Stream automatic detection with convolutional neural networks

Vera-Casanova, A ORCID: 0000-0003-4312-3679, Monsalves Gonzalez, N ORCID: 0000-0002-4129-8195, Gómez, FA ORCID: 0000-0003-4232-8584, Jaque Arancibia, M ORCID: 0000-0002-8086-5746, Fontirroig, V ORCID: 0009-0000-1589-9766, Pallero, D ORCID: 0000-0002-1577-7475, Pakmor, R ORCID: 0000-0003-3308-2420, Van De Voort, F ORCID: 0000-0002-6301-638X, Grand, RJJ ORCID: 0000-0001-9667-1340, Bieri, R and Marinacci, F (2025) Stream automatic detection with convolutional neural networks. Astronomy and Astrophysics, 704. ISSN 0004-6361

Preview

Text Stream automatic detection with convolutional neural networks.pdf - Published Version Available under License Creative Commons Attribution. Download (1MB) | Preview

Abstract

Context. Galactic halos host faint substructures such as stellar streams and shells, which provide insights into the hierarchical assembly history of galaxies. To date, such features have been identified in external galaxies by visual inspection. However, with the advent of larger and deeper surveys and the associated increase in data volume, this methodology is becoming impractical.

Aims. Here we aim to develop an automated method to detect low surface brightness features in galactic stellar halos. Moreover, we seek to quantify the performance of this method when considering progressively more complex datasets, including different stellar disc orientations and redshifts. Methods. We have developed the stream automatic detection with convolutional neural networks (SAD-CNNs) models. This tool was trained on mock surface brightness maps obtained from simulations of the Auriga Project. The model incorporates transfer learning, data augmentation, and balanced datasets to optimise its detection capabilities at surface brightness limiting magnitudes ranging from 27 to 31 mag arcsec−2.

Results. The iterative training approach, coupled with transfer learning, allowed the model to adapt to increasingly challenging datasets, achieving precision and recall metrics above 80% in all considered scenarios. The use of a well-balanced training dataset is critical for mitigating biases and ensuring that the CNN accurately distinguishes between galaxies with and without streams.

Conclusions. SAD-CNN is a reliable and scalable tool for automating the detection of faint substructures in galactic halos. Its adaptability makes it well suited to future applications that would include the analysis of data from upcoming large astronomical surveys such as LSST and JWT.

Item Type:	Article
Uncontrolled Keywords:	5109 Space Sciences; 5107 Particle and High Energy Physics; 5101 Astronomical Sciences; 51 Physical Sciences; Bioengineering; Networking and Information Technology R&D (NITRD); 0201 Astronomical and Space Sciences; Astronomy & Astrophysics; 5101 Astronomical sciences; 5107 Particle and high energy physics; 5109 Space sciences
Subjects:	Q Science > QB Astronomy Q Science > QC Physics
Divisions:	Astrophysics Research Institute
Publisher:	EDP Sciences
Date of acceptance:	15 September 2025
Date of first compliant Open Access:	8 January 2026
Date Deposited:	08 Jan 2026 15:47
Last Modified:	08 Jan 2026 15:47
DOI or ID number:	10.1051/0004-6361/202554688
URI:	https://researchonline.ljmu.ac.uk/id/eprint/27826

View Item