Estimating Flux Densities of Diffuse Cosmological Radio Sources Exploiting Vision Transformers
Open Access
- 5 October 2026
- journal article
- research article
- Published by Cambridge University Press (CUP) in Proceedings of the International Astronomical Union
- Vol. 21 (S397) , 221-225
Abstract
We present TUNA, a Vision-Transformer based network adapted from segmentation to flux regression for faint, diffuse radio emission. Trained on LOFAR-like mock observations derived from cosmological simulations, TUNA accurately reconstructs low surface-brightness structures, with only mild smoothing and small brightness-dependent biases. Applied to LOFAR data of the A399-A401 galaxy cluster system, it recovers the ridge not identifiable in the high resolution observation and matches the low resolution tapered map. These results indicate how TUNA can deliver automated, quantitative surface brightness estimates for diffuse extragalactic sources, enabling scalable analyses for upcoming surveys.Keywords
This publication has 7 references indexed in Scilit:
- Mapping diffuse radio sources using TUNA: a transformer-based deep learning approachMonthly Notices of the Royal Astronomical Society, 2025
- Convolutional deep denoising autoencoders for radio astronomical imagesMonthly Notices of the Royal Astronomical Society, 2021
- Australian square kilometre array pathfinder: I. system descriptionPublications of the Astronomical Society of Australia, 2021
- A radio ridge connecting two galaxy clusters in a filament of the cosmic webScience, 2019
- An optimized algorithm for multiscale wideband deconvolution of radio astronomical imagesMonthly Notices of the Royal Astronomical Society, 2017
- LOFAR: The LOw-Frequency ARrayAstronomy & Astrophysics, 2013
- The Murchison Widefield Array: The Square Kilometre Array Precursor at Low Radio FrequenciesPublications of the Astronomical Society of Australia, 2013