J/MNRAS/437/968 AGN automatic photometric classification (Cavuoti+, 2014)
Photometric classification of emission line galaxies with machine-learning
methods.
Cavuoti S., Brescia M., D'Abrusco R., Longo G., Paolillo M.
<Mon. Not. R. Astron. Soc. 437, 968 (2014)>
=2014MNRAS.437..968C 2014MNRAS.437..968C
ADC_Keywords: Active gal. nuclei ; Surveys ; Galaxy catalogs ; Photometry, SDSS
Keywords: methods: data analysis - catalogues - surveys - galaxies: active -
galaxies: Seyfert
Abstract:
In this paper, we discuss an application of machine-learning-based
methods to the identification of candidate active galactic nucleus
(AGN) from optical survey data and to the automatic classification
ofAGNs in broad classes. We applied four different machine-learning
algorithms, namely the Multi Layer Perceptron, trained, respectively,
with the Conjugate Gradient, the Scaled Conjugate Gradient, the Quasi
Newton learning rules and the Support Vector Machines, Q4 to tackle
the problem of the classification of emission line galaxies in
different classes, mainly AGNs versus non-AGNs, obtained using optical
photometry in place of the diagnostics based on line intensity ratios
which are classically used in the literature. Using the same
photometric features, we discuss also the behaviour of the classifiers
on finer AGN classification tasks, namely Seyfert I versus Seyfert II,
and Seyfert versus LINER. Furthermore, we describe the algorithms
employed, the samples of spectroscopically classified galaxies used to
train the algorithms, the procedure followed to select the photometric
parameters and the performances of our methods in terms of multiple
statistical indicators. The results of the experiments show that the
application of self-adaptive data mining algorithms trained on
spectroscopic data sets and applied to carefully chosen photometric
parameters represents a viable alternative to the classical methods
that employ time-consuming spectroscopic observations.
Description:
Photometric catalog of 3,201,824 candidate AGN objects. The objects
are referred to the SDSS DR4 archive (table Galaxy).
File Summary:
--------------------------------------------------------------------------------
FileName Lrecl Records Explanations
--------------------------------------------------------------------------------
ReadMe 80 . This file
dame_agn.dat 96 3201824 Candidate AGN objects from SDSS-DR4
--------------------------------------------------------------------------------
See also:
II/267 : The SDSS Photometric Catalog, Release 4 (Adelman-McCarthy+, 2006)
http://www.sdss.org : SDSS Home Page
Byte-by-byte Description of file: dame_agn.dat
--------------------------------------------------------------------------------
Bytes Format Units Label Explanations
--------------------------------------------------------------------------------
1- 18 I18 --- objID Unique SDSS identifier
20- 28 F9.5 deg RAdeg Right Ascension (J2000)
30- 38 F9.5 deg DEdeg Declination (J2000)
40- 46 F7.5 --- zph [0/0.3] Photometric redshift, computed from
D'Abrusco et al., 2007ApJ...663..752D 2007ApJ...663..752D
49- 54 F6.3 mag rmag r band flux in 3" diameter of the fiber radius
56- 62 F7.3 mag u-g u-g color index from deredenned SDSS magnitudes
64- 70 F7.3 mag g-r g-r color index from deredenned SDSS magnitudes
72- 78 F7.3 mag r-i r-i color index from deredenned SDSS magnitudes
80- 86 F7.3 mag i-z i-z color index from deredenned SDSS magnitudes
89- 94 F6.3 mag rmag0 Simplified r magnitude corrected for extinction
96 I1 --- AGN [1/3] Quality Flag of the AGN classification:
1=basic, 2=medium, 3=high quality
--------------------------------------------------------------------------------
Acknowledgements:
Stefano Cavuoti, stefano.cavuoti(at)gmail.com
History:
* 30-Oct-2013: original file from the first author
* 22-Jun-2014: file reformatted (removed useless digits)
(End) Stefano Cavuoti [INAF-OACN, Italy], Patricia Vannier [CDS] 30-Oct-2013