The miniJPAS and J-NEP surveys: Machine learning for star-galaxy separation
arXiv:2511.20524 · doi:10.3390/galaxies14010006
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.
28 pages; accepted for publication in Galaxies
References in corpus (16)
- XGBoost: A Scalable Tree Boosting System
- The Eleventh and Twelfth Data Releases of the Sloan Digital Sky Survey: Final Data from SDSS-III
- Second Data Release of the Hyper Suprime-Cam Subaru Strategic Program
- Galactic Reddening in 3D from Stellar Photometry - An Improved Map
- Binospec: A Wide-field Imaging Spectrograph for the MMT
- The miniJPAS survey: a preview of the Universe in 56 colours
- The DEEP3 Galaxy Redshift Survey: Keck/DEIMOS Spectroscopy in the GOODS-N Field
- The miniJPAS survey: star-galaxy classification using machine learning
- J-PLUS: Morphological star/galaxy classification by PDF analysis
- J-PLUS: photometric calibration of large area multi-filter surveys with stellar and white dwarf loci
- The James Webb Space Telescope North Ecliptic Pole Time-Domain Field -- I: Field Selection of a JWST Community Field for Time-Domain Studies
- Photometric identification of compact galaxies, stars and quasars using multiple neural networks
- J-NEP: 60-band photometry and photometric redshifts for the James Webb Space Telescope North Ecliptic Pole Time-Domain Field
- J-PLUS DR3: Galaxy-Star-Quasar classification
- J-PLUS: Bayesian object classification with a strum of BANNJOS
- Semi-supervised classification of stars, galaxies and quasars using K-means and random-forest approaches