Navigation auf zora.uzh.ch

Search ZORA

ZORA (Zurich Open Repository and Archive)

Euclid Preparation TBD. Characterization of convolutional neural networks for the identification of galaxy-galaxy strong lensing events

Leuzzi, L; Meneghetti, M; Angora, G; Metcalf, R B; Moscardini, L; Rosati, P; Bergamini, P; Calura, F; Clément, B; Gavazzi, R; Gentile, F; Lochner, M; Grillo, C; Vernardos, G; Aghanim, N; Amara, A; Amendola, L; Auricchio, N; Bodendorf, C; Bonino, D; Branchini, E; Brescia, M; Brinchmann, J; Camera, S; Capobianco, V; Carbone, C; Carretero, J; Castellano, M; Cavuoti, S; et al (2024). Euclid Preparation TBD. Characterization of convolutional neural networks for the identification of galaxy-galaxy strong lensing events. Astronomy and Astrophysics, 681:A68.

Abstract

Forthcoming imaging surveys will increase the number of known galaxy-scale strong lenses by several orders of magnitude. For this to happen, images of billions of galaxies will have to be inspected to identify potential candidates. In this context, deep-learning techniques are particularly suitable for finding patterns in large data sets, and convolutional neural networks (CNNs) in particular can efficiently process large volumes of images. We assess and compare the performance of three network architectures in the classification of strong-lensing systems on the basis of their morphological characteristics. In particular, we implemented a classical CNN architecture, an inception network, and a residual network. We trained and tested our networks on different subsamples of a data set of 40 000 mock images whose characteristics were similar to those expected in the wide survey planned with the ESA mission Euclid, gradually including larger fractions of faint lenses. We also evaluated the importance of adding information about the color difference between the lens and source galaxies by repeating the same training on single- and multiband images. Our models find samples of clear lenses with ≳90% precision and completeness. Nevertheless, when lenses with fainter arcs are included in the training set, the performance of the three models deteriorates with accuracy values of ~0.87 to ~0.75, depending on the model. Specifically, the classical CNN and the inception network perform similarly in most of our tests, while the residual network generally produces worse results. Our analysis focuses on the application of CNNs to high-resolution space-like images, such as those that the Euclid telescope will deliver. Moreover, we investigated the optimal training strategy for this specific survey to fully exploit the scientific potential of the upcoming observations. We suggest that training the networks separately on lenses with different morphology might be needed to identify the faint arcs. We also tested the relevance of the color information for the detection of these systems, and we find that it does not yield a significant improvement. The accuracy ranges from ~0.89 to ~0.78 for the different models. The reason might be that the resolution of the Euclid telescope in the infrared bands is lower than that of the images in the visual band.

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:07 Faculty of Science > Institute for Computational Science
Dewey Decimal Classification:530 Physics
Scopus Subject Areas:Physical Sciences > Astronomy and Astrophysics
Physical Sciences > Space and Planetary Science
Uncontrolled Keywords:Space and Planetary Science, Astronomy and Astrophysics
Language:English
Date:1 January 2024
Deposited On:03 Feb 2024 11:30
Last Modified:31 Oct 2024 02:35
Publisher:EDP Sciences
ISSN:0004-6361
OA Status:Hybrid
Free access at:Publisher DOI. An embargo period may apply.
Publisher DOI:https://doi.org/10.1051/0004-6361/202347244
Download PDF  'Euclid Preparation TBD. Characterization of convolutional neural networks for the identification of galaxy-galaxy strong lensing events'.
Preview
  • Content: Published Version
  • Language: English
  • Licence: Creative Commons: Attribution 4.0 International (CC BY 4.0)

Metadata Export

Statistics

Citations

Altmetrics

Downloads

3 downloads since deposited on 03 Feb 2024
3 downloads since 12 months
Detailed statistics

Authors, Affiliations, Collaborations

Similar Publications