A Generative Model for Disentangling Galaxy Photometric Parameters

TL;DR

This paper introduces a Conditional AutoEncoder framework trained on simulated galaxy images to efficiently and accurately extract morphological parameters, offering a scalable alternative to traditional fitting methods for large surveys.

Contribution

We develop a CAE model that disentangles galaxy morphological parameters from images, enabling rapid and precise characterization at scale.

Findings

Accurately recovers galaxy parameters like flux and size

Efficiently processes large datasets with high fidelity

Outperforms traditional parametric fitting methods

Abstract

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.