Parameter Extraction from RVS Stellar Spectra by Means of Artificial Neural Networks and Spectral Density Analysis

  • Diego Ordóñez
  • Carlos Dafonte
  • Minia Manteiga
  • Bernardino Arcay
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5271)


The Gaia Galactic Survey Satellite is among the key future missions of the European Space Agency, who plans its launch near the end of 2011. Gaia will carry out what is being called a “Galaxy Survey”, gathering exact information on the nature of the galaxy’s main constituents, including the spectra of objects. A first approach to the extraction of atmospheric parameters from spectra (Effective Temperature (Teff), Gravity (log G), Metallicity ([Fe/H]), and Alpha elements abundance ([α/Fe])) was their indirect measurement by means of the Morgan-Keenan (MK) classification system. However, traditional methods based on MK are slow and subjective. This is why an automatic and robust method has become an essential requirement. This work presents the preliminary results of a study on the automatic extraction potential of the main atmospheric stellar parameters: Teff, log G, [Fe/H], and [α/Fe] in the spectral region of the RVS, between 8470 and 8740 Å. The study was carried out by means of an algorithm based on artificial neural networks which is a technique widely used in that kind of automatic spectral parameterisation.


stellar spectra signal processing spectral density FFT SNR Artificial Neural Network feed-forward backpropagation wavelet 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bailer-Jones, C.A.L.: A method for exploiting domain information in astrophysical parameter estimation. In: Astronomical Data Analysis Software and Systems XVII. ASP Conference Series, vol. XXX, London (2008)Google Scholar
  2. 2.
    Kaempf, T.A., Willemsen, P.G., Bailer-Jones, C.A.L., de Boer, K.S.: Parameterisation of RVS spectra with Artificial Neural Networks – First Steps. In: 10th RVS workshop, Cambridge (September 2005)Google Scholar
  3. 3.
    Bailer -Jones, C.A.L.: Stellar parameters from very low resolution spectra and medium band filters. Astronomy and Astrophysics 357, 197–205 (2000)Google Scholar
  4. 4.
    Christlieb, N., Wisotzki, L., Graβhoff, G.: Statistical Methods of automatic spectral classification and their application to the Hamburg/ESO sourvey. Astronomy and Astrophysics 391, 397–406 (2002)CrossRefGoogle Scholar
  5. 5.
    Von Hippel, T., Allende, C., Sneden, C.: Automated Stellar Spectral Classification and Parameterization for the Masses. In: The Garrison Festschrift conference proceedings, June 10 - 11 (2002)Google Scholar
  6. 6.
    Allende, C., Rebolo, R., Garcia, R., Serra-Ricart, M.: The INT Search for Metal-Poor Stars. Spectroscopic Observations and Classification via Artificial Neural Networks. The Astronomical Journal 120, 1516–1531 (2000)CrossRefGoogle Scholar
  7. 7.
    Fiorentin, P.R., Bailer-Jones, C.A.L., Lee, Y.S., Beers, T.C., Sivarani, T., Wilhelm, R., Allende, C., Norris, J.E.: Estimation of stellar atmospheric parameters from SDSS/SEGUE spectra. Astronomy and Astrophysics 467, 1373–1387 (2007)CrossRefGoogle Scholar
  8. 8.
    Recio-Blanco, A., Bijaoui, A., de Laverny, P.: Automated derivation of stellar atmospheric parameters and chemical abundances: the MATISSE algorithm. R. Astron. Soc., 1–11 (2002)Google Scholar
  9. 9.
    Morgan, W.W., Keenan, P.C., Kellman, E.: An atlas of stellar spectra with outline of spectral classification. Astrophys. Monographs. University of Chicago Press (1943)Google Scholar
  10. 10.
    GAIA: The galactic census problem,
  11. 11.
    Cooley, J.W., Tukey, J.W.: An algorithm for the machine calculation of complex Fourier series. Math. Comput. 19, 297–301 (1965)zbMATHCrossRefMathSciNetGoogle Scholar
  12. 12.
    Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323, 533–536 (1986)CrossRefGoogle Scholar
  13. 13.
    Harinder, P., Gulati, R.K., Gupta, R.: Stellar Spectral Classification using Principal Component Analysis and Artificial Neural Networks. In: MNRAS, vol. 295, pp. 312–318 (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Diego Ordóñez
    • 1
  • Carlos Dafonte
    • 1
  • Minia Manteiga
    • 2
  • Bernardino Arcay
    • 1
  1. 1.Information and Comunications Technologies Department, Faculty of Computer ScienceUniversity of A CoruñaA CoruñaSpain
  2. 2.Department of Navigation and Earth SciencesUniversity of A CoruñaA CoruñaSpain

Personalised recommendations