Show simple item record

dc.contributor.authorSánchez, H. Domínguez
dc.contributor.authorHuertas-Company, M.
dc.contributor.authorBernardi, M.
dc.contributor.authorKaviraj, S.
dc.contributor.authorFischer, J. L.
dc.contributor.authorAbbott, T. M. C.
dc.contributor.authorAbdalla, F. B.
dc.contributor.authorAnnis, J.
dc.contributor.authorAvila, S.
dc.contributor.authorBuckley-Geer, E.
dc.contributor.authorRosell, A. Carnero
dc.contributor.authorKind, M. Carrasco
dc.contributor.authorCarretero, J.
dc.contributor.authorCunha, C. E.
dc.contributor.authorD'Andrea, C. B.
dc.contributor.authorCosta, L. N. da
dc.contributor.authorDavis, C.
dc.contributor.authorVicente, J. De
dc.contributor.authorDoel, P.
dc.contributor.authorEvrard, A. E.
dc.contributor.authorFosalba, P.
dc.contributor.authorFrieman, J.
dc.contributor.authorGarcía-Bellido, J.
dc.contributor.authorGaztanaga, E.
dc.contributor.authorGerdes, D. W.
dc.contributor.authorGruen, D.
dc.contributor.authorGruendl, R. A.
dc.contributor.authorGschwend, J.
dc.contributor.authorGutierrez, G.
dc.contributor.authorHartley, W. G.
dc.contributor.authorHollowood, D. L.
dc.contributor.authorHonscheid, K.
dc.contributor.authorHoyle, B.
dc.contributor.authorKuehn, K.
dc.contributor.authorKuropatkin, N.
dc.contributor.authorLahav, O.
dc.contributor.authorMaia, M. A. G.
dc.contributor.authorMarch, M.
dc.contributor.authorMelchior, P.
dc.contributor.authorMenanteau, F.
dc.contributor.authorMiquel, R.
dc.contributor.authorNord, B.
dc.contributor.authorPlazas, A. A.
dc.contributor.authorSanchez, E.
dc.contributor.authorScarpine, V.
dc.contributor.authorSchindler, R.
dc.contributor.authorSchubnell, M.
dc.contributor.authorSoares-Santos, M.
dc.contributor.authorSobreira, F.
dc.contributor.authorSuchyta, E.
dc.contributor.authorSwanson, M. E. C.
dc.contributor.authorTarle, G.
dc.contributor.authorWalker, A. R.
dc.contributor.authorZuntz, J.
dc.date.accessioned2019-02-08T15:45:02Z
dc.date.available2019-02-08T15:45:02Z
dc.date.issued2018-12-28
dc.identifier.citationSánchez , H D , Huertas-Company , M , Bernardi , M , Kaviraj , S , Fischer , J L , Abbott , T M C , Abdalla , F B , Annis , J , Avila , S , Buckley-Geer , E , Rosell , A C , Kind , M C , Carretero , J , Cunha , C E , D'Andrea , C B , Costa , L N D , Davis , C , Vicente , J D , Doel , P , Evrard , A E , Fosalba , P , Frieman , J , García-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 , 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 , Soares-Santos , M , Sobreira , F , Suchyta , E , Swanson , M E C , Tarle , G , Walker , A R & Zuntz , J 2018 , ' Transfer learning for galaxy morphology from one survey to another ' , Monthly Notices of the Royal Astronomical Society , vol. 484 , no. 1 , pp. 93-100 . https://doi.org/10.1093/mnras/sty3497
dc.identifier.issn0035-8711
dc.identifier.otherPURE: 16159247
dc.identifier.otherPURE UUID: acf75012-b5e0-416b-b47b-c7f219ffce61
dc.identifier.otherArXiv: http://arxiv.org/abs/1807.00807v3
dc.identifier.otherScopus: 85062264285
dc.identifier.urihttp://hdl.handle.net/2299/21049
dc.description© 2018 The Author(s). Published by Oxford University Press on behalf of the Royal Astronomical Society.
dc.description.abstractDeep 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 dataset, 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 $\sim$5000 galaxies with a similar redshift distribution to SDSS. Applying the models directly to DES data provides a reasonable global accuracy ($\sim$ 90%), but small completeness and purity values. A fast domain adaptation step, consisting in a further training with a small DES sample of galaxies ($\sim$500-300), is enough for obtaining an accuracy > 95% and a significant improvement in the completeness and purity values. This demonstrates that, once trained with a particular dataset, 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.en
dc.format.extent8
dc.language.isoeng
dc.relation.ispartofMonthly Notices of the Royal Astronomical Society
dc.rightsOpen
dc.subjectastro-ph.GA
dc.titleTransfer learning for galaxy morphology from one survey to anotheren
dc.contributor.institutionCentre for Astrophysics Research
dc.contributor.institutionSchool of Physics, Astronomy and Mathematics
dc.contributor.institutionCentre of Data Innovation Research
dc.description.statusPeer reviewed
dc.relation.schoolSchool of Physics, Astronomy and Mathematics
dc.description.versiontypeFinal Accepted Version
dcterms.dateAccepted2018-12-28
rioxxterms.versionAM
rioxxterms.versionofrecordhttps://doi.org/10.1093/mnras/sty3497
rioxxterms.typeJournal Article/Review
herts.preservation.rarelyaccessedtrue
herts.rights.accesstypeOpen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record