Tuning target selection algorithms to improve galaxy redshift estimates

TL;DR

This paper introduces machine learning-based target selection algorithms that optimize galaxy observations for spectroscopic follow-up, reducing resource use while maintaining redshift estimation accuracy.

Contribution

It develops iterative ML algorithms predicting target difficulty, improving efficiency over traditional and random selection methods in galaxy redshift surveys.

Findings

ML algorithms predict redshift error and bias within 10-30% accuracy.

Some ML algorithms reduce required observing time by 2-3 times.

Potential to enable deeper spectroscopy with fewer resources.

Abstract

We showcase machine learning (ML) inspired target selection algorithms to determine which of all potential targets should be selected first for spectroscopic follow up. Efficient target selection can improve the ML redshift uncertainties as calculated on an independent sample, while requiring less targets to be observed. We compare the ML targeting algorithms with the Sloan Digital Sky Survey (SDSS) target order, and with a random targeting algorithm. The ML inspired algorithms are constructed iteratively by estimating which of the remaining target galaxies will be most difficult for the machine learning methods to accurately estimate redshifts using the previously observed data. This is performed by predicting the expected redshift error and redshift offset (or bias) of all of the remaining target galaxies. We find that the predicted values of bias and error are accurate to better than 10-30% of the true values, even with only limited training sample sizes. We construct a hypothetical follow-up survey and find that some of the ML targeting algorithms are able to obtain the same redshift predictive power with 2-3 times less observing time, as compared to that of the SDSS, or random, target selection algorithms. The reduction in the required follow up resources could allow for a change to the follow-up strategy, for example by obtaining deeper spectroscopy, which could improve ML redshift estimates for deeper test data.