Automated Detection of Classical Novae with Neural Networks | Zendy

Stephen M. Feeney | Zendy; Vasily Belokurov | Zendy; N. W. Evans | Zendy; J. An | Zendy; P. C. Hewett | Zendy; M. F. Bode | Zendy; M. J. Darnley | Zendy; E. Kerins | Zendy; P. Baillon | Zendy; B. J. Carr | Zendy; S. PaulinHenriksson | Zendy; Andrew Gould | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Automated Detection of Classical Novae with Neural Networks

Author(s) -

Stephen M. Feeney,

Vasily Belokurov,

N. W. Evans,

J. An,

P. C. Hewett,

M. F. Bode,

M. J. Darnley,

E. Kerins,

P. Baillon,

B. J. Carr,

S. PaulinHenriksson,

Andrew Gould

Publication year - 2005

Publication title -

the astronomical journal

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 2.61

H-Index - 271

eISSN - 1538-3881

pISSN - 0004-6256

DOI - 10.1086/430844

Subject(s) - physics , light curve , gravitational microlensing , artificial neural network , astrophysics , set (abstract data type) , identification (biology) , population , variable (mathematics) , astronomy , artificial intelligence , computer science , stars , mathematical analysis , programming language , botany , demography , mathematics , sociology , biology

The POINT-AGAPE collaboration surveyed M31 with the primary goal of opticaldetection of microlensing events, yet its data catalogue is also a prime sourceof lightcurves of variable and transient objects, including classical novae(CNe). A reliable means of identification, combined with a thorough survey ofthe variable objects in M31, provides an excellent opportunity to locate andstudy an entire galactic population of CNe. This paper presents a set of 440neural networks, working in 44 committees, designed specifically to identifyfast CNe. The networks are developed using training sets consisting ofsimulated novae and POINT-AGAPE lightcurves, in a novel variation on K-foldcross-validation. They use the binned, normalised power spectra of thelightcurves as input units. The networks successfully identify 9 of the 13previously identified M31 CNe within their optimal working range (and 11 out of13 if the network error bars are taken into account). They provide a catalogueof 19 new candidate fast CNe, of which 4 are strongly favoured.Comment: 28 pages, 8 figures, The Astronomical Journal (in press

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research