Complete Multi-Band Structural Characterization for 10 Million Galaxies in the Hyper Suprime-Cam Wide Survey using Deep Learning
Abstract
Galaxy structure is wavelength-dependent, as different photometric bands trace distinct stellar populations and structural components. We present per-galaxy Bayesian posterior distributions of the bulge-to-total light ratio (LB/LT), effective radius (Re), and flux (F) in the g, r, and i bands for nearly $10$ million galaxies across ∼1400\,deg2 of the Hyper Suprime-Cam Subaru Strategic Program (HSC-SSP) Wide survey at z ≤ 0.75 and m < 23. To our knowledge, this is the largest multi-band catalog of bulge--disk structural parameters with per-galaxy posteriors. ∼3.9 million of the above galaxies have full multi-band coverage. Measurements are generated using the Galaxy Morphology Posterior Estimation Network (\gampen{}), a Bayesian deep-learning framework. We demonstrate that we can adapt \gampen{} from previously-trained single-band models to the new bands by using transfer learning on only ∼0.5\% of our dataset. Despite this extremely small training set, \gampen{} successfully reproduces light-profile fitting measurements and its output posteriors are extremely well-calibrated with ≲6% mean deviation. This approach offers a scalable pathway to structural parameter measurements with robust uncertainties for Rubin, Euclid, and Roman data, which we will pursue in forthcoming work. While structural measurements remain robust across most bands and redshift ranges, performance degrades significantly for the g-band at z ≳ 0.5, where it increasingly probes rest-frame ultraviolet emission; these measurements are therefore excluded from the public release. This public catalog will enable large-scale statistical studies of morphological color gradients, wavelength-dependent galaxy structure, and galaxy evolution.
Related
- Virgo Filaments VIII: Characterizing the Structural Parameters of Virgo Galaxies with Machine Learning to Probe Environmental Quenching
- The SIRMOS mission concept: a space-based near-IR spectroscopic survey of 100 million galaxies in the Euclid Wide Survey footprint
- A High-Mass Size Deficit for Void Galaxies in the Complete SDSS DR7
- Stellar parameters and abundances for 3.2 million DESI DR1 spectra using machine learning
- Multiband Structural Analysis of KiDS-selected Low Surface Brightness Galaxies with Hyper Suprime-Cam Imaging
BibTeX
@misc{sarkar2026complete,
title = {{Complete Multi-Band Structural Characterization for 10 Million Galaxies in the Hyper Suprime-Cam Wide Survey using Deep Learning}},
author = {Milind Sarkar and Aritra Ghosh and Andrew Connolly and C. Megan Urry and Andrew Coli and Joshua S. Speagle and Rhythm Shimakawa and Charles Willard and Diego Lockyer},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.32913},
eprint = {2610.32913},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.32913},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Complete Multi-Band Structural Characterization for 10 Million Galaxies in the Hyper Suprime-Cam Wide Survey using Deep Learning
AU - Milind Sarkar
AU - Aritra Ghosh
AU - Andrew Connolly
AU - C. Megan Urry
AU - Andrew Coli
AU - Joshua S. Speagle
AU - Rhythm Shimakawa
AU - Charles Willard
AU - Diego Lockyer
PY - 2026
DA - 2026/10/23
PB - arXiv
DO - 10.48550/arxiv.2610.32913
UR - https://arxiv.org/abs/2610.32913
AB - Galaxy structure is wavelength-dependent, as different photometric bands trace distinct stellar populations and structural components. We present per-galaxy Bayesian posterior distributions of the bulge-to-total light ratio (L_B/L_T), effective radius (R_e), and flux (F) in the g, r, and i bands for nearly $10$ million galaxies across ∼1400\,deg^2 of the Hyper Suprime-Cam Subaru Strategic Program (HSC-SSP) Wide survey at z ≤ 0.75 and m < 23. To our knowledge, this is the largest multi-band catalog of bulge--disk structural parameters with per-galaxy posteriors. ∼3.9 million of the above galaxies have full multi-band coverage. Measurements are generated using the Galaxy Morphology Posterior Estimation Network (\gampen{}), a Bayesian deep-learning framework. We demonstrate that we can adapt \gampen{} from previously-trained single-band models to the new bands by using transfer learning on only ∼0.5\% of our dataset. Despite this extremely small training set, \gampen{} successfully reproduces light-profile fitting measurements and its output posteriors are extremely well-calibrated with ≲6% mean deviation. This approach offers a scalable pathway to structural parameter measurements with robust uncertainties for Rubin, Euclid, and Roman data, which we will pursue in forthcoming work. While structural measurements remain robust across most bands and redshift ranges, performance degrades significantly for the g-band at z ≳ 0.5, where it increasingly probes rest-frame ultraviolet emission; these measurements are therefore excluded from the public release. This public catalog will enable large-scale statistical studies of morphological color gradients, wavelength-dependent galaxy structure, and galaxy evolution.
ER -