Photometric redshifts for the S-PLUS Survey: is machine learning up to the task?

TL;DR

This study evaluates machine learning techniques for photometric redshift estimation using the S-PLUS survey's twelve-filter system, finding deep learning models outperform traditional methods in accuracy and reliability.

Contribution

It introduces and compares three machine learning methods, demonstrating that a Bayesian Neural Network combined with a Mixture Density Network yields the most precise photometric redshifts for S-PLUS data.

Findings

Deep learning models outperform template-fitting methods in redshift accuracy.

The best model achieves a scatter of 0.023 in photometric redshifts.

Outlier fraction is reduced to 0.64% with the optimal model.

Abstract

The Southern Photometric Local Universe Survey (S-PLUS) is a novel project that aims to map the Southern Hemisphere using a twelve filter system, comprising five broad-band SDSS-like filters and seven narrow-band filters optimized for important stellar features in the local universe. In this paper we use the photometry and morphological information from the first S-PLUS data release (S-PLUS DR1) cross-matched to unWISE data and spectroscopic redshifts from Sloan Digital Sky Survey DR15. We explore three different machine learning methods (Gaussian Processes with GPz and two Deep Learning models made with TensorFlow) and compare them with the currently used template-fitting method in the S-PLUS DR1 to address whether machine learning methods can take advantage of the twelve filter system for photometric redshift prediction. Using tests for accuracy for both single-point estimates such as the calculation of the scatter, bias, and outlier fraction, and probability distribution functions (PDFs) such as the Probability Integral Transform (PIT), the Continuous Ranked Probability Score (CRPS) and the Odds distribution, we conclude that a deep-learning method using a combination of a Bayesian Neural Network and a Mixture Density Network offers the most accurate photometric redshifts for the current test sample. It achieves single-point photometric redshifts with scatter ($\sigma_\text{NMAD}$) of 0.023, normalized bias of -0.001, and outlier fraction of 0.64% for galaxies with r-auto magnitudes between 16 and 21.