A Generative Model for Disentangling Galaxy Photometric Parameters

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Leung, Keen, Yan, Colen, Yin, Jun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917170999459840
author Leung, Keen
Yan, Colen
Yin, Jun
author_facet Leung, Keen
Yan, Colen
Yin, Jun
contents Ongoing and future photometric surveys will produce unprecedented volumes of galaxy images, necessitating robust, efficient methods for deriving galaxy morphological parameters at scale. Traditional approaches, such as parametric light-profile fitting, offer valuable insights but become computationally prohibitive when applied to billions of sources. In this work, we propose a Conditional AutoEncoder (CAE) framework to simultaneously model and characterize galaxy morphology. Our CAE is trained on a suite of realistic mock galaxy images generated via GalSim, encompassing a broad range of galaxy types, photometric parameters (e.g., flux, half-light radius, Sersic index, ellipticity), and observational conditions. By encoding each galaxy image into a low-dimensional latent representation conditioned on key parameters, our model effectively recovers these morphological features in a disentangled manner, while also reconstructing the original image. The results demonstrate that the CAE approach can accurately and efficiently infer complex structural properties, offering a powerful alternative to existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2507_15898
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Generative Model for Disentangling Galaxy Photometric Parameters
Leung, Keen
Yan, Colen
Yin, Jun
Instrumentation and Methods for Astrophysics
Astrophysics of Galaxies
Artificial Intelligence
Ongoing and future photometric surveys will produce unprecedented volumes of galaxy images, necessitating robust, efficient methods for deriving galaxy morphological parameters at scale. Traditional approaches, such as parametric light-profile fitting, offer valuable insights but become computationally prohibitive when applied to billions of sources. In this work, we propose a Conditional AutoEncoder (CAE) framework to simultaneously model and characterize galaxy morphology. Our CAE is trained on a suite of realistic mock galaxy images generated via GalSim, encompassing a broad range of galaxy types, photometric parameters (e.g., flux, half-light radius, Sersic index, ellipticity), and observational conditions. By encoding each galaxy image into a low-dimensional latent representation conditioned on key parameters, our model effectively recovers these morphological features in a disentangled manner, while also reconstructing the original image. The results demonstrate that the CAE approach can accurately and efficiently infer complex structural properties, offering a powerful alternative to existing methods.
title A Generative Model for Disentangling Galaxy Photometric Parameters
topic Instrumentation and Methods for Astrophysics
Astrophysics of Galaxies
Artificial Intelligence
url https://arxiv.org/abs/2507.15898