Transformer-based source detection and morphological classification in LOFAR Deep-Field continuum images
Open Access
- 30 May 2026
- journal article
- Published by Oxford University Press (OUP) in Monthly Notices of the Royal Astronomical Society
- Vol. 549 (3)
Abstract
Radio source detection and morphological classification are fundamental for exploiting the scientific potential of modern radio continuum surveys. However, the rapidly increasing data volumes and the wide diversity of radio morphologies make traditional visual inspection infeasible and pose significant challenges for automated source finding. We apply a transformer-based set-prediction detector (RF-DETR) to 150 MHz continuum images from the LOFAR Deep Fields for instance-level source detection and morphological classification. The method is adapted to multi-frequency-synthesis images of interferometric data and trained with a morphology-driven scheme using five mutually exclusive classes. The model is trained on the ELAIS-N1 Deep Field, where it achieves high detection and classification performance ($\mathrm{F1}\simeq 91$ per cent), and is then applied without retraining to the other three LOFAR Deep Fields. Across all four fields, the model yields consistent catalogues with modest field-to-field differences arising from survey depth and calibration. Compared with widely used PyBDSF catalogues, RF-DETR recovers the majority of PyBDSF sources while representing classical multi-component radio galaxies as single source-level detections rather than fragmented Gaussian components. Artefact-affected and spurious detections are identified as explicit classes, allowing these detections to be distinguished from general astrophysical sources in the resulting catalogues. As external validation, RF-DETR recovers the majority of visually identified extended and giant radio galaxies in the LOFAR Deep Fields and assigns them predominantly to extended morphological classes. These results indicate that transformer-based detectors provide a practical, scalable, morphology-aware approach to source finding in deep radio surveys, with clear relevance for forthcoming facilities such as SKA-Low.Keywords
All Related Versions
Funding Information
- Science and Technology Facilities Council (ST/Y004159/1)
- UK Research and Innovation (MR/X005399/1)
- Alfred P. Sloan Foundation
This publication has 65 references indexed in Scilit:
- Self-supervised contrastive learning of radio data for source detection, classification and peculiar object discoveryPublications of the Astronomical Society of Australia, 2024
- Advances on the morphological classification of radio galaxies: A reviewNew Astronomy Reviews, 2023
- Radio sources segmentation and classification with deep learningAstronomy and Computing, 2023
- Radio astronomical images object detection and segmentation: a benchmark on deep learning methodsExperimental Astronomy, 2023
- Astronomical source detection in radio continuum maps with deep neural networksAstronomy and Computing, 2022
- Australian square kilometre array pathfinder: I. system descriptionPublications of the Astronomical Society of Australia, 2021
- End-to-End Object Detection with Transformers2020
- Radio galaxies and feedback from AGN jetsNew Astronomy Reviews, 2020
- Source Finding in the Era of the SKA (Precursors): Aegean 2.0Publications of the Astronomical Society of Australia, 2018
- The Murchison Widefield Array: The Square Kilometre Array Precursor at Low Radio FrequenciesPublications of the Astronomical Society of Australia, 2013