CERN Accelerating science

Article
Report number	astro-ph/0504236
Title	Automated Detection of Classical Novae with Neural Networks
Author(s)	Feeney, S. (Cambridge U., Inst. of Astron.) ; Belokurov, V. (Cambridge U., Inst. of Astron.) ; Evans, N.W. (Cambridge U., Inst. of Astron.) ; An, J. (Cambridge U., Inst. of Astron.) ; Hewett, Paul C. (Cambridge U., Inst. of Astron.) ; Bode, M. (Liverpool John Moores U., ARI) ; Darnley, M. (Liverpool John Moores U., ARI) ; Kerins, E. (Liverpool John Moores U., ARI) ; Baillon, P. (CERN) ; Carr, Bernard J. (Queen Mary, U. of London, Math. Sci.) ; Paulin-Henriksson, S. (College de France) ; Gould, A. (Ohio State U., Dept. Astron.)
Affiliation	(CERN) ; (Cambridge University,) ; (College de France, Paris,) ; (Liverpool John Moores University,) ; (Ohio State University) ; (University of London,)
Publication	2005
Imprint	11 Apr 2005
Number of pages	28
In:	Astron. J. 130 (2005) 84-94
DOI	10.1086/430844
Subject category	Astrophysics and Astronomy
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.

Corresponding record in: Inspire