Using gamma regression for photometric redshifts of survey galaxies
arXiv:1507.01293 · doi:10.1007/978-3-319-19330-4_13
Abstract
Machine learning techniques offer a plethora of opportunities in tackling big data within the astronomical community. We present the set of Generalized Linear Models as a fast alternative for determining photometric redshifts of galaxies, a set of tools not commonly applied within astronomy, despite being widely used in other professions. With this technique, we achieve catastrophic outlier rates of the order of ~1%, that can be achieved in a matter of seconds on large datasets of size ~1,000,000. To make these techniques easily accessible to the astronomical community, we developed a set of libraries and tools that are publicly available.
arXiv commentRefereed Proceeding of "The Universe of Digital Sky Surveys" conference held at the INAF - Observatory of Capodimonte, Naples, on 25th-28th November 2014, to be published in the Astrophysics and Space Science Proceedings, edited by Longo, Napolitano, Marconi, Paolillo, Iodice, 6 pages, and 1 figure
References in corpus (9)
- Scikit-learn: Machine Learning in Python
- The Sloan Digital Sky Survey: Technical Summary
- LSST Science Book, Version 2.0
- PHAT: PHoto-z Accuracy Testing
- Wide-Field InfraRed Survey Telescope (WFIRST) Final Report
- Euclid Imaging Consortium Science Book
- Exhausting the Information: Novel Bayesian Combination of Photometric Redshift PDFs
- Robust PCA and MIC statistics of baryons in early mini-haloes
- The Overlooked Potential of Generalized Linear Models in Astronomy-II: Gamma regression and photometric redshifts