arXiv subjects

Tobias Vičánek Martínez

Publications and source records attributed to Tobias Vičánek Martínez.

3 recordsLinked to original sources

arXiv2026

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

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 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 arbitrary size with the LDM. This is done by sampling 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 a 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 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 of 512 pixel side length, corresponding to ~5.7 arcmin, with precise control over source locations and brightness. Control over source extension was achieved at lower precision. Sampling of arbitrary-sized maps was made possible, showing realistic results with seamless combination of individual samples and limited only by occasional sampling artifacts.

astro-ph.IM↗

arXiv2025

Simulating realistic radio continuum survey maps with diffusion models

The next generation of radio surveys is going to be transformative for cosmology and other aspects of our understanding of astrophysics. Realistic simulations of radio observations are essential for the design and planning of radio surveys. They are employed in the development of methods for tasks, such as data calibration and reduction, automated analysis and statistical studies in cosmology. We implemented a software for machine learning-assisted simulations of realistic surveys with the LOFAR telescope, resulting in a synthetic radio sky model and a corresponding artificial telescope observation. We employed a diffusion model trained on LoTSS observations to generate individual radio galaxy images with control over the angular size. Single sources are assembled into a radio sky model, using an input catalog from cosmological simulations. We then transformed this sky model into visibilities corresponding to a typical LoTSS pointing. We added realistic noise to this synthetic measurement and obtained our final simulated sky maps through deconvolution. We explored different ways to evaluate our resulting sky model. We were able to simulate realistic LOFAR observations, covering a sky patch of 5x5 degrees at an effective resolution of 8.5 arcseconds. The simulated sources have flux and size distributions that match real observations, and the resulting maps have sensitivities compatible with LoTSS observations. Our diffusion model is able to synthesize high-quality realistic radio galaxy images with precise control over the source sizes. This software can readily be applied to other instruments.

astro-ph.IM↗

arXiv2024

Simulating images of radio galaxies with diffusion models

With increasing amounts of data in astronomy, automated analysis methods have become crucial. Synthetic data are required for developing and testing such methods. Current simulations often suffer from insufficient detail or inaccurate representation of source type occurrences. To overcome those deficiencies, we implemented a deep generative model trained on observations to generate realistic radio galaxy images with full control over the flux and source morphology. We used a diffusion model, trained with continuous time steps to reduce sampling time without quality impairments. Two models were trained on two different datasets, respectively. One set was a selection of images from the second data release of the LOFAR Two-Metre Sky Survey (LoTSS). The model is conditioned on peak flux values to preserve signal intensity information after re-scaling image pixel values. The other, smaller set was obtained from the VLA survey of Faint Images of the Radio Sky at Twenty-Centimeters (FIRST). In that set, every image was provided with a morphological class label the corresponding model was conditioned on. Conditioned sampling is realized with classifier-free diffusion guidance. We evaluated the quality of generated images by comparing distributions of different quantities over the real and generated data, including results from the standard source-finding algorithms. The class conditioning was evaluated by training a classifier and comparing its performance on both real and generated data. We were able to generate realistic images of high quality using 25 sampling steps, which is unprecedented in the field of radio astronomy. The generated images are visually indistinguishable from the training data and the distributions of different image metrics were replicated. The classifier performs equally well for real and generated images, indicating strong sampling control over morphological properties.

astro-ph.IM↗