Two Novel Approaches for Photometric Redshift Estimation based on SDSS and 2MASS

We investigate two training-set methods: support vector machines (SVMs) and Kernel Regression (KR) for photometric redshift estimation with the data from the databases of Sloan Digital Sky Survey Data Release 5 and Two Micron All Sky Survey. We probe the performances of SVMs and KR for different input patterns. Our experiments show that with more parameters considered, the accuracy does not always increase, and only when appropriate parameters are chosen, the accuracy can improve. For different approaches, the best input pattern is different. With different parameters as input, the optimal bandwidth is dissimilar for KR. The rms errors of photometric redshifts based on SVM and KR methods are less than 0.03 and 0.02, respectively. Strengths and weaknesses of the two approaches are summarized. Compared to other methods of estimating photometric redshifts, they show their superiorities, especially KR, in terms of accuracy.

[1]  A. J. Connolly,et al.  Reconstructing Galaxy Spectral Energy Distributions from Broadband Photometry , 1999, astro-ph/9910389.

[2]  Yanxia Zhang,et al.  Automated clustering algorithms for classification of astronomical objects , 2004, astro-ph/0403431.

[3]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[4]  Alexander S. Szalay,et al.  Toward More Precise Photometric Redshifts: Calibration via CCD Photometry , 1997, astro-ph/9703058.

[5]  Bruce Margon,et al.  A Census of Object Types and Redshift Estimates in the SDSS Photometric Catalog from a Trained Decision-Tree Classifier , 2005 .

[6]  Y. Wadadekar.  Estimating Photometric Redshifts Using Support Vector Machines , 2004, astro-ph/0412005.

[7]  Yong-Heng Zhao,et al.  A Comparison of BBN, ADTree and MLP in separating Quasars from Large Survey Catalogues , 2007 .

[8]  Michigan.,et al.  Estimating photometric redshifts with artificial neural networks , 2002, astro-ph/0203250.

[9]  W. T. Vestrand,et al.  Identifying Red Variables in the Northern Sky Variability Survey , 2004 .

[10]  Y. X. Zhang,et al.  Kernel regression for determining photometric redshifts from Sloan broad‐band photometry , 2007, 0706.2704.

[11]  E. Nadaraya.  On Estimating Regression , 1964 .

[12]  Bhasker K. Moorthy,et al.  The First Data Release of the Sloan Digital Sky Survey , 2003, astro-ph/0305492.

[13]  H. Lin,et al.  A Photometric Redshift Galaxy Catalog from the Red-Sequence Cluster Survey , 2005 .

[14]  Xu Zhou,et al.  Photometric redshift determination with the BATC multicolor system , 2002 .

[15]  Edwin L. Turner,et al.  A Catalog of Color-based Redshift Estimates for Z <~ 4 Galaxies in the Hubble Deep Field , 1998 .

[16]  M. Raddick,et al.  The Fifth Data Release of the Sloan Digital Sky Survey , 2007, 0707.3380.

[17]  D. C. Koo,et al.  Optical multicolors - A poor person's z machine for galaxies , 1985 .

[18]  Yong-Heng Zhao,et al.  Estimating Photometric Redshifts with Artificial Neural Networks and Multi-Parameters , 2007 .

[19]  Robert J. Brunner,et al.  Robust Machine Learning Applied to Astronomical Data Sets. II. Quantifying Photometric Redshifts for Quasars Using Instance-based Learning , 2006, astro-ph/0612471.

[20]  Jean-Luc Starck,et al.  Astronomical Data Analysis II , 2002 .

[21]  D. Weedman,et al.  Colors and magnitudes predicted for high redshift galaxies , 1980 .

[22]  E. Spillar,et al.  Photometric Redshifts of Galaxies , 1986 .

[23]  S. Okamura,et al.  Galaxy types in the Sloan Digital Sky survey using supervised artificial neural networks , 2003, astro-ph/0306390.

[24]  M. Skrutskie,et al.  2MASS Extended Source Catalog: Overview and Algorithms , 2000, astro-ph/0004318.

[25]  Roberto Tagliaferri,et al.  Neural Networks for Photometric Redshifts Evaluation , 2003, WIRN.

[26]  M. Way,et al.  Novel Methods for Predicting Photometric Redshifts from Broadband Photometry Using Virtual Sensors , 2006 .

[27]  John E. Davis,et al.  Sloan Digital Sky Survey: Early Data Release , 2002 .

[28]  R. Nichol,et al.  The Application of Photometric Redshifts to the SDSS Early Data Release , 2002, astro-ph/0211080.

[29]  Yanxia Zhang,et al.  Classification of AGNs from stars and normal galaxies by support vector machines , 2002, SPIE Astronomical Telescopes + Instrumentation.

[30]  S. Gunn.  Support Vector Machines for Classification and Regression , 1998 .

[31]  Vladimir Cherkassky,et al.  The Nature Of Statistical Learning Theory , 1997, IEEE Trans. Neural Networks.

[32]  A. Fontana,et al.  Photometric redshifts with the Multilayer Perceptron Neural Network: Application to the HDF-S and SDSS , 2003, astro-ph/0312064.

[33]  E. al.,et al.  The Sloan Digital Sky Survey: Technical summary , 2000, astro-ph/0006396.

[34]  A. Szalay,et al.  Slicing Through Multicolor Space: Galaxy Redshifts from Broadband Photometry , 1995, astro-ph/9508100.

[35]  S. Charlot,et al.  Spectral evolution of stellar populations using isochrone synthesis , 1993 .

[36]  Ofer Lahav,et al.  ANNz: Estimating Photometric Redshifts Using Artificial Neural Networks , 2004 .