Measuring photometric redshifts using galaxy images and Deep Neural Networks

We propose a new method to estimate the photometric redshift of galaxies by using the full galaxy image in each measured band. This method draws from the latest techniques and advances in machine learning, in particular Deep Neural Networks. We pass the entire multi-band galaxy image into the machine learning architecture to obtain a redshift estimate that is competitive with the best existing standard machine learning techniques. The standard techniques estimate redshifts using post-processed features, such as magnitudes and colours, which are extracted from the galaxy images and are deemed to be salient by the user. This new method removes the user from the photometric redshift estimation pipeline. However we do note that Deep Neural Networks require many orders of magnitude more computing resources than standard machine learning architectures.

[1]  Sander Dieleman,et al.  Rotation-invariant convolutional neural networks for galaxy morphology prediction , 2015, ArXiv.

[2]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[3]  D. Schlegel,et al.  Maps of Dust Infrared Emission for Use in Estimation of Reddening and Cosmic Microwave Background Radiation Foregrounds , 1998 .

[4]  Robert Lupton,et al.  A Modified Magnitude System that Produces Well-Behaved Magnitudes, Colors, and Errors Even for Low Signal-to-Noise Ratio Measurements , 1999, astro-ph/9903081.

[5]  R. Nichol,et al.  Photometric redshift analysis in the Dark Energy Survey Science Verification data , 2014, 1406.4407.

[6]  W. M. Wood-Vasey,et al.  SDSS-III: MASSIVE SPECTROSCOPIC SURVEYS OF THE DISTANT UNIVERSE, THE MILKY WAY, AND EXTRA-SOLAR PLANETARY SYSTEMS , 2011, 1101.1529.

[7]  Jiangang Hao,et al.  ArborZ: PHOTOMETRIC REDSHIFTS USING BOOSTED DECISION TREES , 2009, The Astrophysical Journal.

[8]  Walter A. Siegmund,et al.  The 2.5 m Telescope of the Sloan Digital Sky Survey , 2006, astro-ph/0602326.

[9]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[10]  D. A. García-Hernández,et al.  THE TENTH DATA RELEASE OF THE SLOAN DIGITAL SKY SURVEY: FIRST SPECTROSCOPIC DATA FROM THE SDSS-III APACHE POINT OBSERVATORY GALACTIC EVOLUTION EXPERIMENT , 2013, 1307.7735.

[11]  Eibe Frank,et al.  Accurate photometric redshift probability density estimation – method comparison and application , 2015, 1503.08215.

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

[13]  C. Donalek,et al.  Neural networks and photometric redshifts , 2002 .

[14]  J. Friedman.  Special Invited Paper-Additive logistic regression: A statistical view of boosting , 2000 .

[15]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[16]  Kerstin Paech,et al.  Anomaly detection for machine learning redshifts applied to SDSS galaxies , 2015, 1503.08214.

[17]  Yoshua Bengio,et al.  Convolutional networks for images, speech, and time series , 1998 .

[18]  Kazuhiro Shimasaku,et al.  The ugriz Standard-Star System , 2002 .

[19]  Joseph E. Gonzalez,et al.  GraphLab: A New Parallel Framework for Machine Learning , 2010 .

[20]  D. Gerdes,et al.  PHAT: PHoto-z Accuracy Testing , 2010, 1008.0658.

[21]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[22]  J. Weller,et al.  Data augmentation for machine learning redshifts applied to Sloan Digital Sky Survey galaxies , 2015, 1501.06759.

[23]  Roman Zitlau,et al.  Feature importance for machine learning redshifts applied to SDSS galaxies , 2014, 1410.4696.

[24]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[25]  M. Brescia,et al.  A catalogue of photometric redshifts for the SDSS-DR9 galaxies , 2014, 1407.2527.

[26]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[27]  R. J. Brunner,et al.  TPZ: photometric redshift PDFs and ancillary information by using prediction trees and random forests , 2013, 1303.7269.

[28]  Ofer Lahav.  Artificial Neural Networks as a Tool for Galaxy Classification , 1996 .

[29]  C. Bonnett.  Using neural networks to estimate redshift distributions. An application to CFHTLenS , 2013, 1312.1287.

[30]  C. Lintott,et al.  Galaxy Zoo 2: detailed morphological classifications for 304,122 galaxies from the Sloan Digital Sky Survey , 2013, 1308.3496.

[31]  D. York,et al.  The u'g'r'i'z' Standard Star Network , 2002, astro-ph/0201143.

[32]  Harris Drucker,et al.  Improving Regressors using Boosting Techniques , 1997, ICML.

[33]  A. Fontana,et al.  A Critical Assessment of Photometric Redshift Methods: A CANDELS Investigation , 2013, 1308.5353.