Journal
ASTRONOMY & ASTROPHYSICS
Volume 621, Issue -, Pages -Publisher
EDP SCIENCES S A
DOI: 10.1051/0004-6361/201833617
Keywords
galaxies: distances and redshifts; surveys; methods: data analysis; techniques: image processing
Categories
Funding
- OCEVU Labex [ANR-11-LABX-0060]
- Spin(e) project [ANR-13-BS05-0005]
- Programme National Cosmologie et Galaxies (PNCG)
- A*MIDEX project - Investissements d'Avenir French government [ANR-11-IDEX-0001-02]
- Alfred P. Sloan Foundation
- National Science Foundation
- US Department of Energy Office of Science
- University of Arizona
- Brazilian Participation Group
- Brookhaven National Laboratory
- Carnegie Mellon University
- University of Florida
- French Participation Group
- German Participation Group
- Harvard University
- Instituto de Astrofisica de Canarias
- Michigan State/Notre Dame/JINA Participation Group
- Johns Hopkins University
- Lawrence Berkeley National Laboratory
- Max Planck Institute for Astrophysics
- Max Planck Institute for Extraterrestrial Physics
- New Mexico State University
- New York University
- Ohio State University
- Pennsylvania State University
- University of Portsmouth
- Princeton University
- Spanish Participation Group
- University of Tokyo
- University of Utah
- Vanderbilt University
- University of Virginia
- University of Washington
- Yale University
Ask authors/readers for more resources
We developed a deep convolutional neural network (CNN), used as a classifier, to estimate photometric redshifts and associated probability distribution functions (PDF) for galaxies in the Main Galaxy Sample of the Sloan Digital Sky Survey at z < 0.4. Our method exploits all the information present in the images without any feature extraction. The input data consist of 64 x 64 pixel ugriz images centered on the spectroscopic targets, plus the galactic reddening value on the line-of-sight. For training sets of 100k objects or more (>= 20% of the database), we reach a dispersion sigma(MAD) < 0.01, significantly lower than the current best one obtained from another machine learning technique on the same sample. The bias is lower than 10(-4), independent of photometric redshift. The PDFs are shown to have very good predictive power. We also find that the CNN redshifts are unbiased with respect to galaxy inclination, and that sigma(MAD) decreases with the signal-to-noise ratio (S/N), achieving values below 0.007 for S/N > 100, as in the deep stacked region of Stripe 82. We argue that for most galaxies the precision is limited by the S/N of SDSS images rather than by the method. The success of this experiment at low redshift opens promising perspectives for upcoming surveys.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available