Automated Detection of Classical Novae with Neural Networks

Abstract

The POINT-AGAPE collaboration surveyed M31 with the primary goal of optical detection of microlensing events, yet its data catalogue is also a prime source of lightcurves of variable and transient objects, including classical novae (CNe). A reliable means of identification, combined with a thorough survey of the variable objects in M31, provides an excellent opportunity to locate and study an entire galactic population of CNe. This paper presents a set of 440 neural networks, working in 44 committees, designed specifically to identify fast CNe. The networks are developed using training sets consisting of simulated novae and POINT-AGAPE lightcurves, in a novel variation on K-fold cross-validation. They use the binned, normalised power spectra of the lightcurves as input units. The networks successfully identify 9 of the 13 previously identified M31 CNe within their optimal working range (and 11 out of 13 if the network error bars are taken into account). They provide a catalogue of 19 new candidate fast CNe, of which 4 are strongly favoured.

28 pages, 8 figures, The Astronomical Journal (in press)

References in corpus (9)

• Neural computation as a tool for galaxy classification : methods and examples
• A Short Timescale Candidate Microlensing Event in the POINT-AGAPE Pixel Lensing Survey of M31
• The Point-Agape survey: 4 high signal-to-noise ratio microlensing candidates detected towards M31
• Classical novae from the POINT-AGAPE microlensing survey of M31 -- I. The nova catalogue
• Lightcurve Classification in Massive Variability Surveys
• The automated classification of astronomical lightcurves using Kohonen self-organising maps
• The POINT-AGAPE Survey I: The Variable Stars in M31
• Lightcurve Classification in Massive Variability Surveys II: Transients towards the Large Magellanic Cloud
• A Candidate M31/M32 Intergalactic Microlensing Event

Cited by in corpus (4)

• Classical novae from the POINT-AGAPE microlensing survey of M31 -- II. Rate and statistical characteristics of the nova population
• Comparative performance of selected variability detection techniques in photometric time series
• The OGLE View of Microlensing towards the Magellanic Clouds. I. A Trickle of Events in the OGLE-II LMC data
• On a century of extragalactic novae and the rise of the rapid recurrent novae