A Generative Model for Disentangling Galaxy Photometric Parameters
This work addresses the problem of scaling galaxy morphology analysis for astronomers, but it is incremental as it applies a known deep learning method to a specific domain with existing data.
The paper tackles the challenge of efficiently deriving morphological parameters from large volumes of galaxy images in photometric surveys by proposing a Conditional AutoEncoder (CAE) framework, which accurately recovers parameters like flux and half-light radius while reconstructing images, offering a robust alternative to computationally intensive traditional methods.
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.