Evolutionary Map of the Universe (EMU): Selection of active galactic nuclei and star-formation emission with machine-learning techniques
Abstract
Sources detected by recent large-area radio surveys require robust classification and characterisation. The Evolutionary Map of the Universe (EMU) is a prime example of machine-learning (ML) techniques efficiently enriching existing catalogues with classifications and derived physical properties that would be impractical to obtain from spectroscopy or colour selection alone. We aim to build a labelled sample of sources in the EMU pilot survey (EMU-PS, at 944 MHz, with rms ~ 30 uJy/beam over 270 deg2 in the southern sky) classified as being dominated by active galactic nuclei (AGNs) or non-AGN processes including star-formation. We will then use this sample to examine radio properties and redshift-dependent trends. We applied a pre-trained multi-stage ML pipeline to optical-to-infrared photometry of EMU-PS sources to derive classifications and photometric redshifts, which we used to compute additional radio properties, including luminosities. We increase the known number of AGNs and non-AGNs in the EMU-PS by more than a factor of 15 (recall 96 %) up to z ~ 5, and by nearly a factor of 100 (recall 94 %) for z > 1, respectively. In extrapolating these numbers for the full EMU survey, we expect to recover more than 3.4 million AGN candidates. A non-negligible low-redshift subsample of selected non-AGNs shows radio luminosities in excess of those expected from star formation alone, revealing detachment between photometric and radio classification. Radio-derived properties show expected trends for luminosities and a lack of evolution for in-band (800-1088 MHz) spectral indices. The ML-based pipeline provides a scalable way to produce large catalogues for the ongoing EMU survey and future Square Kilometre Array observations and reveals that multi-wavelength analysis can uncover radio populations and trends often missed by colour cuts or spectroscopy alone.
Related
- The age of the Universe from a large sample of the oldest Galactic stars
- How nanoscale physics shapes ice formation in the Universe. Rethinking gas freeze-out on dust grains
- Simulation of PBH formation in a matter-dominated universe
- Probing Multi-formation Channels of Dark Matter-Deficient Galaxies in a Simulated Universe
- How nanoscale physics shapes ice formation in the Universe: Rethinking gas freeze-out on dust grains
BibTeX
@misc{carvajal2026evolutionary,
title = {{Evolutionary Map of the Universe (EMU): Selection of active galactic nuclei and star-formation emission with machine-learning techniques}},
author = {R. Carvajal and I. Matute and J. Afonso and H. Messias and M. J. I. Brown and D. Farrah and A. M. Hopkins and J. Th. van Loon and K. J. Luken and C. M. Pennock and J. Prathap and S. S. Shabala and D. A. Leahy and S. F. Rahman and K. A. Pimbblet and T. Zafar},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.06190},
eprint = {2611.06190},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.06190},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Evolutionary Map of the Universe (EMU): Selection of active galactic nuclei and star-formation emission with machine-learning techniques
AU - R. Carvajal
AU - I. Matute
AU - J. Afonso
AU - H. Messias
AU - M. J. I. Brown
AU - D. Farrah
AU - A. M. Hopkins
AU - J. Th. van Loon
AU - K. J. Luken
AU - C. M. Pennock
AU - J. Prathap
AU - S. S. Shabala
AU - D. A. Leahy
AU - S. F. Rahman
AU - K. A. Pimbblet
AU - T. Zafar
PY - 2026
DA - 2026/11/04
PB - arXiv
DO - 10.48550/arxiv.2611.06190
UR - https://arxiv.org/abs/2611.06190
AB - Sources detected by recent large-area radio surveys require robust classification and characterisation. The Evolutionary Map of the Universe (EMU) is a prime example of machine-learning (ML) techniques efficiently enriching existing catalogues with classifications and derived physical properties that would be impractical to obtain from spectroscopy or colour selection alone. We aim to build a labelled sample of sources in the EMU pilot survey (EMU-PS, at 944 MHz, with rms ~ 30 uJy/beam over 270 deg2 in the southern sky) classified as being dominated by active galactic nuclei (AGNs) or non-AGN processes including star-formation. We will then use this sample to examine radio properties and redshift-dependent trends. We applied a pre-trained multi-stage ML pipeline to optical-to-infrared photometry of EMU-PS sources to derive classifications and photometric redshifts, which we used to compute additional radio properties, including luminosities. We increase the known number of AGNs and non-AGNs in the EMU-PS by more than a factor of 15 (recall 96 %) up to z ~ 5, and by nearly a factor of 100 (recall 94 %) for z > 1, respectively. In extrapolating these numbers for the full EMU survey, we expect to recover more than 3.4 million AGN candidates. A non-negligible low-redshift subsample of selected non-AGNs shows radio luminosities in excess of those expected from star formation alone, revealing detachment between photometric and radio classification. Radio-derived properties show expected trends for luminosities and a lack of evolution for in-band (800-1088 MHz) spectral indices. The ML-based pipeline provides a scalable way to produce large catalogues for the ongoing EMU survey and future Square Kilometre Array observations and reveals that multi-wavelength analysis can uncover radio populations and trends often missed by colour cuts or spectroscopy alone.
ER -