Skip to main content

Research Repository

Advanced Search

Lessons Learned from the Two Largest Galaxy Morphological Classification Catalogues built by Convolutional Neural Networks

Cheng, Ting-Yun; 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


Ting-Yun Cheng

H Domínguez Sánchez

J Vega-Ferrero

C J Conselice

M Siudek

M Bernardi

R Cooke

L Ferreira

M Huertas-Company

J Krywult

A Palmese

A Pieres

A A Plazas Malagón

A Carnero Rosell

D Gruen

D Thomas

D Bacon

D Brooks

D J James

D L Hollowood

D Friedel

E Suchyta

E Sanchez

F Menanteau

F Paz-Chinchón

G Gutierrez

G Tarle

I Sevilla-Noarbe

I Ferrero

J Annis

J Frieman

J García-Bellido

J Mena-Fernández

K Honscheid

K Kuehn

L N da Costa

M Gatti

M Raveri

M E S Pereira

M Rodriguez-Monroy

M Smith

M Carrasco Kind

M Aguena

M E C Swanson

N Weaverdyck

P Doel

R Miquel

R L C Ogando

R A Gruendl

S Allam

S R Hinton

S Dodelson

S Bocquet

S Desai

S Everett

V Scarpine


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%), 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.


Cheng, T., Domínguez Sánchez, H., Vega-Ferrero, J., Conselice, C. J., Siudek, M., Aragón-Salamanca, A., …Scarpine, V. (2023). Lessons Learned from the Two Largest Galaxy Morphological Classification Catalogues built by Convolutional Neural Networks. Monthly Notices of the Royal Astronomical Society, 518(2), 2794–2809.

Journal Article Type Article
Acceptance Date Nov 2, 2022
Online Publication Date Nov 11, 2022
Publication Date 2023-01
Deposit Date Nov 4, 2022
Publicly Available Date Nov 11, 2022
Journal Monthly Notices of the Royal Astronomical Society
Print ISSN 0035-8711
Electronic ISSN 1365-2966
Publisher Oxford University Press
Peer Reviewed Peer Reviewed
Volume 518
Issue 2
Pages 2794–2809
Keywords Space and Planetary Science, Astronomy and Astrophysics
Public URL
Publisher URL


You might also like

Downloadable Citations