Galaxy types in the Sloan Digital Sky survey using supervised artificial neural networks

N. M. Ball, J. Loveday, M. Fukugita, Osamu Nakamura, S. Okamura, J. Brinkmann, R. J. Brunner

Research output: Contribution to journalArticle

89 Citations (Scopus)

Abstract

Supervised artificial neural networks are used to predict useful properties of galaxies in the Sloan Digital Sky Survey, in this instance morphological classifications, spectral types and redshifts. By giving the trained networks unseen data, it is found that correlations between predicted and actual properties are around 0.9 with rms errors of order ten per cent. Thus, given a representative training set, these properties may be reliably estimated for galaxies in the survey for which there are no spectra and without human intervention.

Original languageEnglish
Pages (from-to)1038-1046
Number of pages9
JournalMonthly Notices of the Royal Astronomical Society
Volume348
Issue number3
Publication statusPublished - 2004 Mar 1
Externally publishedYes

Fingerprint

artificial neural network
galaxies
education

Keywords

  • Galaxies: fundamental parameters
  • Galaxies: photometry
  • Galaxies: statistics
  • Methods: data analysis
  • Methods: statistical

ASJC Scopus subject areas

  • Space and Planetary Science

Cite this

Ball, N. M., Loveday, J., Fukugita, M., Nakamura, O., Okamura, S., Brinkmann, J., & Brunner, R. J. (2004). Galaxy types in the Sloan Digital Sky survey using supervised artificial neural networks. Monthly Notices of the Royal Astronomical Society, 348(3), 1038-1046.

Galaxy types in the Sloan Digital Sky survey using supervised artificial neural networks. / Ball, N. M.; Loveday, J.; Fukugita, M.; Nakamura, Osamu; Okamura, S.; Brinkmann, J.; Brunner, R. J.

In: Monthly Notices of the Royal Astronomical Society, Vol. 348, No. 3, 01.03.2004, p. 1038-1046.

Research output: Contribution to journalArticle

Ball, NM, Loveday, J, Fukugita, M, Nakamura, O, Okamura, S, Brinkmann, J & Brunner, RJ 2004, 'Galaxy types in the Sloan Digital Sky survey using supervised artificial neural networks', Monthly Notices of the Royal Astronomical Society, vol. 348, no. 3, pp. 1038-1046.
Ball, N. M. ; Loveday, J. ; Fukugita, M. ; Nakamura, Osamu ; Okamura, S. ; Brinkmann, J. ; Brunner, R. J. / Galaxy types in the Sloan Digital Sky survey using supervised artificial neural networks. In: Monthly Notices of the Royal Astronomical Society. 2004 ; Vol. 348, No. 3. pp. 1038-1046.
@article{110febbbd9914854a91f4656c690614e,
title = "Galaxy types in the Sloan Digital Sky survey using supervised artificial neural networks",
abstract = "Supervised artificial neural networks are used to predict useful properties of galaxies in the Sloan Digital Sky Survey, in this instance morphological classifications, spectral types and redshifts. By giving the trained networks unseen data, it is found that correlations between predicted and actual properties are around 0.9 with rms errors of order ten per cent. Thus, given a representative training set, these properties may be reliably estimated for galaxies in the survey for which there are no spectra and without human intervention.",
keywords = "Galaxies: fundamental parameters, Galaxies: photometry, Galaxies: statistics, Methods: data analysis, Methods: statistical",
author = "Ball, {N. M.} and J. Loveday and M. Fukugita and Osamu Nakamura and S. Okamura and J. Brinkmann and Brunner, {R. J.}",
year = "2004",
month = "3",
day = "1",
language = "English",
volume = "348",
pages = "1038--1046",
journal = "Monthly Notices of the Royal Astronomical Society",
issn = "0035-8711",
publisher = "Oxford University Press",
number = "3",

}

TY - JOUR

T1 - Galaxy types in the Sloan Digital Sky survey using supervised artificial neural networks

AU - Ball, N. M.

AU - Loveday, J.

AU - Fukugita, M.

AU - Nakamura, Osamu

AU - Okamura, S.

AU - Brinkmann, J.

AU - Brunner, R. J.

PY - 2004/3/1

Y1 - 2004/3/1

N2 - Supervised artificial neural networks are used to predict useful properties of galaxies in the Sloan Digital Sky Survey, in this instance morphological classifications, spectral types and redshifts. By giving the trained networks unseen data, it is found that correlations between predicted and actual properties are around 0.9 with rms errors of order ten per cent. Thus, given a representative training set, these properties may be reliably estimated for galaxies in the survey for which there are no spectra and without human intervention.

AB - Supervised artificial neural networks are used to predict useful properties of galaxies in the Sloan Digital Sky Survey, in this instance morphological classifications, spectral types and redshifts. By giving the trained networks unseen data, it is found that correlations between predicted and actual properties are around 0.9 with rms errors of order ten per cent. Thus, given a representative training set, these properties may be reliably estimated for galaxies in the survey for which there are no spectra and without human intervention.

KW - Galaxies: fundamental parameters

KW - Galaxies: photometry

KW - Galaxies: statistics

KW - Methods: data analysis

KW - Methods: statistical

UR - http://www.scopus.com/inward/record.url?scp=1542327730&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1542327730&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:1542327730

VL - 348

SP - 1038

EP - 1046

JO - Monthly Notices of the Royal Astronomical Society

JF - Monthly Notices of the Royal Astronomical Society

SN - 0035-8711

IS - 3

ER -