Automated physical classification in the SDSS DR10. A catalogue of candidate Quasars

TL;DR

This paper demonstrates that machine learning, specifically MLPQNA, can effectively classify astronomical objects in SDSS DR10 using photometric data, producing a large catalog of candidate quasars with high accuracy.

Contribution

The study applies a neural network approach to classify SDSS objects photometrically, creating a comprehensive quasar candidate catalog with high efficiency and purity.

Findings

Achieved 91.31% overall classification efficiency.

Produced a catalog of approximately 3.6 million quasar candidates.

Demonstrated effectiveness of machine learning in photometric classification.

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 multi-band 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 - 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 starforming 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% and a QSO class purity of ~95%. 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.