A Guided Unconditional Diffusion Model to Synthesize and Inpaint Radio Galaxies from FIRST, MGCLS and Radio Zoo

TL;DR

This paper introduces a guided diffusion model trained on radio galaxy datasets to generate and inpaint realistic radio galaxy images, aiding data augmentation in radio astronomy.

Contribution

A novel guided diffusion approach for realistic radio galaxy synthesis and inpainting, trained on multiple radio datasets, enhancing data-driven analysis in radio astronomy.

Findings

Produces morphologically realistic radio galaxies

Effective inpainting of missing galaxy regions

Supports data augmentation for machine learning

Abstract

We present a masked guided approach for a denoising diffusion probabilistic model (DDPM) trained to generate and inpaint realistic radio galaxy images. We train the DDPM using the FIRST radio galaxy catalog, the Radio Galaxies Zoo and cutouts of the MGCLS catalog. We compared different statistical distributions to make sure that our unconditional approach produces morphologically realistic galaxies, offering a data-driven method to supplement existing radio datasets and support the development of machine learning applications in radio astronomy.