The miniJPAS and J-NEP surveys: Machine learning for star-galaxy separation

TL;DR

This paper develops a machine learning approach using XGBoost to classify stars and galaxies in the miniJPAS and J-NEP surveys, significantly improving classification accuracy by incorporating morphological features.

Contribution

It introduces a robust supervised classification method combining photometric and morphological data, with hyperparameter tuning and feature importance analysis, for star-galaxy separation in these surveys.

Findings

Morphological features improve classification performance.

The classifier outperforms existing catalog classifications.

Key features include concentration and surface brightness.

Abstract

We present a supervised machine learning classification of sources from the Javalambre Physics of the Accelerating Universe Astrophysical Survey (J-PAS) Pathfinder datasets: miniJPAS and J-NEP. Leveraging crossmatches with spectroscopic and photometric catalogs, we construct a robust labeled dataset comprising 14594 sources classified into extended (galaxies) and point-like (stars and quasars) objects. We assess dataset representativeness using UMAP analysis, confirming broad and consistent coverage of feature space. An XGBoost classifier, with hyperparameters tuned using automated optimization, is trained using purely photometric data (60-band J-PAS magnitudes) and combined photometric and morphological features, with performance thoroughly evaluated via ROC and purity-completeness metrics. Incorporating morphology significantly improves classification, outperforming the baseline classifications available in the catalogs. Permutation importance analysis reveals morphological parameters, particularly concentration, normalized peak surface brightness, and PSF, alongside photometric features around 4000 and 6900 A, as crucial for accurate classifications. We release a value-added catalog with our models for star-galaxy classification, enhancing the utility of miniJPAS and J-NEP for subsequent cosmological and astrophysical analyses.