Multi-branch classification of diffuse cluster radio emission from the LOFAR two-metre sky survey

Abstract

Context. Galaxy clusters sometimes host synchrotron radiation on scales of approximately 100 kpc to approximately 1 Mpc, with a surface brightness only a few times the image noise. This diffuse cluster radio emission is a sensitive probe of magnetic fields and intracluster medium dynamics, but disentangling the underlying physical processes requires statistically large samples spanning a wide range of cluster masses, dynamical states, and redshifts, together with a sufficient sensitivity to low-surface-brightness emission. Aims. We explore two techniques for improving the detection of diffuse emission in galaxy cluster images, relative to a baseline classifier: the scattering transform (ST) and squeeze-excitation (SE) attention. Methods. We integrated an ST encoder into a dual-branch classifier (DualSSN) and a scattering network (ScatterNet). We incorporated SE attention into the DualSSN and dual-branch convolutional neural network (DualCSN). These classifiers were then benchmarked against a simple convolutional neural network (CNN), across ten image pre-processing configurations and three cropping strategies. Performance was evaluated on small labelled datasets from the second data release of the LOFAR Two-metre Sky Survey overlapping with the Second Planck catalogue of Sunyaev-Zel'dovich sources (LoTSS-DR2/PSZ2). Results. Alongside the multi-branch approach with SE and ST, cropping the image to a fixed number of telescope beams and uv tapering (smoothing to a coarser angular resolution) improve classification performance, while tacking multiple pre-processed versions of an image does not. Conclusions. Scattering-transform-based multi-branch architectures with beam-normalised cropping are a promising direction for diffuse emission classification in the SKA era.

Diffuse gamma-ray emission in the vicinity of open cluster Berkeley 87
Ziwei Ou, Xiaolong Yang
arXiv22 Sep 2026PreprintCC BY 4.0Full textHigh-energy astrophysicsarXiv
Caught in the act: diffuse stellar and Lyα emission around a halo-less quasar in the assembling cluster CARLA J0800+4029 at z=2
Sofia G Gallego, Simona Mei, Emanuele Daddi +3
HAL29 Sep 2026PreprintCC BY 4.0Full textGalaxies General physicsHALarXiv
The MIni-Halos in MIni-Clusters (MIMIC) project. New insights into the origin of mini-halos from a LOFAR, uGMRT, and MeerKAT study of diffuse radio emission in Abell 496 and ZwCl 235
F. Ubertosi, S. Giacintucci, A. Botteon +18
Astronomy & Astrophysics28 Oct 2026Peer-reviewedPublisher termsGalaxiesCrossref
Search for an all-sky and a Galactic Ridge diffuse neutrino emission with the first 2 years of KM3NeT/ARCA data
O Adriani, A Albert, A.R Alhebsi +286
HAL1 Oct 2026PreprintLicence not statedGeneral astronomy High-energy & particle physicsHAL
Diffuse gamma-ray emissions around the stellar cluster Berkeley 59
Ziwei Ou, Xiaolong Yang, Songpeng Pei
arXiv16 Sep 2026PreprintCC BY 4.0Full textHigh-energy astrophysicsarXiv

Cite

BibTeX RIS

BibTeX

@misc{bredberg2026multibranch,
  title = {{Multi-branch classification of diffuse cluster radio emission from the LOFAR two-metre sky survey}},
  author = {Markus Bredberg and Emma Tolley},
  howpublished = {arXiv},
  year = {2026},
  month = aug,
  doi = {10.48550/arxiv.2607.28349},
  eprint = {2607.28349},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.28349},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - Multi-branch classification of diffuse cluster radio emission from the LOFAR two-metre sky survey
AU  - Markus Bredberg
AU  - Emma Tolley
PY  - 2026
DA  - 2026/08/31
PB  - arXiv
DO  - 10.48550/arxiv.2607.28349
UR  - https://arxiv.org/abs/2607.28349
AB  - Context. Galaxy clusters sometimes host synchrotron radiation on scales of approximately 100 kpc to approximately 1 Mpc, with a surface brightness only a few times the image noise. This diffuse cluster radio emission is a sensitive probe of magnetic fields and intracluster medium dynamics, but disentangling the underlying physical processes requires statistically large samples spanning a wide range of cluster masses, dynamical states, and redshifts, together with a sufficient sensitivity to low-surface-brightness emission. Aims. We explore two techniques for improving the detection of diffuse emission in galaxy cluster images, relative to a baseline classifier: the scattering transform (ST) and squeeze-excitation (SE) attention. Methods. We integrated an ST encoder into a dual-branch classifier (DualSSN) and a scattering network (ScatterNet). We incorporated SE attention into the DualSSN and dual-branch convolutional neural network (DualCSN). These classifiers were then benchmarked against a simple convolutional neural network (CNN), across ten image pre-processing configurations and three cropping strategies. Performance was evaluated on small labelled datasets from the second data release of the LOFAR Two-metre Sky Survey overlapping with the Second Planck catalogue of Sunyaev-Zel'dovich sources (LoTSS-DR2/PSZ2). Results. Alongside the multi-branch approach with SE and ST, cropping the image to a fixed number of telescope beams and uv tapering (smoothing to a coarser angular resolution) improve classification performance, while tacking multiple pre-processed versions of an image does not. Conclusions. Scattering-transform-based multi-branch architectures with beam-normalised cropping are a promising direction for diffuse emission classification in the SKA era.
ER  -

Abstract

Related

Cite