Using gamma regression for photometric redshifts of survey galaxies

TL;DR

This paper introduces gamma regression, a fast and effective machine learning method for estimating galaxy redshifts from survey data, achieving low outlier rates and scalability.

Contribution

It applies Generalized Linear Models to astronomical photometric redshift estimation, providing a novel, efficient alternative to traditional methods.

Findings

Catastrophic outlier rate of ~1%

Fast computation on datasets of ~1 million galaxies

Accessible libraries and tools for astronomers

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.