%0 Journal Article
%A Huertas Company, M.
%A Gravet, R.
%A Cabrera Vives, G.
%A Pérez González, Pablo Guillermo
%A Kartaltepe, J. S.
%A Barro, G.
%A Bernardi, M.
%A Mei, S.
%A Shankar, F.
%A Dimauro, P.
%A Bell, E. F.
%A Kocevski, D.
%A Koo, D. C.
%A Faber, S. M.
%A Mcintosh, D. H.
%T A catalog of visual-like morphologies in the 5 candels fields using deep learning
%D 2015
%@ 0067-0049
%U https://hdl.handle.net/20.500.14352/24298
%X We present a catalog of visual-like H-band morphologies of ~50.000 galaxies (H_f160w < 24.5) in the 5 CANDELS fields (GOODS-N, GOODS-S, UDS, EGS, and COSMOS). Morphologies are estimated using Convolutional Neural Networks (ConvNets). The median redshift of the sample is < z> 1.25. The algorithm is trained on GOODS-S, for which visual classifications are publicly available, and then applied to the other 4 fields. Following the CANDELS main morphology classification scheme, our model retrieves for each galaxy the probabilities of having a spheroid or a disk, presenting an irregularity, being compact or a point source, and being unclassifiable. ConvNets are able to predict the fractions of votes given to a galaxy image with zero bias and ~10% scatter. The fraction of mis-classifications is less than 1%. Our classification scheme represents a major improvement with respect to Concentration-Asymmetry-Smoothness-based methods, which hit a 20%–30% contamination limit at high z.
%~