DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Photometric redshifts for the S-PLUS Survey: Is machine learning up to the task?

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. In conclusion, it achieves single-point photometric redshiftsmore » with scatter (σNMAD) of 0.023, normalized bias of -0.001, and outlier fraction of 0.64% for galaxies with r_auto magnitudes between 16 and 21.« less

Authors:
ORCiD logo [1]; ORCiD logo [1];  [2]; ORCiD logo [3];  [1]; ORCiD logo [1]; ORCiD logo [4]; ORCiD logo [1];  [5]; ORCiD logo [6];  [7]; ORCiD logo [8]; ORCiD logo [9]; ORCiD logo [10];  [11];  [12];  [13]
  1. Univ. of Sao Paulo (Brazil)
  2. Centro Brasileiro de Pesquisas Físicas, Rio de Janeiro (Brazil); Centro Federal de Educação Tecnológica Celso Suckow da Fonseca, Rio de Janeiro (Brazil)
  3. Centro Brasileiro de Pesquisas Físicas, Rio de Janeiro (Brazil)
  4. Univ. of Sao Paulo (Brazil); Federal Univ. of Rio Grande do Sul, Porto Alegre (Brazil)
  5. Universidad de La Serena (Chile); SIGMA Space Science and Technologies, La Serena (Chile)
  6. Polish Academy of Sciences (PAS), Warsaw (Poland)
  7. Universidade do Vale do Paraíba, São José dos Campos (Brazil)
  8. Universidade Estadual de Maringá (Brazil); Universidade Federal do Paraná, Jandaia do Sul (Brazil)
  9. National Observatory of Athens, Penteli (Greece)
  10. Consejo Superior de Investigaciones Cientificas (CSIC), Granada (Spain). Instituto de Astrofísica de Andalucía
  11. Universidade Federal de Santa Catarina (UFSC), Florianopolis, SC (Brazil)
  12. National Optical Astronomy Observatory (NOAO), Tucson, AZ (United States)
  13. GMTO Corporation, Pasadena, CA (United States)
Publication Date:
Research Org.:
US Department of Energy (USDOE), Washington, DC (United States). Office of Science, Sloan Digital Sky Survey (SDSS)
Sponsoring Org.:
USDOE Office of Science (SC); Coordenação de Aperfeiçoamento de Pessoal de Nível Superior, Brazil (CAPES); Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq); São Paulo Research Foundation FAPESP; Southern Office of Aerospace Research and development (SOARD); US Air Force Office of Scientific Research (AFOSR); Polish National Science Centre (NCN); European Union (EU); State Agency for Research of the Spanish MCIU
OSTI Identifier:
1981545
Grant/Contract Number:  
88887.470064/2019-00; 169181/2017-0; 2019/01312-2; 2014/10566-4; 2018/09165-6; 2019/23388-0; 2015/11442-0; 2019/06766-1; FA9550-18-1-0018; FA9550-22-1-0037; 2019/34/E/ST9/00133; 5077; 898633; 2009/54006-4
Resource Type:
Accepted Manuscript
Journal Name:
Astronomy and Computing
Additional Journal Information:
Journal Volume: 38; Journal Issue: C; Journal ID: ISSN 2213-1337
Publisher:
Elsevier
Country of Publication:
United States
Language:
English
Subject:
79 ASTRONOMY AND ASTROPHYSICS; astronomy; astrophysics; computer science; galaxies; distances; redshifts; data analysis; software development; photometric techniques; surveys

Citation Formats

Lima, Erik V. Rodrigues, Sodré, Laerte, Bom, C. R., Teixeira, Gabriel S.M., Nakazono, L., Buzzo, Maria Luisa, Queiroz, Carolina, Herpich, Fabio R., Castellon, J.L. Nilo, Dantas, Maria Luiza Linhares, Dors, O. L., Souza, Rodrigo Clementa Thom de, Akras, Stavros, Jiménez-Teja, Yolanda, Kanaan, A., Ribeiro, T., and Schoennell, W. Photometric redshifts for the S-PLUS Survey: Is machine learning up to the task?. United States: N. p., 2021. Web. doi:10.1016/j.ascom.2021.100510.
Lima, Erik V. Rodrigues, Sodré, Laerte, Bom, C. R., Teixeira, Gabriel S.M., Nakazono, L., Buzzo, Maria Luisa, Queiroz, Carolina, Herpich, Fabio R., Castellon, J.L. Nilo, Dantas, Maria Luiza Linhares, Dors, O. L., Souza, Rodrigo Clementa Thom de, Akras, Stavros, Jiménez-Teja, Yolanda, Kanaan, A., Ribeiro, T., & Schoennell, W. Photometric redshifts for the S-PLUS Survey: Is machine learning up to the task?. United States. https://doi.org/10.1016/j.ascom.2021.100510
Lima, Erik V. Rodrigues, Sodré, Laerte, Bom, C. R., Teixeira, Gabriel S.M., Nakazono, L., Buzzo, Maria Luisa, Queiroz, Carolina, Herpich, Fabio R., Castellon, J.L. Nilo, Dantas, Maria Luiza Linhares, Dors, O. L., Souza, Rodrigo Clementa Thom de, Akras, Stavros, Jiménez-Teja, Yolanda, Kanaan, A., Ribeiro, T., and Schoennell, W. Tue . "Photometric redshifts for the S-PLUS Survey: Is machine learning up to the task?". United States. https://doi.org/10.1016/j.ascom.2021.100510. https://www.osti.gov/servlets/purl/1981545.
@article{osti_1981545,
title = {Photometric redshifts for the S-PLUS Survey: Is machine learning up to the task?},
author = {Lima, Erik V. Rodrigues and Sodré, Laerte and Bom, C. R. and Teixeira, Gabriel S.M. and Nakazono, L. and Buzzo, Maria Luisa and Queiroz, Carolina and Herpich, Fabio R. and Castellon, J.L. Nilo and Dantas, Maria Luiza Linhares and Dors, O. L. and Souza, Rodrigo Clementa Thom de and Akras, Stavros and Jiménez-Teja, Yolanda and Kanaan, A. and Ribeiro, T. and Schoennell, W.},
abstractNote = {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. In conclusion, it achieves single-point photometric redshifts with scatter (σNMAD) of 0.023, normalized bias of -0.001, and outlier fraction of 0.64% for galaxies with r_auto magnitudes between 16 and 21.},
doi = {10.1016/j.ascom.2021.100510},
journal = {Astronomy and Computing},
number = C,
volume = 38,
place = {United States},
year = {Tue Nov 09 00:00:00 EST 2021},
month = {Tue Nov 09 00:00:00 EST 2021}
}

Works referenced in this record:

THE COSMOS2015 CATALOG: EXPLORING THE 1 < z < 6 UNIVERSE WITH HALF A MILLION GALAXIES
journal, June 2016

  • Laigle, C.; McCracken, H. J.; Ilbert, O.
  • The Astrophysical Journal Supplement Series, Vol. 224, Issue 2
  • DOI: 10.3847/0067-0049/224/2/24

Large Synoptic Survey Telescope: From science drivers to reference design
journal, January 2008

  • Ivezic, Z.; Axelrod, T.; Brandt, W. N.
  • Serbian Astronomical Journal, Issue 176
  • DOI: 10.2298/SAJ0876001I

Data augmentation for machine learning redshifts applied to Sloan Digital Sky Survey galaxies
journal, April 2015

  • Hoyle, Ben; Rau, Markus Michael; Bonnett, Christopher
  • Monthly Notices of the Royal Astronomical Society, Vol. 450, Issue 1
  • DOI: 10.1093/mnras/stv599

TPZ: photometric redshift PDFs and ancillary information by using prediction trees and random forests
journal, May 2013

  • Carrasco Kind, Matias; Brunner, Robert J.
  • Monthly Notices of the Royal Astronomical Society, Vol. 432, Issue 2
  • DOI: 10.1093/mnras/stt574

SExtractor: Software for source extraction
journal, June 1996

  • Bertin, E.; Arnouts, S.
  • Astronomy and Astrophysics Supplement Series, Vol. 117, Issue 2
  • DOI: 10.1051/aas:1996164

J-PLUS: The Javalambre Photometric Local Universe Survey
journal, February 2019


CFHTLenS: improving the quality of photometric redshifts with precision photometry★: CFHTLenS: photometric redshifts
journal, February 2012


Bayesian Photometric Redshift Estimation
journal, June 2000

  • Benitez, Narciso
  • The Astrophysical Journal, Vol. 536, Issue 2
  • DOI: 10.1086/308947

Sloan Digital Sky Survey IV: Mapping the Milky Way, Nearby Galaxies, and the Distant Universe
journal, June 2017

  • Blanton, Michael R.; Bershady, Matthew A.; Abolfathi, Bela
  • The Astronomical Journal, Vol. 154, Issue 1
  • DOI: 10.3847/1538-3881/aa7567

Accurate photometric redshifts for the CFHT legacy survey calibrated using the VIMOS VLT deep survey
journal, September 2006


Measuring Baryon Acoustic Oscillations Along the line of Sight with Photometric Redshifts: the pau Survey
journal, January 2009


ANNz2: Photometric Redshift and Probability Distribution Function Estimation using Machine Learning
journal, August 2016


Constraining cosmological parameters using Sunyaev-Zel’dovich cluster surveys
journal, October 2003


unWISE: UNBLURRED COADDS OF THE WISE IMAGING
journal, April 2014


CFHTLenS: combined probe cosmological model comparison using 2D weak gravitational lensing
journal, February 2013

  • Kilbinger, Martin; Fu, Liping; Heymans, Catherine
  • Monthly Notices of the Royal Astronomical Society, Vol. 430, Issue 3
  • DOI: 10.1093/mnras/stt041

A sparse Gaussian process framework for photometric redshift estimation
journal, November 2015

  • Almosallam, Ibrahim A.; Lindsay, Sam N.; Jarvis, Matt J.
  • Monthly Notices of the Royal Astronomical Society, Vol. 455, Issue 3
  • DOI: 10.1093/mnras/stv2425

Wide-Field InfraRed Survey Telescope (WFIRST) Mission and Synergies with LISA and LIGO-Virgo
journal, May 2015


Spectrophotometric Redshifts in the Faint Infrared Grism Survey: Finding Overdensities of Faint Galaxies
journal, March 2018

  • Pharo, John; Malhotra, Sangeeta; Rhoads, James
  • The Astrophysical Journal, Vol. 856, Issue 2
  • DOI: 10.3847/1538-4357/aaadfc

GPz: non-stationary sparse Gaussian processes for heteroscedastic uncertainty estimation in photometric redshifts
journal, July 2016

  • Almosallam, Ibrahim A.; Jarvis, Matt J.; Roberts, Stephen J.
  • Monthly Notices of the Royal Astronomical Society, Vol. 462, Issue 1
  • DOI: 10.1093/mnras/stw1618

COSMOLOGICAL CONSTRAINTS FROM THE SLOAN DIGITAL SKY SURVEY MaxBCG CLUSTER CATALOG
journal, December 2009


KiDS-450: cosmological parameter constraints from tomographic weak gravitational lensing
journal, November 2016

  • Hildebrandt, H.; Viola, M.; Heymans, C.
  • Monthly Notices of the Royal Astronomical Society, Vol. 465, Issue 2
  • DOI: 10.1093/mnras/stw2805

Estimating photometric redshifts with artificial neural networks
journal, March 2003

  • Firth, Andrew E.; Lahav, Ofer; Somerville, Rachel S.
  • Monthly Notices of the Royal Astronomical Society, Vol. 339, Issue 4
  • DOI: 10.1046/j.1365-8711.2003.06271.x

Observational probes of cosmic acceleration
journal, September 2013


Improving photometric redshift estimation using GPz: size information, post processing, and improved photometry
journal, December 2017

  • Gomes, Zahra; Jarvis, Matt J.; Almosallam, Ibrahim A.
  • Monthly Notices of the Royal Astronomical Society, Vol. 475, Issue 1
  • DOI: 10.1093/mnras/stx3187

CLASH: accurate photometric redshifts with 14 HST bands in massive galaxy cluster cores
journal, May 2017

  • Molino, A.; Benítez, N.; Ascaso, B.
  • Monthly Notices of the Royal Astronomical Society, Vol. 470, Issue 1
  • DOI: 10.1093/mnras/stx1243

The Dark Energy Survey
journal, November 2010


The CANDELS/SHARDS Multiwavelength Catalog in GOODS-N: Photometry, Photometric Redshifts, Stellar Masses, Emission-line Fluxes, and Star Formation Rates
journal, July 2019

  • Barro, Guillermo; Pérez-González, Pablo G.; Cava, Antonio
  • The Astrophysical Journal Supplement Series, Vol. 243, Issue 2
  • DOI: 10.3847/1538-4365/ab23f2

Measuring and modelling the redshift evolution of clustering: the Hubble Deep Field North
journal, December 1999


The Zurich Extragalactic Bayesian Redshift Analyzer and its first application: COSMOS
journal, October 2006


Deriving photometric redshifts using fuzzy archetypes and self-organizing maps – I. Methodology
journal, March 2017

  • Speagle, Joshua S.; Eisenstein, Daniel J.
  • Monthly Notices of the Royal Astronomical Society, Vol. 469, Issue 1
  • DOI: 10.1093/mnras/stw1485

EAZY: A Fast, Public Photometric Redshift Code
journal, October 2008

  • Brammer, Gabriel B.; van Dokkum, Pieter G.; Coppi, Paolo
  • The Astrophysical Journal, Vol. 686, Issue 2
  • DOI: 10.1086/591786