Measuring photometric redshifts using galaxy images and Deep Neural Networks
Abstract
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, in terms of the measured point prediction metrics, 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, and as such are only tractable for making predictions on datasets of size ≤50k before implementing parallelisation techniques.
- Publication:
-
Astronomy and Computing
- Pub Date:
- July 2016
- DOI:
- 10.1016/j.ascom.2016.03.006
- arXiv:
- arXiv:1504.07255
- Bibcode:
- 2016A&C....16...34H
- Keywords:
-
- Astronomy;
- Machine learning;
- Cosmology;
- Astrophysics - Instrumentation and Methods for Astrophysics;
- Astrophysics - Cosmology and Nongalactic Astrophysics;
- Astrophysics - Astrophysics of Galaxies;
- Physics - Data Analysis;
- Statistics and Probability
- E-Print:
- 24 pages, 3 figures, 1 table, version accepted by Astronomy and Computer Science. Expanded conclusions and discussion. Increased test sample size. Results unchanged