Mapping Diffuse Radio Sources Using TUNA: A Transformer-Based Deep Learning Approach

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sanvitale, Nicoletta, Gheller, Claudio, Vazza, Franco, Bonafede, Annalisa, Cuciti, Virginia, De Rubeis, Emanuele, Govoni, Federica, Murgia, Matteo, Vacca, Valentina
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909734917898240
author Sanvitale, Nicoletta
Gheller, Claudio
Vazza, Franco
Bonafede, Annalisa
Cuciti, Virginia
De Rubeis, Emanuele
Govoni, Federica
Murgia, Matteo
Vacca, Valentina
author_facet Sanvitale, Nicoletta
Gheller, Claudio
Vazza, Franco
Bonafede, Annalisa
Cuciti, Virginia
De Rubeis, Emanuele
Govoni, Federica
Murgia, Matteo
Vacca, Valentina
contents Vision Transformers are used via a customized TransUNet architecture, which is a hybrid model combining Transformers into a U-Net backbone, to achieve precise, automated, and fast segmentation of radio astronomy data affected by calibration and imaging artifacts, addressing the identification of faint, diffuse radio sources. Trained on mock radio observations from numerical simulations, the network is applied to the LOFAR Two-meter Sky Survey data. It is then evaluated on key use cases, specifically megahalos and bridges between galaxy clusters, to assess its performance in targeting sources at different resolutions and at the sensitivity limits of the telescope. The network is capable of detecting low surface brightness radio emission without manual source subtraction or re-imaging. The results demonstrate its groundbreaking capability to identify sources that typically require reprocessing at resolutions 4-6 times lower than that of the input image, accurately capturing their morphology and ensuring detection completeness. This approach represents a significant advancement in accelerating discovery within the large datasets generated by next-generation radio telescopes.
format Preprint
id arxiv_https___arxiv_org_abs_2507_11320
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mapping Diffuse Radio Sources Using TUNA: A Transformer-Based Deep Learning Approach
Sanvitale, Nicoletta
Gheller, Claudio
Vazza, Franco
Bonafede, Annalisa
Cuciti, Virginia
De Rubeis, Emanuele
Govoni, Federica
Murgia, Matteo
Vacca, Valentina
Instrumentation and Methods for Astrophysics
Vision Transformers are used via a customized TransUNet architecture, which is a hybrid model combining Transformers into a U-Net backbone, to achieve precise, automated, and fast segmentation of radio astronomy data affected by calibration and imaging artifacts, addressing the identification of faint, diffuse radio sources. Trained on mock radio observations from numerical simulations, the network is applied to the LOFAR Two-meter Sky Survey data. It is then evaluated on key use cases, specifically megahalos and bridges between galaxy clusters, to assess its performance in targeting sources at different resolutions and at the sensitivity limits of the telescope. The network is capable of detecting low surface brightness radio emission without manual source subtraction or re-imaging. The results demonstrate its groundbreaking capability to identify sources that typically require reprocessing at resolutions 4-6 times lower than that of the input image, accurately capturing their morphology and ensuring detection completeness. This approach represents a significant advancement in accelerating discovery within the large datasets generated by next-generation radio telescopes.
title Mapping Diffuse Radio Sources Using TUNA: A Transformer-Based Deep Learning Approach
topic Instrumentation and Methods for Astrophysics
url https://arxiv.org/abs/2507.11320