Estimation of Photometric Redshifts. I. Machine Learning Inference for Pan-STARRS1 Galaxies Using Neural Networks

TL;DR

This paper introduces a neural network-based machine learning model for estimating photometric redshifts of galaxies in Pan-STARRS1, achieving high accuracy within the training data domain and providing reliable confidence estimates.

Contribution

The work presents a novel neural network ensemble model that improves photometric redshift estimation accuracy and calibration, with analysis of its applicability and limitations across different data regimes.

Findings

High accuracy for densely sampled training data

Reliable confidence calibration of redshift estimates

Performance diminishes for out-of-distribution samples

Abstract

We present a new machine learning model for estimating photometric redshifts with improved accuracy for galaxies in Pan-STARRS1 data release 1. Depending on the estimation range of redshifts, this model based on neural networks can handle the difficulty for inferring photometric redshifts. Moreover, to reduce bias induced by the new model's ability to deal with estimation difficulty, it exploits the power of ensemble learning. We extensively examine the mapping between input features and target redshift spaces to which the model is validly applicable to discover the strength and weaknesses of trained model. Because our trained model is well calibrated, our model produces reliable confidence information about objects with non-catastrophic estimation. While our model is highly accurate for most test examples residing in the input space, where training samples are densely populated, its accuracy quickly diminishes for sparse samples and unobserved objects (i.e., unseen samples) in training. We report that out-of-distribution (OOD) samples for our model contain both physically OOD objects (i.e., stars and quasars) and galaxies with observed properties not represented by training data. The code for our model is available at https://github.com/GooLee0123/MBRNN for other uses of the model and retraining the model with different data.