or equivalent in the popup menu