The miniJPAS survey quasar selection III: Classification with artificial neural networks and hybridisation
| Title: | The miniJPAS survey quasar selection III: Classification with artificial neural networks and hybridisation |
|---|---|
| Authors: | Martínez-Solaeche, G., Queiroz, Carolina, Delgado, R. M. González, Rodrigues, Natália V. N., García-Benito, R., Pérez-Ràfols, Ignasi, Abramo, L. Raul, Díaz-García, Luis, Pieri, Matthew M., Chaves-Montero, Jonás, Hernán-Caballero, A., Rodríguez-Martín, J. E., Bonoli, Silvia, Morrison, Sean S., Márquez, Isabel, Vílchez, J. M., López-Sanjuan, C., Cenarro, A. J., Dupke, R. A., Martín-Franch, A., Varel, J., Ramió, H. Vázquez, Cristóbal-Hornillos, D., Moles, M., Alcaniz, J., Benitez, N., Fernández-Ontiveros, J. A., Ederoclite, A., Marra, V., de Oliveira, C. Mendes, Taylor, K. |
| Source: | A&A 673, A103 (2023) |
| Publication Year: | 2023 |
| Collection: | Astrophysics |
| Subject Terms: | Astrophysics - Astrophysics of Galaxies, Astrophysics - Cosmology and Nongalactic Astrophysics |
| More Details: | This paper is part of large effort within the J-PAS collaboration that aims to classify point-like sources in miniJPAS, which were observed in 60 optical bands over $\sim$ 1 deg$^2$ in the AEGIS field. We developed two algorithms based on artificial neural networks (ANN) to classify objects into four categories: stars, galaxies, quasars at low redshift ($z < 2.1)$, and quasars at high redshift ($z \geq 2.1$). As inputs, we used miniJPAS fluxes for one of the classifiers (ANN$_1$) and colours for the other (ANN$_2$). The ANNs were trained and tested using mock data in the first place. We studied the effect of augmenting the training set by creating hybrid objects, which combines fluxes from stars, galaxies, and quasars. Nevertheless, the augmentation processing did not improve the score of the ANN. We also evaluated the performance of the classifiers in a small subset of the SDSS DR12Q superset observed by miniJPAS. In the mock test set, the f1-score for quasars at high redshift with the ANN$_1$ (ANN$_2$) are $0.99$ ($0.99$), $0.93$ ($0.92$), and $0.63$ ($0.57$) for $17 < r \leq 20$, $20 < r \leq 22.5$, and $22.5 < r \leq 23.6$, respectively, where $r$ is the J-PAS rSDSS band. In the case of low-redshift quasars, galaxies, and stars, we reached $0.97$ ($0.97$), $0.82$ ($0.79$), and $0.61$ ($0.58$); $0.94$ ($0.94$), $0.90$ ($0.89$), and $0.81$ ($0.80$); and $1.0$ ($1.0$), $0.96$ ($0.94$), and $0.70$ ($0.52$) in the same r bins. In the SDSS DR12Q superset miniJPAS sample, the weighted f1-score reaches 0.87 (0.88) for objects that are mostly within $20 < r \leq 22.5$. Finally, we estimate the number of point-like sources that are quasars, galaxies, and stars in miniJPAS. |
| Document Type: | Working Paper |
| DOI: | 10.1051/0004-6361/202245750 |
| Access URL: | http://arxiv.org/abs/2303.12684 |
| Accession Number: | edsarx.2303.12684 |
| Database: | arXiv |
| FullText | Text: Availability: 0 CustomLinks: – Url: http://arxiv.org/abs/2303.12684 Name: EDS - Arxiv Category: fullText Text: View this record from Arxiv MouseOverText: View this record from Arxiv – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsarx&genre=article&issn=&ISBN=&volume=&issue=&date=20230322&spage=&pages=&title=The miniJPAS survey quasar selection III: Classification with artificial neural networks and hybridisation&atitle=The%20miniJPAS%20survey%20quasar%20selection%20III%3A%20Classification%20with%20artificial%20neural%20networks%20and%20hybridisation&aulast=Mart%C3%ADnez-Solaeche%2C%20G.&id=DOI:10.1051/0004-6361/202245750 Name: Full Text Finder (for New FTF UI) (s8985755) Category: fullText Text: Find It @ SCU Libraries MouseOverText: Find It @ SCU Libraries |
|---|---|
| Header | DbId: edsarx DbLabel: arXiv An: edsarx.2303.12684 RelevancyScore: 1051 AccessLevel: 3 PubType: Report PubTypeId: report PreciseRelevancyScore: 1051.00573730469 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: The miniJPAS survey quasar selection III: Classification with artificial neural networks and hybridisation – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Martínez-Solaeche%2C+G%2E%22">Martínez-Solaeche, G.</searchLink><br /><searchLink fieldCode="AR" term="%22Queiroz%2C+Carolina%22">Queiroz, Carolina</searchLink><br /><searchLink fieldCode="AR" term="%22Delgado%2C+R%2E+M%2E+González%22">Delgado, R. M. González</searchLink><br /><searchLink fieldCode="AR" term="%22Rodrigues%2C+Natália+V%2E+N%2E%22">Rodrigues, Natália V. N.</searchLink><br /><searchLink fieldCode="AR" term="%22García-Benito%2C+R%2E%22">García-Benito, R.</searchLink><br /><searchLink fieldCode="AR" term="%22Pérez-Ràfols%2C+Ignasi%22">Pérez-Ràfols, Ignasi</searchLink><br /><searchLink fieldCode="AR" term="%22Abramo%2C+L%2E+Raul%22">Abramo, L. Raul</searchLink><br /><searchLink fieldCode="AR" term="%22Díaz-García%2C+Luis%22">Díaz-García, Luis</searchLink><br /><searchLink fieldCode="AR" term="%22Pieri%2C+Matthew+M%2E%22">Pieri, Matthew M.</searchLink><br /><searchLink fieldCode="AR" term="%22Chaves-Montero%2C+Jonás%22">Chaves-Montero, Jonás</searchLink><br /><searchLink fieldCode="AR" term="%22Hernán-Caballero%2C+A%2E%22">Hernán-Caballero, A.</searchLink><br /><searchLink fieldCode="AR" term="%22Rodríguez-Martín%2C+J%2E+E%2E%22">Rodríguez-Martín, J. E.</searchLink><br /><searchLink fieldCode="AR" term="%22Bonoli%2C+Silvia%22">Bonoli, Silvia</searchLink><br /><searchLink fieldCode="AR" term="%22Morrison%2C+Sean+S%2E%22">Morrison, Sean S.</searchLink><br /><searchLink fieldCode="AR" term="%22Márquez%2C+Isabel%22">Márquez, Isabel</searchLink><br /><searchLink fieldCode="AR" term="%22Vílchez%2C+J%2E+M%2E%22">Vílchez, J. M.</searchLink><br /><searchLink fieldCode="AR" term="%22López-Sanjuan%2C+C%2E%22">López-Sanjuan, C.</searchLink><br /><searchLink fieldCode="AR" term="%22Cenarro%2C+A%2E+J%2E%22">Cenarro, A. J.</searchLink><br /><searchLink fieldCode="AR" term="%22Dupke%2C+R%2E+A%2E%22">Dupke, R. A.</searchLink><br /><searchLink fieldCode="AR" term="%22Martín-Franch%2C+A%2E%22">Martín-Franch, A.</searchLink><br /><searchLink fieldCode="AR" term="%22Varel%2C+J%2E%22">Varel, J.</searchLink><br /><searchLink fieldCode="AR" term="%22Ramió%2C+H%2E+Vázquez%22">Ramió, H. Vázquez</searchLink><br /><searchLink fieldCode="AR" term="%22Cristóbal-Hornillos%2C+D%2E%22">Cristóbal-Hornillos, D.</searchLink><br /><searchLink fieldCode="AR" term="%22Moles%2C+M%2E%22">Moles, M.</searchLink><br /><searchLink fieldCode="AR" term="%22Alcaniz%2C+J%2E%22">Alcaniz, J.</searchLink><br /><searchLink fieldCode="AR" term="%22Benitez%2C+N%2E%22">Benitez, N.</searchLink><br /><searchLink fieldCode="AR" term="%22Fernández-Ontiveros%2C+J%2E+A%2E%22">Fernández-Ontiveros, J. A.</searchLink><br /><searchLink fieldCode="AR" term="%22Ederoclite%2C+A%2E%22">Ederoclite, A.</searchLink><br /><searchLink fieldCode="AR" term="%22Marra%2C+V%2E%22">Marra, V.</searchLink><br /><searchLink fieldCode="AR" term="%22de+Oliveira%2C+C%2E+Mendes%22">de Oliveira, C. Mendes</searchLink><br /><searchLink fieldCode="AR" term="%22Taylor%2C+K%2E%22">Taylor, K.</searchLink> – Name: TitleSource Label: Source Group: Src Data: A&A 673, A103 (2023) – Name: DatePubCY Label: Publication Year Group: Date Data: 2023 – Name: Subset Label: Collection Group: HoldingsInfo Data: Astrophysics – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Astrophysics+-+Astrophysics+of+Galaxies%22">Astrophysics - Astrophysics of Galaxies</searchLink><br /><searchLink fieldCode="DE" term="%22Astrophysics+-+Cosmology+and+Nongalactic+Astrophysics%22">Astrophysics - Cosmology and Nongalactic Astrophysics</searchLink> – Name: Abstract Label: Description Group: Ab Data: This paper is part of large effort within the J-PAS collaboration that aims to classify point-like sources in miniJPAS, which were observed in 60 optical bands over $\sim$ 1 deg$^2$ in the AEGIS field. We developed two algorithms based on artificial neural networks (ANN) to classify objects into four categories: stars, galaxies, quasars at low redshift ($z < 2.1)$, and quasars at high redshift ($z \geq 2.1$). As inputs, we used miniJPAS fluxes for one of the classifiers (ANN$_1$) and colours for the other (ANN$_2$). The ANNs were trained and tested using mock data in the first place. We studied the effect of augmenting the training set by creating hybrid objects, which combines fluxes from stars, galaxies, and quasars. Nevertheless, the augmentation processing did not improve the score of the ANN. We also evaluated the performance of the classifiers in a small subset of the SDSS DR12Q superset observed by miniJPAS. In the mock test set, the f1-score for quasars at high redshift with the ANN$_1$ (ANN$_2$) are $0.99$ ($0.99$), $0.93$ ($0.92$), and $0.63$ ($0.57$) for $17 < r \leq 20$, $20 < r \leq 22.5$, and $22.5 < r \leq 23.6$, respectively, where $r$ is the J-PAS rSDSS band. In the case of low-redshift quasars, galaxies, and stars, we reached $0.97$ ($0.97$), $0.82$ ($0.79$), and $0.61$ ($0.58$); $0.94$ ($0.94$), $0.90$ ($0.89$), and $0.81$ ($0.80$); and $1.0$ ($1.0$), $0.96$ ($0.94$), and $0.70$ ($0.52$) in the same r bins. In the SDSS DR12Q superset miniJPAS sample, the weighted f1-score reaches 0.87 (0.88) for objects that are mostly within $20 < r \leq 22.5$. Finally, we estimate the number of point-like sources that are quasars, galaxies, and stars in miniJPAS. – Name: TypeDocument Label: Document Type Group: TypDoc Data: Working Paper – Name: DOI Label: DOI Group: ID Data: 10.1051/0004-6361/202245750 – Name: URL Label: Access URL Group: URL Data: <link linkTarget="URL" linkTerm="http://arxiv.org/abs/2303.12684" linkWindow="_blank">http://arxiv.org/abs/2303.12684</link> – Name: AN Label: Accession Number Group: ID Data: edsarx.2303.12684 |
| PLink | https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.2303.12684 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1051/0004-6361/202245750 Subjects: – SubjectFull: Astrophysics - Astrophysics of Galaxies Type: general – SubjectFull: Astrophysics - Cosmology and Nongalactic Astrophysics Type: general Titles: – TitleFull: The miniJPAS survey quasar selection III: Classification with artificial neural networks and hybridisation Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Martínez-Solaeche, G. – PersonEntity: Name: NameFull: Queiroz, Carolina – PersonEntity: Name: NameFull: Delgado, R. M. González – PersonEntity: Name: NameFull: Rodrigues, Natália V. N. – PersonEntity: Name: NameFull: García-Benito, R. – PersonEntity: Name: NameFull: Pérez-Ràfols, Ignasi – PersonEntity: Name: NameFull: Abramo, L. Raul – PersonEntity: Name: NameFull: Díaz-García, Luis – PersonEntity: Name: NameFull: Pieri, Matthew M. – PersonEntity: Name: NameFull: Chaves-Montero, Jonás – PersonEntity: Name: NameFull: Hernán-Caballero, A. – PersonEntity: Name: NameFull: Rodríguez-Martín, J. E. – PersonEntity: Name: NameFull: Bonoli, Silvia – PersonEntity: Name: NameFull: Morrison, Sean S. – PersonEntity: Name: NameFull: Márquez, Isabel – PersonEntity: Name: NameFull: Vílchez, J. M. – PersonEntity: Name: NameFull: López-Sanjuan, C. – PersonEntity: Name: NameFull: Cenarro, A. J. – PersonEntity: Name: NameFull: Dupke, R. A. – PersonEntity: Name: NameFull: Martín-Franch, A. – PersonEntity: Name: NameFull: Varel, J. – PersonEntity: Name: NameFull: Ramió, H. Vázquez – PersonEntity: Name: NameFull: Cristóbal-Hornillos, D. – PersonEntity: Name: NameFull: Moles, M. – PersonEntity: Name: NameFull: Alcaniz, J. – PersonEntity: Name: NameFull: Benitez, N. – PersonEntity: Name: NameFull: Fernández-Ontiveros, J. A. – PersonEntity: Name: NameFull: Ederoclite, A. – PersonEntity: Name: NameFull: Marra, V. – PersonEntity: Name: NameFull: de Oliveira, C. Mendes – PersonEntity: Name: NameFull: Taylor, K. IsPartOfRelationships: – BibEntity: Dates: – D: 22 M: 03 Type: published Y: 2023 |
| ResultId | 1 |