Lessons learned from the two largest Galaxy morphological classification catalogues built by convolutional neural networks

Cheng, T. -Y.; Domínguez Sánchez, H.; Vega-Ferrero, J.; Conselice, C. J.; Siudek, M.; Aragón-Salamanca, A.; Bernardi, M.; Cooke, R.; Ferreira, L.; Huertas-Company, M.; Krywult, J.; Palmese, A.; Pieres, A.; Plazas Malagón, A. A.; Carnero Rosell, A.; Gruen, D.; Thomas, D.; Bacon, D.; Brooks, D.; James, D. J.; Hollowood, D. L.; Friedel, D.; Suchyta, E.; Sanchez, E.; Menanteau, F.; Paz-Chinchón, F.; Gutierrez, G.; Tarle, G.; Sevilla-Noarbe, I.; Ferrero, I.; Annis, J.; Frieman, J.; García-Bellido, J.; Mena-Fernández, J.; Honscheid, K.; Kuehn, K.; da Costa, L. N.; Gatti, M.; Raveri, M.; Pereira, M. E. S.; Rodriguez-Monroy, M.; Smith, M.; Carrasco Kind, M.; Aguena, M.; Swanson, M. E. C.; Weaverdyck, N.; Doel, P.; Miquel, R.; Ogando, R. L. C.; Gruendl, R. A.; Allam, S.; Hinton, S. R.; Dodelson, S.; Bocquet, S.; Desai, S.; Everett, S.; Scarpine, V.
Bibliographical reference

Monthly Notices of the Royal Astronomical Society

Advertised on:
1
2023
Number of authors
57
IAC number of authors
2
Citations
6
Refereed citations
4
Description
We compare the two largest galaxy morphology catalogues, which separate early- and late-type galaxies at intermediate redshift. The two catalogues were built by applying supervised deep learning (convolutional neural networks, CNNs) to the Dark Energy Survey data down to a magnitude limit of ~21 mag. The methodologies used for the construction of the catalogues include differences such as the cutout sizes, the labels used for training, and the input to the CNN - monochromatic images versus gri-band normalized images. In addition, one catalogue is trained using bright galaxies observed with DES (i < 18), while the other is trained with bright galaxies (r < 17.5) and 'emulated' galaxies up to r-band magnitude 22.5. Despite the different approaches, the agreement between the two catalogues is excellent up to i < 19, demonstrating that CNN predictions are reliable for samples at least one magnitude fainter than the training sample limit. It also shows that morphological classifications based on monochromatic images are comparable to those based on gri-band images, at least in the bright regime. At fainter magnitudes, i > 19, the overall agreement is good (~95 per cent), but is mostly driven by the large spiral fraction in the two catalogues. In contrast, the agreement within the elliptical population is not as good, especially at faint magnitudes. By studying the mismatched cases, we are able to identify lenticular galaxies (at least up to i < 19), which are difficult to distinguish using standard classification approaches. The synergy of both catalogues provides an unique opportunity to select a population of unusual galaxies.
Related projects
Group members
Traces of Galaxy Formation: Stellar populations, Dynamics and Morphology
We are a large, diverse, and very active research group aiming to provide a comprehensive picture for the formation of galaxies in the Universe. Rooted in detailed stellar population analysis, we are constantly exploring and developing new tools and ideas to understand how galaxies came to be what we now observe.
Ignacio
Martín Navarro
 The Invisible Scaffolding of Space
Cosmology with Large Scale Structure Probes
The Cosmic Microwave Background (CMB) contains the statistical information about the early seeds of the structure formation in our Universe. Its natural counterpart in the local universe is the distribution of galaxies that arises as a result of gravitational growth of those primordial and small density fluctuations. The characterization of the
FRANCISCO SHU
KITAURA JOYANES