Improving the reliability of photometric redshift with machine learning

TL;DR

This paper enhances photometric redshift estimation accuracy using machine learning and self-organizing maps to identify and select reliable galaxy data, significantly improving catalog quality.

Contribution

It introduces a combined machine learning and unsupervised learning approach to improve the reliability and accuracy of photometric redshift estimates.

Findings

Photo-z predictions match SED fitting for spec-z<1.2

SOM detects unreliable spec-z causing biases

Cleaning procedures double the quality of photo-z catalogs

Abstract

In order to answer the open questions of modern cosmology and galaxy evolution theory, robust algorithms for calculating photometric redshifts (photo-z) for very large samples of galaxies are needed. Correct estimation of the various photo-z algorithms' performance requires attention to both the performance metrics and the data used for the estimation. In this work, we use the supervised machine learning algorithm MLPQNA to calculate photometric redshifts for the galaxies in the COSMOS2015 catalogue and the unsupervised Self-Organizing Maps (SOM) to determine the reliability of the resulting estimates. We find that for spec-z<1.2, photo-z predictions are on the same level of quality as SED fitting photo-z. We show that the SOM successfully detects unreliable spec-z that cause biases in the estimation of the photo-z algorithms' performance. Additionally, we use SOM to select the objects with reliable photo-z predictions. Our cleaning procedures allow to extract the subset of objects for which the quality of the final photo-z catalogs is improved by a factor of two, compared to the overall statistics.