Rights statement: The final, definitive version of this article has been published in the Journal, Astronomy and Astrophysics, 645, 2021, © EDP Sciences.
Accepted author manuscript, 1.06 MB, PDF document
Final published version
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - The miniJPAS survey
T2 - star-galaxy classification using machine learning
AU - Baqui, P. O.
AU - Marra, V.
AU - Casarini, L.
AU - Angulo, R.
AU - Díaz-García, L. A.
AU - Hernández-Monteagudo, C.
AU - Lopes, P. A. A.
AU - López-Sanjuan, C.
AU - Muniesa, D.
AU - Placco, V. M.
AU - Quartin, M.
AU - Queiroz, C.
AU - Sobral, D.
AU - Solano, E.
AU - Tempel, E.
AU - Varela, J.
AU - Vílchez, J. M.
AU - Abramo, R.
AU - Alcaniz, J.
AU - Benitez, N.
AU - Bonoli, S.
AU - Carneiro, S.
AU - Cenarro, J.
AU - Cristóbal-Hornillos, D.
AU - Amorim, A. L. de
AU - Oliveira, C. M. de
AU - Dupke, R.
AU - Ederoclite, A.
AU - Delgado, R. M. González
AU - Marín-Franch, A.
AU - Moles, M.
AU - Ramió, H. Vázquez
AU - Sodré, L.
N1 - The final, definitive version of this article has been published in the Journal, Astronomy and Astrophysics, 645, 2021, © EDP Sciences.
PY - 2021/1/18
Y1 - 2021/1/18
N2 - Future astrophysical surveys such as J-PAS will produce very large datasets, which will require the deployment of accurate and efficient Machine Learning (ML) methods. In this work, we analyze the miniJPAS survey, which observed about 1 deg2 of the AEGIS field with 56 narrow-band filters and 4 ugri broad-band filters. We discuss the classification of miniJPAS sources into extended (galaxies) and point-like (e.g. stars) objects, a necessary step for the subsequent scientific analyses. We aim at developing an ML classifier that is complementary to traditional tools based on explicit modeling. In order to train and test our classifiers, we crossmatched the miniJPAS dataset with SDSS and HSC-SSP data. We trained and tested 6 different ML algorithms on the two crossmatched catalogs. As input for the ML algorithms we use the magnitudes from the 60 filters together with their errors, with and without the morphological parameters. We also use the mean PSF in the r detection band for each pointing. We find that the RF and ERT algorithms perform best in all scenarios. When analyzing the full magnitude range of 1521). We use our best classifiers, with and without morphology, in order to produce a value added catalog available at https://j-pas.org/datareleases .
AB - Future astrophysical surveys such as J-PAS will produce very large datasets, which will require the deployment of accurate and efficient Machine Learning (ML) methods. In this work, we analyze the miniJPAS survey, which observed about 1 deg2 of the AEGIS field with 56 narrow-band filters and 4 ugri broad-band filters. We discuss the classification of miniJPAS sources into extended (galaxies) and point-like (e.g. stars) objects, a necessary step for the subsequent scientific analyses. We aim at developing an ML classifier that is complementary to traditional tools based on explicit modeling. In order to train and test our classifiers, we crossmatched the miniJPAS dataset with SDSS and HSC-SSP data. We trained and tested 6 different ML algorithms on the two crossmatched catalogs. As input for the ML algorithms we use the magnitudes from the 60 filters together with their errors, with and without the morphological parameters. We also use the mean PSF in the r detection band for each pointing. We find that the RF and ERT algorithms perform best in all scenarios. When analyzing the full magnitude range of 1521). We use our best classifiers, with and without morphology, in order to produce a value added catalog available at https://j-pas.org/datareleases .
KW - astro-ph.IM
U2 - 10.1051/0004-6361/202038986
DO - 10.1051/0004-6361/202038986
M3 - Journal article
VL - 645
JO - Astronomy and Astrophysics
JF - Astronomy and Astrophysics
SN - 1432-0746
M1 - A87
ER -