Work

Generating radio continuum survey maps of an arbitrary size with latent diffusion models

Year: 2026

Type: article

Abstract: Radio surveys provide exponentially increasing amounts of observational data, which requires the development of novel data reduction and analysis methods. To this end, realistic simulations of observational data provide controlled environments for testing and developing new methods. Diffusion models excel at synthesizing realistic image data, but they are limited by size constraints and high computational demands. We implemented a latent diffusion model (LDM) to synthesize realistic radio survey map cutouts. Further, we developed a technique for sampling radio survey maps of an arbitrary size with the LDM. This was done by sampling image patches in multiple sequential steps, whereby consistency is provided through context vectors and image inpainting. We trained our model on observations from the LOFAR telescope obtained from the third data release of the LOFAR Two-Metre Sky Survey. We implemented an LDM composed of a vector-quantized variational autoencoder and a diffusion model operating on the resulting latent representations. We added information on source locations, brightness, and sizes by extracting parameters from the public source catalog and encoding them into a vector format, which is passed as context to the LDM. We trained the model for image inpainting to facilitate continuous sequential sampling. We were able to generate realistic cutouts with a 512 pixel side length, corresponding to ∼! with precise control over source locations and brightness. Control over source extension was achieved at a lower precision. Sampling of arbitrary-sized maps was made possible, showing realistic results with a seamless combination of individual samples and limited only by occasional sampling artifacts.

Source: Astronomy and Astrophysics

DOI: 10.1051/0004-6361/202660213

Authors: T. Vičánek Martínez, M. Brüggen

Language: English

Topic: Radio Astronomy Observations and Technology

Subfield: Astronomy and Astrophysics

Field: Physics and Astronomy

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $1,865

Funders: Deutsche Forschungsgemeinschaft, Bundesministerium für Bildung und Forschung

Awards: G432818845, EXC 2121: Quantum Universe, Verbundprojekt 05D2022 - KISS: Künstliche Intelligenz zur schnellen Simulation von wissenschaftlichen Daten. Teilprojekt 1.