Photometric redshift estimation based on data mining with PhotoRApToR

详细信息    查看全文

• 作者：S. Cavuoti (1)
  M. Brescia (1)
  V. De Stefano (2)
  G. Longo (2)
  
  1. INAF - Astronomical Observatory of Capodimonte ; Napoli ; Italy
  2. Department of Physics ; University Federico II of Naples ; Naples ; Italy
  
• 关键词：Techniques ; photometric ; Galaxies ; distances and redshifts ; Galaxies ; photometry ; Cosmology ; observations ; Methods ; data analysis
• 刊名：Experimental Astronomy
• 出版年：2015
• 出版时间：March 2015
• 年：2015
• 卷：39
• 期：1
• 页码：45-71
• 全文大小：3,029 KB
• 参考文献：1. Albrecht, A., Bernstein, G., Cahn, R., et al.: Report of the Dark Energy Task Force (2006)
  2. ANSI (American National Standards Institute), et al.: American National Standard Code for Information Interchange. The Institute (1977)
  3. Bengio, Y., LeCun, J.: In Large-Scale Kernel Machines. MIT Press (2007)
  4. Biviano, A (2013) CLASH-VLT: The mass, velocity-anisotropy, and pseudo-phase-space density profiles of the z=0.44 cluster, galaxy MACS 1206.2-0847. A&A 558: pp. A1 CrossRef
  5. Breiman, L.: Random Forests. Machine Learning, Springer Eds., 45, 1, 25鈥?2 (2001)
  6. Brescia, M.: New Trends in E-Science: Machine Learning and Knowledge Discovery in Databases, 78 pages, Horizons in Computer Science Research. In: Clary, T.S. (ed.) Series Horizons in Computer Science. ISBN: 978-1-61942-774-7, Vol. 7. Nova Science Publishers (2012)
  7. Brescia, M, Cavuoti, S, Paolillo, M, Longo, G, Puzia, T (2012) The detection of Globular Clusters in galaxies as a data mining problem. MNRAS 421: pp. 1155 CrossRef
  8. Brescia, M, Cavuoti, S, D鈥橝brusco, R, Longo, G, Mercurio, A (2013) Photometric redshifts for Quasars in multi band Surveys. ApJ 772: pp. 140 CrossRef
  9. Brescia, M (2014) DAMEWARE: A web cyberinfrastructure for astrophysical data mining. PASP 126: pp. 783-797
  10. Brescia, M, Cavuoti, S, De Stefano, V, Longo, G (2014) A catalogue of photometric redshifts for the SDSS-DR9 galaxies. A&A 568: pp. A126 CrossRef
  11. Brescia, M., Cavuoti, S., Longo, G.: Automated physical classification in the SDSS DR10. A catalogue of candidate Quasars, MNRAS, accepted (in press) (2015)
  12. Byrd, RH, Nocedal, J, Schnabel, RB (1994) Math. Program. 63: pp. 129 CrossRef
  13. Capozzi, D, De Filippis, E, Paolillo, M, D鈥橝brusco, R, Longo, G (2009) The properties of the heterogeneous Shakhbazyan groups of galaxies in the SDSS. Mon. Not. R. Astron. Soc. 396: pp. 900-917 CrossRef
  14. Cavuoti, S, Brescia, M, Longo, G, Mercurio, A (2012) Photometric redshifts with Quasi Newton Algorithm (MLPQNA). Results in the PHAT1 contest. A&A 546: pp. 1-8
  15. Cavuoti, S, Brescia, M, D鈥橝brusco, R, Longo, G, Paolillo, M (2014) Photometric classification of emission line galaxies with machine-learning methods. MNRAS 437: pp. 968-975 CrossRef
  16. Collister, AA, Lahav, O (2004) ANNz: Estimating Photometric Redshifts Using Artificial Neural Networks. PASP 116: pp. 345 CrossRef
  17. Connolly, AJ, Csabai, I, Szalay, AS, Koo, DC, Kron, RG, Munn, JA (1995) Slicing Through Multicolor Space: Galaxy Redshifts from Broadband Photometry. Astron. J. 110: pp. 2655 CrossRef
  18. Cybenko, G (1989) Approximations by superpositions of sigmoidal functions. Math. Control Signals Syst. 2: pp. 303 CrossRef
  19. The Dark Energy Survey Collaboration, The Dark Energy Survey, White Paper submitted to the Dark Energy Task Force, 42 pages. arXiv:0510346 (2005)
  20. Davidon, W.C.: SIAM Journal on Optimization (1991)
  21. Dietterich, T (1995) Overfitting and Undercomputing in Machine Learning. Comput. Surv. 27: pp. 326 CrossRef
  22. Drucker, H.: Improving regressors using boosting techniques. In: Proceedings of ICML97, pp. 107鈥?15. Morgan Kaufmann Publishers Inc., San Francisco (1997)
  23. Euclid Red Book, ESA Technical Document, ESA/SRE(2011)12, Issue 1.1. arXiv:1110.3193 (2011)
  24. Farrow, DJ (2014) Pan-STARRS1: Galaxy clustering in the Small Area Survey 2. MNRAS 437: pp. 748-770 CrossRef
  25. Geisser, S (1975) The predictive sample reuse method with applications. J. Am. Stat. Assoc. 70: pp. 320-328 CrossRef
  26. Groetsch, C.V.: The Theory of Tikhonov Regularization for Fredholm Equations of the First Kind, Pitman, Boston (1984)
  27. Hildebrandt, H, Arnouts, S, Capak, P, Wolf, C (2010) A&A 523: pp. 31 CrossRef
  28. Hoaglin, DC, Mosteller, F, Tukey, JW (1983) Understanding Robust and Exploratory Data Analysis. Wiley C, New York
  29. Hoyle, B., Rau, M.M., Zitlau, R., Seitz, S., Weller, J.: Feature importance for machine learning redshifts applied to SDSS galaxies, Sumitted to MNRAS. arXiv:1410.4696 (2014)
  30. Ilbert, O, Capak, P, Salvato, M (2009) Cosmos Photometric Redshifts with 30-bands for 2鈭抎eg2. Astrophys. J. 690: pp. 1236 CrossRef
  31. Ivezic, Z., et al.: (the LSST team), The LSST Science Book, v2.0 (2009)
  32. Kearns, M.: In: Touretzky, D.S., Mozer, M.C., Hasselmo, M.E. (eds.) : A Bound on the Error of Cross Validation Using the Approximation and Estimation Rates, with Consequences for Training-Test Split, Neural Information Processing 8, pp. 183鈥?89. Morgan Kaufmann (1996)
  33. Laureijs, R., et al.: Euclid Definition Study Report, ESA/SRE(2011)12, Issue 1.1 (2011)
  34. Marlin, BM (2008) Missing data problems in machine learning. Library and Archives, Canada
  35. Mobasher, B, Capak, P (2007) Photometric Redshifts of Galaxies in COSMOS. Astrophys. J. Suppl. Ser. 172: pp. 117-131 CrossRef
  36. Nissen, S.: Implementation of a Fast Artificial Neural Network Library. Technical Report. Department of Computer Science University of Copenhagen (DIKU) (2003)
  37. Peacock, J.A., Schneider, P., Efstathiou, G., et al.: ESA-ESO Working Group on Fundamental Cosmology, ESA-ESO Working Group on Fundamental Cosmology. Tech. Rep. (2006)
  38. Pedregosa, F (2011) Scikit-learn: Machine Learning in Python. JMLR 12: pp. 2825-2830
  39. Pennebaker, W.B., Mitchell, J.L.: JPEG still image data compression standard, (3rd ed.) (1993)
  40. Provost, F., Fawcett, T., Kohavi, R.: The Case Against Accuracy Estimation for Comparing Induction Algorithms. In: Kaufmann, M. (ed.) Proceedings of the 15th International Conference on Machine Learning, pp. 445鈥?53 (1998)
  41. Repici, J.: How To: The Comma Separated Value (CSV) File Format. Creativyst Inc (2010)
  42. Rosenblatt, F (1961) Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms. Spartan Books, Washington
  43. Rubinstein, R.Y., Kroese D.P.: The Cross-Entropy Method: A Unified Approach to Combinatorial Optimization, Monte-Carlo Simulation, and Machine Learning. Springer, New York (2004)
  44. Serjeant, S (2014) Up to 100,000 Reliable Strong Gravitational Lenses in Future Dark Energy Experiments. ApJ 793: pp. L10 CrossRef
  45. Stehman, SV (1997) Selecting and interpreting measures of thematic classification accuracy. Remote Sens. Environ. 62: pp. 77-89 CrossRef
  46. Tagliaferri, R, Longo, G, Andreon, S, Capozziello, S, Donalek, C, Giordano, G (2002) Neural Networks and Photometric Redshifts, Neural Nets. Lect. Notes Comput. Sci 2859: pp. 226-234 CrossRef
  47. Taylor, MB (2006) STILTS - A Package for Command-Line Processing of Tabular Data. Proceedings of the Astronomical Data Analysis Software and Systems XV ASP Conference Series 351: pp. 666
  48. Umetsu, K, Medezinski, E, Nonino, M (2012) CLASH: Mass Distribution in and around MACS J1206.2-0847 from a Full Cluster Lensing Analysis. ApJ 755: pp. 56 CrossRef
  49. Wells, DC, Greisen, EW, Harten, RH (1981) FITS: a Flexible Image transport System. Astron. Astrophys. Supplement Series 44: pp. 363
  
• 刊物类别：Physics and Astronomy
• 刊物主题：Physics
  Astronomy
  Statistics for Engineering, Physics, Computer Science, Chemistry and Geosciences
  
• 出版者：Springer Netherlands
• ISSN：1572-9508

文摘

Photometric redshifts (photo-z) are crucial to the scientific exploitation of modern panchromatic digital surveys. In this paper we present PhotoRApToR (Photometric Research Application To Redshift): a Java/C ++ based desktop application capable to solve non-linear regression and multi-variate classification problems, in particular specialized for photo-z estimation. It embeds a machine learning algorithm, namely a multi-layer neural network trained by the Quasi Newton learning rule, and special tools dedicated to pre- and post-processing data. PhotoRApToR has been successfully tested on several scientific cases. The application is available for free download from the DAME Program web site.