Euclid preparation : XXXIII. Characterization of convolutional neural networks for the identification of galaxy-galaxy strong-lensing events

Simple item page
dc.contributorAalto-yliopistofi
dc.contributorAalto Universityen
dc.contributor.authorLeuzzi, L.en_US
dc.contributor.authorMeneghetti, M.en_US
dc.contributor.authorAngora, G.en_US
dc.contributor.authorMetcalf, R. B.en_US
dc.contributor.authorMoscardini, L.en_US
dc.contributor.authorRosati, P.en_US
dc.contributor.authorBergamini, P.en_US
dc.contributor.authorCalura, F.en_US
dc.contributor.authorClément, B.en_US
dc.contributor.authorGavazzi, R.en_US
dc.contributor.authorGentile, F.en_US
dc.contributor.authorLochner, M.en_US
dc.contributor.authorGrillo, C.en_US
dc.contributor.authorVernardos, G.en_US
dc.contributor.authorAghanim, N.en_US
dc.contributor.authorAmara, A.en_US
dc.contributor.authorAmendola, L.en_US
dc.contributor.authorAuricchio, N.en_US
dc.contributor.authorBodendorf, C.en_US
dc.contributor.authorBonino, D.en_US
dc.contributor.authorBranchini, E.en_US
dc.contributor.authorBrescia, M.en_US
dc.contributor.authorBrinchmann, J.en_US
dc.contributor.authorCamera, S.en_US
dc.contributor.authorCapobianco, V.en_US
dc.contributor.authorCarbone, C.en_US
dc.contributor.authorCarretero, J.en_US
dc.contributor.authorCastellano, M.en_US
dc.contributor.authorCavuoti, S.en_US
dc.contributor.authorCimatti, A.en_US
dc.contributor.authorCledassou, R.en_US
dc.contributor.authorCongedo, G.en_US
dc.contributor.authorConselice, C. J.en_US
dc.contributor.authorConversi, L.en_US
dc.contributor.authorCopin, Y.en_US
dc.contributor.authorCorcione, L.en_US
dc.contributor.authorCourbin, F.en_US
dc.contributor.authorCropper, M.en_US
dc.contributor.authorDa Silva, A.en_US
dc.contributor.authorDegaudenzi, H.en_US
dc.contributor.authorDinis, J.en_US
dc.contributor.authorDubath, F.en_US
dc.contributor.authorDupac, X.en_US
dc.contributor.authorDusini, S.en_US
dc.contributor.authorFarrens, S.en_US
dc.contributor.authorNiemi, S. M.en_US
dc.contributor.authorSchneider, P.en_US
dc.contributor.authorWang, Y.en_US
dc.contributor.authorGozaliasl, G.en_US
dc.contributor.authorSánchez, A. G.en_US
dc.contributor.author, Euclid Collaborationen_US
dc.contributor.departmentDepartment of Computer Scienceen
dc.contributor.organizationUniversitá di Bolognaen_US
dc.contributor.organizationIstituto di Astrofisica Spaziale e Fisica Cosmica di Bolognaen_US
dc.contributor.organizationUniversity of Ferraraen_US
dc.contributor.organizationSwiss Federal Institute of Technology Lausanneen_US
dc.contributor.organizationAix-Marseille Universitéen_US
dc.contributor.organizationUniversity of the Western Capeen_US
dc.contributor.organizationUniversity of Milanen_US
dc.contributor.organizationUniversité Paris-Saclayen_US
dc.contributor.organizationUniversity of Portsmouthen_US
dc.contributor.organizationHeidelberg University en_US
dc.contributor.organizationMax Planck Institute for Extraterrestrial Physicsen_US
dc.contributor.organizationNational Institute for Astrophysics (INAF)en_US
dc.contributor.organizationUniversity of Genoaen_US
dc.contributor.organizationOsservatorio Astronomico di Capodimonteen_US
dc.contributor.organizationUniversidade do Portoen_US
dc.contributor.organizationIstituto Nazionale di Astrofisica (INAF)en_US
dc.contributor.organizationInstitute for High Energy Physicsen_US
dc.contributor.organizationOsservatorio Astronomico di Romaen_US
dc.contributor.organizationCentre national d'études spatialesen_US
dc.contributor.organizationUniversity of Edinburghen_US
dc.contributor.organizationUniversity of Manchesteren_US
dc.contributor.organizationESRIN - ESA Centre for Earth Observationen_US
dc.contributor.organizationUniversité Claude Bernard Lyon 1en_US
dc.contributor.organizationUniversity College Londonen_US
dc.contributor.organizationUniversity of Lisbonen_US
dc.contributor.organizationUniversity of Genevaen_US
dc.contributor.organizationUrbanización Villafranca Del Castilloen_US
dc.contributor.organizationNational Institute for Nuclear Physicsen_US
dc.contributor.organizationEuropean Space Research and Technology Centreen_US
dc.contributor.organizationUniversity of Bonnen_US
dc.contributor.organizationCalifornia Institute of Technologyen_US
dc.date.accessioned2024-02-07T08:19:32Z
dc.date.available2024-02-07T08:19:32Z
dc.date.issued2024-01-01en_US
dc.descriptionFunding Information: The authors acknowledge the Euclid Consortium, the European Space Agency, and a number of agencies and institutes that have supported the development of Euclid, in particular the Academy of Finland, the Agenzia Spaziale Italiana, the Belgian Science Policy, the Canadian Euclid Consortium, the French Centre National d’Etudes Spatiales, the Deutsches Zentrum für Luft- und Raumfahrt, the Danish Space Research Institute, the Fundação para a Ciência e a Tecnologia, the Ministerio de Ciencia e Innovación, the National Aeronautics and Space Administration, the National Astronomical Observatory of Japan, the Netherlandse Onderzoekschool Voor Astronomie, the Norwegian Space Agency, the Romanian Space Agency, the State Secretariat for Education, Research and Innovation (SERI) at the Swiss Space Office (SSO), and the United Kingdom Space Agency. A complete and detailed list is available on the Euclid web site ( http://www.euclid-ec.org ). We acknowledge support from the grants PRIN-MIUR 2017 WSCC32, PRIN-MIUR 2020 SKSTHZ and ASI no. 2018-23-HH.0. M.M. was supported by INAF Grant "The Big-Data era of cluster lensing". This work has made use of CosmoHub. CosmoHub has been developed by the Port d’Informació Científica (PIC), maintained through a collaboration of the Institut de Física d’Altes Energies (IFAE) and the Centro de Investigaciones Energéticas, Medioambientales y Tecnológicas (CIEMAT) and the Institute of Space Sciences (CSIC & IEEC), and was partially funded by the "Plan Estatal de Investigación Científica y Técnica y de Innovación" program of the Spanish government. Publisher Copyright: © 2024 EDP Sciences. All rights reserved.
dc.description.abstractForthcoming 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.en
dc.description.versionPeer revieweden
dc.format.extent23
dc.format.extent1-23
dc.format.mimetypeapplication/pdfen_US
dc.identifier.citationLeuzzi, 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, Cimatti, A, Cledassou, R, Congedo, G, Conselice, C J, Conversi, L, Copin, Y, Corcione, L, Courbin, F, Cropper, M, Da Silva, A, Degaudenzi, H, Dinis, J, Dubath, F, Dupac, X, Dusini, S, Farrens, S, Niemi, S M, Schneider, P, Wang, Y, Gozaliasl, G, Sánchez, A G & Euclid Collaboration 2024, ' Euclid preparation : XXXIII. Characterization of convolutional neural networks for the identification of galaxy-galaxy strong-lensing events ', Astronomy and Astrophysics, vol. 681, A68, pp. 1-23 . https://doi.org/10.1051/0004-6361/202347244en
dc.identifier.doi10.1051/0004-6361/202347244en_US
dc.identifier.issn0004-6361
dc.identifier.issn1432-0746
dc.identifier.otherPURE UUID: 9143589c-f56b-431f-9ec2-04de53d49b8cen_US
dc.identifier.otherPURE ITEMURL: https://research.aalto.fi/en/publications/9143589c-f56b-431f-9ec2-04de53d49b8cen_US
dc.identifier.otherPURE LINK: http://www.scopus.com/inward/record.url?scp=85182904839&partnerID=8YFLogxKen_US
dc.identifier.otherPURE FILEURL: https://research.aalto.fi/files/135669408/Euclid_preparation_-_XXXIII._Characterization_of_convolutional_neural_networks_for_the_identification_of_galaxy-galaxy_strong-lensing_events.pdfen_US
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/126700
dc.identifier.urnURN:NBN:fi:aalto-202402072359
dc.language.isoenen
dc.publisherEDP Sciences
dc.relation.ispartofseriesAstronomy and Astrophysicsen
dc.relation.ispartofseriesVolume 681en
dc.rightsopenAccessen
dc.subject.keywordGravitational lensing: strongen_US
dc.subject.keywordMethods: data analysisen_US
dc.subject.keywordMethods: statisticalen_US
dc.subject.keywordSurveysen_US
dc.titleEuclid preparation : XXXIII. Characterization of convolutional neural networks for the identification of galaxy-galaxy strong-lensing eventsen
dc.typeA1 Alkuperäisartikkeli tieteellisessä aikakauslehdessäfi
dc.type.versionpublishedVersion
Files
Collections
[article-cris] Perustieteiden korkeakoulu / SCI