Deep Learning assessment of galaxy morphology in S-PLUS Data Release 1
The morphological diversity of galaxies is a relevant probe of galaxy evolution and cosmological structure formation, but the classification of galaxies in large sky surveys is becoming a significant challenge. We use data from the Stripe-82 area observed by the Southern Photometric Local Universe S...
| Autores principales: | , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Articulo Preprint |
| Lenguaje: | Inglés |
| Publicado: |
2021
|
| Materias: | |
| Acceso en línea: | http://sedici.unlp.edu.ar/handle/10915/147171 |
| Aporte de: |
| id |
I19-R120-10915-147171 |
|---|---|
| record_format |
dspace |
| institution |
Universidad Nacional de La Plata |
| institution_str |
I-19 |
| repository_str |
R-120 |
| collection |
SEDICI (UNLP) |
| language |
Inglés |
| topic |
Ciencias Astronómicas galaxies: fundamental parameters galaxies: structure techniques: image processing methods: miscellaneous surveys |
| spellingShingle |
Ciencias Astronómicas galaxies: fundamental parameters galaxies: structure techniques: image processing methods: miscellaneous surveys Bom, Clecio R. Cortesi, A. Lucatelli, G. Dias, Luciana Olivia Schubert, P. Oliveira Schwarz, G. B. Cardoso, N. M. Ev, Lima Mendes de Oliveira, C. Sodré, L. Smith Castelli, Analía Viviana Ferrari, Fabricio Damke, G. Overzier, Roderik Kanaan, Antonio Ribeiro, T. Schoenell, William Deep Learning assessment of galaxy morphology in S-PLUS Data Release 1 |
| topic_facet |
Ciencias Astronómicas galaxies: fundamental parameters galaxies: structure techniques: image processing methods: miscellaneous surveys |
| description |
The morphological diversity of galaxies is a relevant probe of galaxy evolution and cosmological structure formation, but the classification of galaxies in large sky surveys is becoming a significant challenge. We use data from the Stripe-82 area observed by the Southern Photometric Local Universe Survey (S-PLUS) in 12 optical bands, and present a catalogue of the morphologies of galaxies brighter than r = 17 mag determined both using a novel multiband morphometric fitting technique and Convolutional Neural Networks (CNNs) for computer vision. Using the CNNs, we find that, compared to our baseline results with three bands, the performance increases when using 5 broad and 3 narrow bands, but is poorer when using the full 12 band S-PLUS image set. However, the best result is still achieved with just three optical bands when using pre-trained network weights from an ImageNet data set. These results demonstrate the importance of using prior knowledge about neural network weights based on training in unrelated, extensive data sets, when available. Our catalogue contains 3274 galaxies in Stripe-82 that are not present in Galaxy Zoo 1 (GZ1), and we also provide our classifications for 4686 galaxies that were considered ambiguous in GZ1. Finally, we present a prospect of a novel way to take advantage of 12 band information for morphological classification using morphometric features, and we release a model that has been pre-trained on several bands that could be adapted for classifications using data from other surveys. The morphological catalogues are publicly available. |
| format |
Articulo Preprint |
| author |
Bom, Clecio R. Cortesi, A. Lucatelli, G. Dias, Luciana Olivia Schubert, P. Oliveira Schwarz, G. B. Cardoso, N. M. Ev, Lima Mendes de Oliveira, C. Sodré, L. Smith Castelli, Analía Viviana Ferrari, Fabricio Damke, G. Overzier, Roderik Kanaan, Antonio Ribeiro, T. Schoenell, William |
| author_facet |
Bom, Clecio R. Cortesi, A. Lucatelli, G. Dias, Luciana Olivia Schubert, P. Oliveira Schwarz, G. B. Cardoso, N. M. Ev, Lima Mendes de Oliveira, C. Sodré, L. Smith Castelli, Analía Viviana Ferrari, Fabricio Damke, G. Overzier, Roderik Kanaan, Antonio Ribeiro, T. Schoenell, William |
| author_sort |
Bom, Clecio R. |
| title |
Deep Learning assessment of galaxy morphology in S-PLUS Data Release 1 |
| title_short |
Deep Learning assessment of galaxy morphology in S-PLUS Data Release 1 |
| title_full |
Deep Learning assessment of galaxy morphology in S-PLUS Data Release 1 |
| title_fullStr |
Deep Learning assessment of galaxy morphology in S-PLUS Data Release 1 |
| title_full_unstemmed |
Deep Learning assessment of galaxy morphology in S-PLUS Data Release 1 |
| title_sort |
deep learning assessment of galaxy morphology in s-plus data release 1 |
| publishDate |
2021 |
| url |
http://sedici.unlp.edu.ar/handle/10915/147171 |
| work_keys_str_mv |
AT bomclecior deeplearningassessmentofgalaxymorphologyinsplusdatarelease1 AT cortesia deeplearningassessmentofgalaxymorphologyinsplusdatarelease1 AT lucatellig deeplearningassessmentofgalaxymorphologyinsplusdatarelease1 AT diaslucianaolivia deeplearningassessmentofgalaxymorphologyinsplusdatarelease1 AT schubertp deeplearningassessmentofgalaxymorphologyinsplusdatarelease1 AT oliveiraschwarzgb deeplearningassessmentofgalaxymorphologyinsplusdatarelease1 AT cardosonm deeplearningassessmentofgalaxymorphologyinsplusdatarelease1 AT evlima deeplearningassessmentofgalaxymorphologyinsplusdatarelease1 AT mendesdeoliveirac deeplearningassessmentofgalaxymorphologyinsplusdatarelease1 AT sodrel deeplearningassessmentofgalaxymorphologyinsplusdatarelease1 AT smithcastellianaliaviviana deeplearningassessmentofgalaxymorphologyinsplusdatarelease1 AT ferrarifabricio deeplearningassessmentofgalaxymorphologyinsplusdatarelease1 AT damkeg deeplearningassessmentofgalaxymorphologyinsplusdatarelease1 AT overzierroderik deeplearningassessmentofgalaxymorphologyinsplusdatarelease1 AT kanaanantonio deeplearningassessmentofgalaxymorphologyinsplusdatarelease1 AT ribeirot deeplearningassessmentofgalaxymorphologyinsplusdatarelease1 AT schoenellwilliam deeplearningassessmentofgalaxymorphologyinsplusdatarelease1 |
| bdutipo_str |
Repositorios |
| _version_ |
1764820461043056640 |