Decoupling candidate dual AGN from chance superpositions in the GOTHIC survey via a deep-learning framework
astro-ph.GA, cs.CV, cs.LG, math-ph, math.MP, physics.data-an
Submitted: 2026-08-25
Updated: 2026-10-23
Comments: Submitted to MNRAS. Supplementary Material merged in the main text
Code: https://github.com/anuwu/Blindtest-HQ
License: http://creativecommons.org/licenses/by/4.0/
The gist: Dual active galactic nuclei (DAGN) mark a critical phase in the evolution of merging galaxies and the pairing of supermassive black holes, yet they remain difficult to identify in large imaging
Terminology
Abstract
Dual active galactic nuclei (DAGN) mark a critical phase in the evolution of merging galaxies and the pairing of supermassive black holes, yet they remain difficult to identify in large imaging surveys because of projection effects and limited spatial resolution. Compact foreground stars and unresolved substructure can mimic dual nuclei through chance superposition, complicating automated detection. We revisit the 46,061 galaxies flagged but rejected as DAGN candidates by the GOTHIC pipeline, primarily because the two nuclei fell within the SDSS fibre aperture or exceeded its separation threshold. We train a supervised deep-learning framework based on the YOLOv11 oriented-bounding-box architecture on annotated SDSS imaging to separate genuine dual nuclei from foreground stellar contaminants and other spurious alignments. The final model attains a validation precision of 0.919, recall of 0.905, and F 1 of 0.912 for the dual-nuclei class, and yields 29,605 dual-nucleus candidates after removing star-dominated and blended detections. Structured visual inspection indicates that 54.5 -- 62% are consistent with genuine dual nuclei, implying about(1.4 -- 1.8) times10 4 plausible systems. Cross-calibrating the YOLO separation against the deterministic GOTHIC centroid measurement and restricting to the compact regime (d 6.87'') gives a conservative subset of about 13, 672 candidates, reaching calibrated separations of about 0.56''. Spectroscopy of the most compact (1 kpc) systems shows they are dominated by passive, absorption-line galaxies with no resolved double-peaked emission, so confirmation requires higher-resolution follow-up. The catalogue is a statistically refined list of candidates, not confirmed DAGN. Nonetheless, deep-learning detection substantially reduces contamination and expands the plausible DAGN census.
Sources
- Laser Interferometer Space Antenna
- YOLOv11: An Overview of the Key Architectural Enhancements
- An Introduction to Convolutional Neural Networks
- Robustness analysis of Deep Sky Objects detection models on HPC
- You Only Look Once: Unified, Real-Time Object Detection
Related papers
- Apparent Stability in Self-Gravitating Turbulence and the Evolution of Molecular Clouds
- Two sets of potential-density basis pairs for the study of radial perturbations in collisionless spherical stellar systems
- Constraining reionization-era Ly alpha escape with JELS-MUSE: a highly complete H alpha-selected sample at z about6.1
- Deriving volume density profiles of filaments from observed surface densities
- Little Red Dots and Supermassive Black Hole Seed Formation in Ultralight Dark Matter Halos
- MEGATRON: how the first stars can create an iron metallicity plateau in the smallest dwarf galaxies