Redshift Measurement and Spectral Classification for eBOSS Galaxies with the Redmonster Software

TL;DR

This paper introduces the redmonster software for automated redshift measurement and spectral classification in eBOSS, demonstrating high success rates and improvements over previous methods, with detailed analysis of errors and performance factors.

Contribution

The paper presents a new automated spectral classification software, redmonster, optimized for eBOSS data, with improved accuracy and reliability over prior pipelines.

Findings

Achieved 90.5% success rate in redshift classification for luminous red galaxies.

Redmonster's performance meets eBOSS cosmology requirements and surpasses previous pipelines.

Redshift uncertainties are over-estimated by about 54%, based on repeat observations.

Abstract

We describe the redmonster automated redshift measurement and spectral classification software designed for the extended Baryon Oscillation Spectroscopic Survey (eBOSS) of the Sloan Digital Sky Survey IV (SDSS-IV). We describe the algorithms, the template standard and requirements, and the newly developed galaxy templates to be used on eBOSS spectra. We present results from testing on early data from eBOSS, where we have found a 90.5% automated redshift and spectral classification success rate for the luminous red galaxy sample (redshifts 0.6$\lesssim z \lesssim$1.0). The redmonster performance meets the eBOSS cosmology requirements for redshift classification and catastrophic failures, and represents a significant improvement over the previous pipeline. We describe the empirical processes used to determine the optimum number of additive polynomial terms in our models and an acceptable $\Delta\chi_r^2$ threshold for declaring statistical confidence. Statistical errors on redshift measurement due to photon shot noise are assessed, and we find typical values of a few tens of km s$^{-1}$. An investigation of redshift differences in repeat observations scaled by error estimates yields a distribution with a Gaussian mean and standard deviation of $\mu\sim$0.01 and $\sigma\sim$0.65, respectively, suggesting the reported statistical redshift uncertainties are over-estimated by $\sim$54%. We assess the effects of object magnitude, signal-to-noise ratio, fiber number, and fiber head location on the pipeline's redshift success rate. Finally, we describe directions of ongoing development.