Automated physical classification in the SDSS DR10. A catalogue of candidate quasars
Date Issued
2015
Author(s)
Description
The authors wish to thank the anonymous referee for all very useful comments and suggestions which greatly helped to clarify and to improve the readability of the paper. The authors wish to acknowledge the financial support from the PRIN 2011 MIUR grant Cosmology with Euclid . MB acknowledges financial support from PRIN-INAF 2014 Glittering Kaleidoscopes in the sky, the multifaceted nature and role of galaxy clusters . We made use of Topcat tool developed within the Virtual Observatory, and the data mining infrastructure DAMEWARE. This research has made use of the SDSS III DR10 and VizieR catalogue data access tools.
Abstract
We discuss whether modern machine learning methods can be used to characterize the physical nature of the large number of objects sampled by the modern multiband digital surveys. In particular, we applied the MLPQNA (Multi Layer Perceptron with Quasi Newton Algorithm) method to the optical data of the Sloan Digital Sky Survey (SDSS) Data Release 10, investigating whether photometric data alone suffice to disentangle different classes of objects as they are defined in the SDSS spectroscopic classification. We discuss three groups of classification problems: (i) the simultaneous classification of galaxies, quasars and stars; (ii) the separation of stars from quasars; (iii) the separation of galaxies with normal spectral energy distribution from those with peculiar spectra, such as starburst or star-forming galaxies and AGN. While confirming the difficulty of disentangling AGN from normal galaxies on a photometric basis only, MLPQNA proved to be quite effective in the three-class separation. In disentangling quasars from stars and galaxies, our method achieved an overall efficiency of 91.31 per cent and a QSO class purity of ̃95 per cent. The resulting catalogue of candidate quasars/AGNs consists of ̃3.6 million objects, of which about half a million are also flagged as robust candidates, and will be made available on CDS VizieR facility.
Volume
450
Issue
4
Start page
3893
Issn Identifier
0035-8711
Ads BibCode
2015MNRAS.450.3893B
Rights
open.access
File(s)![Thumbnail Image]()
Loading...
Name
stv854.pdf
Size
700.35 KB
Format
Adobe PDF
Checksum (MD5)
e4b65b5a65b59bfcff6ca99bc3b25f57