论文信息 - Automated Detection of Classical Novae with Neural Networks - 字舞流文

Automated Detection of Classical Novae with Neural Networks

The POINT-AGAPE collaboration surveyed M31 with the primary goal of optical detection of microlensing events, yet its data catalog is also a prime source of light curves 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 light curves in a novel variation on K-fold cross validation and use the binned, normalized power spectra of the light curves 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). The networks provide a catalogue of 19 new candidate fast CNe, of which four are strongly favored.

P. Baillon | Paris | College de France | CERN | Liverpool John Moores University | V. Belokurov | N. W. Evans | S. Paulin-Henriksson | Ohio State University | S. Paulin-Henriksson | P. Hewett | E. Kerins | O. University | París | V. Belokurov | P. Baillon | C. France | N. Evans | M. Darnley | M. Bode | Cern | B. Carr | U. London | E. Kerins | M. Bode | P. C. Hewett | J. An | S. Feeney | A. G. C. University | J. An | University of London | A. Gould | S. Feeney | M. Darnley | B. J. Carr | A. Gould Cambridge University

[1] E. Hubble,et al. No. 376. A spiral nebula as a stellar system. Messier 31. , 1929 .

[2] Cecilia Payne-Gaposchkin,et al. The Galactic Novae , 1958 .

[3] A Short-Timescale Candidate Microlensing Event in the POINT-AGAPE Pixel Lensing Survey of M31 , 2001, astro-ph/0102080.

[4] S. Paulin-Henriksson,et al. A Candidate M31/M32 Intergalactic Microlensing Event , 2002, astro-ph/0206387.

[5] S. Paulin-Henriksson,et al. The POINT-AGAPE survey: 4 high signal-to-noise microlensing candidates detected towards M 31 , 2002, astro-ph/0207025.

[6] N. Wyn Evans,et al. Light-curve classification in massive variability surveys — I. Microlensing , 2002, astro-ph/0211121.

[7] D. Prialnik,et al. An extended grid of multicycle nova evolution models , 1995 .

[8] A. Naim,et al. Neural computation as a tool for galaxy classification: methods and examples , 1995, astro-ph/9508012.

[9] Richard G. West,et al. The automated classification of astronomical light curves using Kohonen self-organizing maps , 2004 .

[10] Heekuck Oh,et al. Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[11] Zurich,et al. The POINT-AGAPE Survey - I. The variable stars in M31 , 2004, astro-ph/0401374.

[12] William H. Press,et al. The Art of Scientific Computing Second Edition , 1998 .

[13] M. Irwin,et al. INT WFS pipeline processing , 2001 .

[14] V. Belokurov,et al. Light-curve classification in massive variability surveys - II. Transients towards the Large Magellanic Cloud , 2004, astro-ph/0404232.

[15] Coryn A. L. Bailer-Jones,et al. NEURAL NETWORK CLASSIFICATION OF STELLAR SPECTRA , 1997 .

[16] Yann Le Du,et al. Lightcurve Classification in Massive Variability Surveys , 2003 .

[17] Zurich,et al. Classical novae from the POINT–AGAPE microlensing survey of M31 – I. The nova catalogue , 2004, astro-ph/0403447.

[18] F. A. Seiler,et al. Numerical Recipes in C: The Art of Scientific Computing , 1989 .

[19] David J. C. MacKay,et al. Information Theory, Inference, and Learning Algorithms , 2004, IEEE Transactions on Information Theory.

[20] Judith G. Cohen,et al. Nova shells. II: Calibration of the distance scale using novae , 1985 .

[21] C. Sterken,et al. Light Curves of Variable Stars: Preface , 1996 .