Please use this identifier to cite or link to this item: http://repositorio.unicamp.br/jspui/handle/REPOSIP/341089
Type: Artigo
Title: Transfer learning for galaxy morphology from one survey to another
Author: Sanchez, H. D.
Huertas-Company, M.
Bernardi, M.
Kaviraj, S.
Fischer, J. L.
Abbott, T. M. C.
Abdalla, F. B.
Annis, J.
Avila, S.
Brooks, D.
Buckley-Geer, E.
Rosell, A. C.
Kind, M. C.
Carretero, J.
Cunha, C. E.
D'Andrea, C. B.
da Costa, L. N.
Davis, C.
De Vicente, J.
Doel, P.
Evrard, A. E.
Fosalba, P.
Frieman, J.
Garcia-Bellido, J.
Gaztanaga, E.
Gerdes, D. W.
Gruen, D.
Gruendl, R. A.
Gschwend, J.
Gutierrez, G.
Hartley, W. G.
Hollowood, D. L.
Honscheid, K.
Hoyle, B.
James, D. J.
Kuehn, K.
Kuropatkin, N.
Lahav, O.
Maia, M. A. G.
March, M.
Melchior, P.
Menanteau, F.
Miquel, R.
Nord, B.
Plazas, A. A.
Sanchez, E.
Scarpine, V.
Schindler, R.
Schubnell, M.
Smith, M.
Smith, R. C.
Soares-Santos, M.
Sobreira, F.
Suchyta, E.
Swanson, M. E. C.
Tarle, G.
Thomas, D.
Walker, A. R.
Zuntz, J.
Abstract: Deep learning (DL) algorithms for morphological classification of galaxies have proven very successful, mimicking (or even improving) visual classifications. However, these algorithms rely on large training samples of labelled galaxies (typically thousands of them). A key question for using DL classifications in future Big Data surveys is how much of the knowledge acquired from an existing survey can be exported to a new data set, i.e. if the features learned by the machines are meaningful for different data. We test the performance of DL models, trained with Sloan Digital Sky Survey (SDSS) data, on Dark Energy Survey (DES) using images for a sample of similar to 5000 galaxies with a similar redshift distribution to SDSS. Applying the models directly to DES data provides a reasonable global accuracy (similar to 90 per cent), but small completeness and purity values. A fast domain adaptation step, consisting of a further training with a small DES sample of galaxies (similar to 500-300), is enough for obtaining an accuracy gt;95 per cent and a significant improvement in the completeness and purity values. This demonstrates that, once trained with a particular data set, machines can quickly adapt to new instrument characteristics (e.g. PSF, seeing, depth), reducing by almost one order of magnitude the necessary training sample for morphological classification. Redshift evolution effects or significant depth differences are not taken into account in this study.
Subject: Fotometria
Levantamentos
Galáxias
Photometry
Surveys
Galaxies
Country: Reino Unido
Editor: Oxford University Press
Rights: aberto
Identifier DOI: 10.1093/mnras/sty3497
Address: https://academic.oup.com/mnras/article/484/1/93/5266389
Date Issue: 2019
Appears in Collections:IFGW - Artigos e Outros Documentos

Files in This Item:
File SizeFormat 
000462293100008.pdf1.1 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.