Photometric redshifts for quasars from WISE-PS1-STRM

TL;DR

This paper develops machine learning methods to estimate photometric redshifts for nearly 2.9 million quasars using optical and infrared data, providing a reliable and publicly available catalog for cosmological research.

Contribution

It introduces a robust approach combining XGBoost and neural networks with effective training set coverage estimation for quasar redshift prediction.

Findings

Reliable photometric redshifts for 2.9 million quasars

Validation with clustering-based redshift estimation

Publicly available quasar redshift catalog

Abstract

Three-dimensional wide-field galaxy surveys are fundamental for cosmological studies. For higher redshifts (z > 1.0), where galaxies are too faint, quasars still trace the large-scale structure of the Universe. Since available telescope time limits spectroscopic surveys, photometric methods are efficient for estimating redshifts for many quasars. Recently, machine learning methods are increasingly successful for quasar photometric redshifts, however, they hinge on the distribution of the training set. Therefore a rigorous estimation of reliability is critical. We extracted optical and infrared photometric data from the cross-matched catalogue of the WISE All-Sky and PS1 3$\pi$ DR2 sky surveys. We trained an XGBoost regressor and an artificial neural network on the relation between color indices and spectroscopic redshift. We approximated the effective training set coverage with the K nearest neighbors algorithm. We estimated reliable photometric redshifts of 2,879,298 quasars which overlap with the training set in feature space. We validated the derived redshifts with an independent, clustering-based redshift estimation technique. The final catalog is publicly available.