Fast nonlinear regression via eigenimages applied to galactic morphology

ABSTRACT

Astronomy increasingly faces the issue of massive, unwieldly data sets. The Sloan Digital Sky Survey (SDSS) [11] has so far generated tens of millions of images of distant galaxies, of which only a tiny fraction have been morphologically classified. Morphological classification in this context is achieved by fitting a parametric model of galaxy shape to a galaxy image. This is a nonlinear regression problem, whose challenges are threefold, 1) blurring of the image caused by atmosphere and mirror imperfections, 2) large numbers of local minima, and 3) massive data sets.Our strategy is to use the eigenimages of the parametric model to form a new feature space, and then to map both target image and the model parameters into this feature space. In this low-dimensional space we search for the best image-to-parameter match. To search the space, we sample it by creating a database of many random parameter vectors (prototypes) and mapping them into the feature space. The search problem then becomes one of finding the best prototype match, so the fitting process a nearest-neighbor search.In addition to the savings realized by decomposing the original space into an eigenspace, we can use the fact that the model is a linear sum of functions to reduce the prototypes further: the only prototypes stored are the components of the model function. A modified form of nearest neighbor is used to search among them.Additional complications arise in the form of missing data and heteroscedasticity, both of which are addressed with weighted linear regression. Compared to existing techniques, speed-ups ach-ieved are between 2 and 3 orders of magnitude. This should enable the analysis of the entire SDSS dataset.

REFERENCES

• 1: N. Ball, M. Fukugita, O. Nakamura, S. Okamura, J. Brinkmann, and R. J. Brunner. Galaxy Types in the Sloan Digital Sky Survey Using Supervised Artificial Neural Networks. Mon.Not.Roy.Astron.Soc., 348:1038, 2004.
• 2: K. C. Freeman. On the Disks of Spiral and s0 Galaxies. Astrophysical Journal, 160:811, 1970.
• 3: E. Hubble. The realm of the nebulae. Yale University Press, 1936.
• 4: Mathworks Inc. Matlab, version 6, release 13, 2003.
• 5: S. Kirshner, I. Cadez, P. Smyth, and C. Kamath. Learning to classify galaxy shapes using the EM algorithm. In Advances in Neural Information Processing Systems, volume 15. Morgan Kaufmann, 2002.
• 6: J. Kormendy. Brightness distributions in compact and normal galaxies. III - Decomposition of observed profiles into spheroid and disk components. Astrophysical Journal, 217:406--419, 1977.
• 7: C. Y. Peng, L. C. Ho, C. D. Impey, and H. Rix. Detailed Structural Decomposition of Galaxy Images. Astronomical Journal, 124:266--293, 2002.
• 8: K. Ratnatunga, R. Griffiths, and E. Ostrander. Disk And Bulge Morphology Of Wfpc2 Galaxies: The Hst Medium Deep Survey Database. accepted to Astronomical Journal, 1999.
• 9: Luc Simard, Christopher N. A. Willmer, Nicole P. Vogt, Vicki L. Sarajedini, Andrew C. Phillips, Benjamin J. Weiner, David C. Koo, Myungshin Im, Garth D. Illingworth, and S. M. Faber. The Deep Groth Strip Survey II. Hubble Space Telescope Structural Parameters of Galaxies in the Groth Strip. Astrophysical Journal Supplements, 142(1), 2002.
• 10: N. Slonim, R. Somerville, N. Tishby, and O. Lahav. Objective Classification of Galaxy Spectra using the Information Bottleneck Method. Monthly Notices to the Royal Astronomical Society, 323, 2001.
• 11: D. G. York, J. Adelman, J.E. Anderson, and et al. The Sloan Digital Sky Survey: Technical Summary. Astronomical Journal, 120:1579--1587, 2000.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.5 PATTERN RECOGNITION
      I.5.5 Implementation

General Terms:
Algorithms

Keywords:
astronomy, morphology, nearest neighbor, pincipal component analysis, regression