Galaxy Morphological Classification Catalogue of the Dark Energy Survey Year 3 data with Convolutional Neural Networks

Galaxy Morphological Classification Catalogue of the Dark Energy Survey Year 3 data with Convolutional Neural Networks. Cheng, T., Conselice, C. J., Aragón-Salamanca, A., Aguena, M., Allam, S., Andrade-Oliveira, F., Annis, J., Bluck, A. F. L., Brooks, D., Burke, D. L., Carrasco Kind, M., Carretero, J., Choi, A., Costanzi, M., da Costa, L. N., Pereira, M. E. S., De Vicente, J., Diehl, H. T., Drlica-Wagner, A., Eckert, K., Everett, S., Evrard, A. E., Ferrero, I., Fosalba, P., Frieman, J., García-Bellido, J., Gerdes, D. W., Giannantonio, T., Gruen, D., Gruendl, R. A., Gschwend, J., Gutierrez, G., Hinton, S. R., Hollowood, D. L., Honscheid, K., James, D. J., Krause, E., Kuehn, K., Kuropatkin, N., Lahav, O., Maia, M. A. G., March, M., Menanteau, F., Miquel, R., Morgan, R., Paz-Chinchón, F., Pieres, A., Plazas Malagón, A. A., Roodman, A., Sanchez, E., Scarpine, V., Serrano, S., Sevilla-Noarbe, I., Smith, M., Soares-Santos, M., Suchyta, E., Swanson, M. E. C., Tarle, G., Thomas, D., & To, C. Monthly Notices of the Royal Astronomical Society, July, 2021. ADS Bibcode: 2021MNRAS.tmp.1911C

Paper doi abstract bibtex

We present in this paper one of the largest galaxy morphological classification catalogues to date, including over 20 million of galaxies, using the Dark Energy Survey (DES) Year 3 data based on Convolutional Neural Networks (CNN). Monochromatic i-band DES images with linear, logarithmic, and gradient scales, matched with debiased visual classifications from the Galaxy Zoo 1 (GZ1) catalogue, are used to train our CNN models. With a training set including bright galaxies (16 ≤ i \textless 18) at low redshift (z \textless 0.25), we furthermore investigate the limit of the accuracy of our predictions applied to galaxies at fainter magnitude and at higher redshifts. Our final catalogue covers magnitudes 16 ≤ i \textless 21, and redshifts z \textless 1.0, and provides predicted probabilities to two galaxy types - Ellipticals and Spirals (disk galaxies). Our CNN classifications reveal an accuracy of over 99% for bright galaxies when comparing with the GZ1 classifications (i \textless 18). For fainter galaxies, the visual classification carried out by three of the co-authors shows that the CNN classifier correctly categorises disky galaxies with rounder and blurred features, which humans often incorrectly visually classify as Ellipticals. As a part of the validation, we carry out one of the largest examination of non-parametric methods, including \textasciitilde100,000 galaxies with the same coverage of magnitude and redshift as the training set from our catalogue. We find that the Gini coefficient is the best single parameter discriminator between Ellipticals and Spirals for this data set.

@article{2021MNRAS.tmp.1911C,
	title = {Galaxy {Morphological} {Classification} {Catalogue} of the {Dark} {Energy} {Survey} {Year} 3 data with {Convolutional} {Neural} {Networks}},
	issn = {0035-8711},
	url = {https://ui.adsabs.harvard.edu/abs/2021MNRAS.tmp.1911C},
	doi = {10.1093/mnras/stab2142},
	abstract = {We present in this paper one of the largest galaxy morphological classification catalogues to date, including over 20 million of galaxies, using the Dark Energy Survey (DES) Year 3 data based on Convolutional Neural Networks (CNN). Monochromatic i-band DES images with linear, logarithmic, and gradient scales, matched with debiased visual classifications from the Galaxy Zoo 1 (GZ1) catalogue, are used to train our CNN models. With a training set including bright galaxies (16 ≤ i {\textless} 18) at low redshift (z {\textless} 0.25), we furthermore investigate the limit of the accuracy of our predictions applied to galaxies at fainter magnitude and at higher redshifts. Our final catalogue covers magnitudes 16 ≤ i {\textless} 21, and redshifts z {\textless} 1.0, and provides predicted probabilities to two galaxy types - Ellipticals and Spirals (disk galaxies). Our CNN classifications reveal an accuracy of over 99\% for bright galaxies when comparing with the GZ1 classifications (i {\textless} 18). For fainter galaxies, the visual classification carried out by three of the co-authors shows that the CNN classifier correctly categorises disky galaxies with rounder and blurred features, which humans often incorrectly visually classify as Ellipticals. As a part of the validation, we carry out one of the largest examination of non-parametric methods, including {\textasciitilde}100,000 galaxies with the same coverage of magnitude and redshift as the training set from our catalogue. We find that the Gini coefficient is the best single parameter discriminator between Ellipticals and Spirals for this data set.},
	urldate = {2021-09-07},
	journal = {Monthly Notices of the Royal Astronomical Society},
	author = {Cheng, Ting-Yun and Conselice, Christopher J. and Aragón-Salamanca, Alfonso and Aguena, M. and Allam, S. and Andrade-Oliveira, F. and Annis, J. and Bluck, A. F. L. and Brooks, D. and Burke, D. L. and Carrasco Kind, M. and Carretero, J. and Choi, A. and Costanzi, M. and da Costa, L. N. and Pereira, M. E. S. and De Vicente, J. and Diehl, H. T. and Drlica-Wagner, A. and Eckert, K. and Everett, S. and Evrard, A. E. and Ferrero, I. and Fosalba, P. and Frieman, J. and García-Bellido, J. and Gerdes, D. W. and Giannantonio, T. and Gruen, D. and Gruendl, R. A. and Gschwend, J. and Gutierrez, G. and Hinton, S. R. and Hollowood, D. L. and Honscheid, K. and James, D. J. and Krause, E. and Kuehn, K. and Kuropatkin, N. and Lahav, O. and Maia, M. A. G. and March, M. and Menanteau, F. and Miquel, R. and Morgan, R. and Paz-Chinchón, F. and Pieres, A. and Plazas Malagón, A. A. and Roodman, A. and Sanchez, E. and Scarpine, V. and Serrano, S. and Sevilla-Noarbe, I. and Smith, M. and Soares-Santos, M. and Suchyta, E. and Swanson, M. E. C. and Tarle, G. and Thomas, D. and To, C.},
	month = jul,
	year = {2021},
	note = {ADS Bibcode: 2021MNRAS.tmp.1911C},
	keywords = {Astrophysics - Astrophysics of Galaxies, catalogues, galaxies: structure, methods: data analysis, methods: observational},
}

Downloads: 0