| Full text | |
| Author(s): Show less - |
Lima, E. V. R.
;
Sodre Jr, L.
;
Bom, C. R.
;
Teixeira, G. S. M.
;
Nakazono, L.
;
Buzzo, M. L.
;
Queiroz, C.
;
Herpich, F. R.
;
Nilo Castellon, J. L.
;
Dantas, M. L. L.
;
Dors Jr, O. L.
;
Thom de Souza, R. C.
;
Akras, S.
;
Jimenez-Teja, Y.
;
Kanaan, A.
;
Ribeiro, T.
;
Schoennell, W.
Total Authors: 17
|
| Document type: | Journal article |
| Source: | ASTRONOMY AND COMPUTING; v. 38, p. 15-pg., 2022-01-01. |
| Abstract | |
The Southern Photometric Local Universe Survey (S-PLUS) is a novel project that aims to map the Southern Hemisphere using a twelve filter system, comprising five broad-band SDSS-like filters and seven narrow-band filters optimized for important stellar features in the local universe.In this paper we use the photometry and morphological information from the first S-PLUS data release (S-PLUS DR1) cross-matched to unWISE data and spectroscopic redshifts from Sloan Digital Sky Survey DR15. We explore three different machine learning methods (Gaussian Processes with GPz and two Deep Learning models made with TensorFlow) and compare them with the currently used template-fitting method in the S-PLUS DR1 to address whether machine learning methods can take advantage of the twelve filter system for photometric redshift prediction. Using tests for accuracy for both single-point estimates such as the calculation of the scatter, bias, and outlier fraction, and probability distribution functions (PDFs) such as the Probability Integral Transform (PIT), the Continuous Ranked Probability Score (CRPS) and the Odds distribution, we conclude that a deep-learning method using a combination of a Bayesian Neural Network and a Mixture Density Network offers the most accurate photometric redshifts for the current test sample. It achieves single-point photometric redshifts with scatter (& USigma;(NMAD)) of 0.023, normalized bias of -0.001, and outlier fraction of 0.64% for galaxies with r_auto magnitudes between 16 and 21. (c) 2021 Elsevier B.V. All rights reserved. (AU) | |
| FAPESP's process: | 19/06766-1 - Selection of Quasar candidates based on multi-band photometric data |
| Grantee: | Carolina Queiroz de Abreu Silva |
| Support Opportunities: | Scholarships abroad - Research Internship - Doctorate |
| FAPESP's process: | 09/54006-4 - A computer cluster for the Astronomy Department of the University of São Paulo Institute of Astronomy, Geophysics and Atmospheric Sciences and for the Cruzeiro do Sul University Astrophysics Center |
| Grantee: | Elisabete Maria de Gouveia Dal Pino |
| Support Opportunities: | Multi-user Equipment Program |
| FAPESP's process: | 14/10566-4 - Separation of stars and quasars in multispectral images |
| Grantee: | Lilianne Mariko Izuti Nakazono |
| Support Opportunities: | Scholarships in Brazil - Scientific Initiation |
| FAPESP's process: | 15/11442-0 - Combining quasars and galaxies to trace large-scale structure |
| Grantee: | Carolina Queiroz de Abreu Silva |
| Support Opportunities: | Scholarships in Brazil - Doctorate |
| FAPESP's process: | 19/10923-5 - Artificial inteligence tools for large galaxy surveys |
| Grantee: | Laerte Sodré Junior |
| Support Opportunities: | Regular Research Grants |
| FAPESP's process: | 19/01312-2 - Stellar populations of galaxies in the Hydra cluster: an IFU-like approach |
| Grantee: | Lilianne Mariko Izuti Nakazono |
| Support Opportunities: | Scholarships in Brazil - Doctorate (Direct) |
| FAPESP's process: | 18/09165-6 - Recovering galaxies' formation history from multi-band photometry |
| Grantee: | Maria Luísa Gomes Buzzo |
| Support Opportunities: | Scholarships in Brazil - Master |
| FAPESP's process: | 18/21661-9 - Cataloguing Variable Sources and IFU-like Science with Multiband Surveys. |
| Grantee: | Fábio Rafael Herpich |
| Support Opportunities: | Scholarships in Brazil - Post-Doctoral |