Using a Neural Network Classifier to Select Galaxies with the Most Accurate Photometric Redshifts

Broussard, Adam; Gawiser, Eric

doi:10.3847/1538-4357/ac2147

Using a Neural Network Classifier to Select Galaxies with the Most Accurate Photometric Redshifts

Journal Article · Fri Nov 26 00:00:00 EST 2021 · The Astrophysical Journal

DOI:https://doi.org/10.3847/1538-4357/ac2147· OSTI ID:1981229

^[1]; ^[2]

Rutgers Univ., Piscataway, NJ (United States); Rutgers Univ., Piscataway, NJ (United States)
Rutgers Univ., Piscataway, NJ (United States)

The Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST) will produce several billion photometric redshifts (photo-z's), enabling cosmological analyses to select a subset of galaxies with the most accurate photo-z. For this work, we perform initial redshift fits on Subaru Strategic Program galaxies with deep grizy photometry using Trees for Photo-Z (TPZ) before applying a custom neural network classifier (NNC) tuned to select galaxies with (z_phot – z_spec)/(1 + z_spec) < 0.10. We consider four cases of training and test sets ranging from an idealized case to using data augmentation to increase the representation of dim galaxies in the training set. Selections made using the NNC yield significant further improvements in outlier fraction and photo-z scatter (σ_z) over those made with typical photo-z uncertainties. As an example, when selecting the best third of the galaxy sample, the NNC achieves a 35% improvement in outlier rate and a 23% improvement in σ_z compared to using uncertainties from TPZ. For cosmology and galaxy evolution studies, this method can be tuned to retain a particular sample size or to achieve a desired photo-z accuracy; our results show that it is possible to retain more than a third of an LSST-like galaxy sample while reducing σ_z by a factor of 2 compared to the full sample, with one-fifth as many photo-z outliers. For surveys like LSST that are not limited by shot noise, this method enables a larger number of tomographic redshift bins and hence a significant increase in the total signal to noise of galaxy angular power spectra.

View Accepted Manuscript (DOE)

Research Organization:: Rutgers Univ., Piscataway, NJ (United States)

Sponsoring Organization:: USDOE Office of Science (SC), High Energy Physics (HEP)

Grant/Contract Number:: SC0010008

OSTI ID:: 1981229

Journal Information:: The Astrophysical Journal, Journal Name: The Astrophysical Journal Journal Issue: 2 Vol. 922; ISSN 0004-637X

Publisher:: IOP PublishingCopyright Statement

Country of Publication:: United States

Language:: English

References (54)

Ian Goodfellow, Yoshua Bengio, and Aaron Courville: Deep learning Heaton, Jeff Genetic Programming and Evolvable Machines, Vol. 19, Issue 1-2 https://doi.org/10.1007/s10710-017-9314-z	journal	October 2017
A theory of learning from different domains Ben-David, Shai; Blitzer, John; Crammer, Koby Machine Learning, Vol. 79, Issue 1-2 https://doi.org/10.1007/s10994-009-5152-4	journal	October 2009
Multilayer feedforward networks are universal approximators Hornik, Kurt; Stinchcombe, Maxwell; White, Halbert Neural Networks, Vol. 2, Issue 5 https://doi.org/10.1016/0893-6080(89)90020-8	journal	January 1989
Halo models of large scale structure Cooray, A.; Sheth, R. Physics Reports, Vol. 372, Issue 1 https://doi.org/10.1016/S0370-1573(02)00276-4	journal	December 2002
Large-scale galaxy bias Desjacques, Vincent; Jeong, Donghui; Schmidt, Fabian Physics Reports, Vol. 733 https://doi.org/10.1016/j.physrep.2017.12.002	journal	February 2018
Deep learning LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey Nature, Vol. 521, Issue 7553 https://doi.org/10.1038/nature14539	journal	May 2015
Measuring and modelling the redshift evolution of clustering: the Hubble Deep Field North Arnouts, S.; Cristiani, S.; Moscardini, L. Monthly Notices of the Royal Astronomical Society, Vol. 310, Issue 2 https://doi.org/10.1046/j.1365-8711.1999.02978.x	journal	December 1999
Measuring the redshift evolution of clustering: the Hubble Deep Field South Arnouts, S.; Moscardini, L.; Vanzella, E. Monthly Notices of the Royal Astronomical Society, Vol. 329, Issue 2 https://doi.org/10.1046/j.1365-8711.2002.04988.x	journal	January 2002
PHAT: PHoto- z Accuracy Testing Hildebrandt, H.; Arnouts, S.; Capak, P. Astronomy & Astrophysics, Vol. 523 https://doi.org/10.1051/0004-6361/201014885	journal	November 2010
The VIMOS VLT Deep Survey final data release: a spectroscopic sample of 35 016 galaxies and AGN out to z ~ 6.7 selected with 17.5 ≤ i _AB ≤ 24.75 Le Fèvre, O.; Cassata, P.; Cucciati, O. Astronomy & Astrophysics, Vol. 559 https://doi.org/10.1051/0004-6361/201322179	journal	October 2013
The VIMOS Public Extragalactic Survey (VIPERS): First Data Release of 57 204 spectroscopic measurements Garilli, B.; Guzzo, L.; Scodeggio, M. Astronomy & Astrophysics, Vol. 562 https://doi.org/10.1051/0004-6361/201322790	journal	January 2014
The Sloan Digital Sky Survey Quasar Catalog: Fourteenth data release Pâris, Isabelle; Petitjean, Patrick; Aubourg, Éric Astronomy & Astrophysics, Vol. 613 https://doi.org/10.1051/0004-6361/201732445	journal	May 2018
Accurate photometric redshifts for the CFHT legacy survey calibrated using the VIMOS VLT deep survey Ilbert, O.; Arnouts, S.; McCracken, H. J. Astronomy & Astrophysics, Vol. 457, Issue 3 https://doi.org/10.1051/0004-6361:20065138	journal	September 2006
Formation of Galaxies and Clusters of Galaxies by Self-Similar Gravitational Condensation Press, William H.; Schechter, Paul The Astrophysical Journal, Vol. 187 https://doi.org/10.1086/152650	journal	February 1974
The evolution of large-scale structure in a universe dominated by cold dark matter Davis, M.; Efstathiou, G.; Frenk, C. S. The Astrophysical Journal, Vol. 292 https://doi.org/10.1086/163168	journal	May 1985
A measurement of the mass density of the universe Loh, E. D.; Spillar, E. J. The Astrophysical Journal, Vol. 307 https://doi.org/10.1086/184717	journal	August 1986
The Luminosity and Color Dependence of the Galaxy Correlation Function Zehavi, Idit; Zheng, Zheng; Weinberg, David H. The Astrophysical Journal, Vol. 630, Issue 1 https://doi.org/10.1086/431891	journal	September 2005
EAZY: A Fast, Public Photometric Redshift Code Brammer, Gabriel B.; van Dokkum, Pieter G.; Coppi, Paolo The Astrophysical Journal, Vol. 686, Issue 2 https://doi.org/10.1086/591786	journal	October 2008
The Prism Multi-Object Survey (Primus). i. Survey Overview and Characteristics Coil, Alison L.; Blanton, Michael R.; Burles, Scott M. The Astrophysical Journal, Vol. 741, Issue 1 https://doi.org/10.1088/0004-637X/741/1/8	journal	October 2011
The Prism Multi-Object Survey (Primus). ii. data Reduction and Redshift Fitting Cool, Richard J.; Moustakas, John; Blanton, Michael R. The Astrophysical Journal, Vol. 767, Issue 2 https://doi.org/10.1088/0004-637X/767/2/118	journal	April 2013
THE zCOSMOS 10k-BRIGHT SPECTROSCOPIC SAMPLE Lilly, Simon J.; Le Brun, Vincent; Maier, Christian The Astrophysical Journal Supplement Series, Vol. 184, Issue 2 https://doi.org/10.1088/0067-0049/184/2/218	journal	September 2009
The Deep3 Galaxy Redshift Survey: Keck/Deimos Spectroscopy in the Goods-N Field Cooper, Michael C.; Aird, James A.; Coil, Alison L. The Astrophysical Journal Supplement Series, Vol. 193, Issue 1 https://doi.org/10.1088/0067-0049/193/1/14	journal	March 2011
The Deep2 Galaxy Redshift Survey: Design, Observations, data Reduction, and Redshifts Newman, Jeffrey A.; Cooper, Michael C.; Davis, Marc The Astrophysical Journal Supplement Series, Vol. 208, Issue 1 https://doi.org/10.1088/0067-0049/208/1/5	journal	August 2013
3d-Hst Wfc3-Selected Photometric Catalogs in the five Candels/3d-Hst Fields: Photometry, Photometric Redshifts, and Stellar Masses Skelton, Rosalind E.; Whitaker, Katherine E.; Momcheva, Ivelina G. The Astrophysical Journal Supplement Series, Vol. 214, Issue 2 https://doi.org/10.1088/0067-0049/214/2/24	journal	October 2014
The Eleventh and Twelfth data Releases of the Sloan Digital sky Survey: Final data from Sdss-Iii Alam, Shadab; Albareti, Franco D.; Prieto, Carlos Allende The Astrophysical Journal Supplement Series, Vol. 219, Issue 1 https://doi.org/10.1088/0067-0049/219/1/12	journal	July 2015
THE FMOS-COSMOS SURVEY OF STAR-FORMING GALAXIES AT z ∼ 1.6. III. SURVEY DESIGN, PERFORMANCE, AND SAMPLE CHARACTERISTICS Silverman, J. D.; Kashino, D.; Sanders, D. The Astrophysical Journal Supplement Series, Vol. 220, Issue 1 https://doi.org/10.1088/0067-0049/220/1/12	journal	September 2015
Stable architectures for deep neural networks Haber, Eldad; Ruthotto, Lars Inverse Problems, Vol. 34, Issue 1 https://doi.org/10.1088/1361-6420/aa9a90	journal	December 2017
Stellar polytropes and Navarro–Frenk–White halo models: comparison with observations Zavala, Jesús; Núñez, Darío; Sussman, Roberto A. Journal of Cosmology and Astroparticle Physics, Vol. 2006, Issue 06 https://doi.org/10.1088/1475-7516/2006/06/008	journal	June 2006
Tomographic galaxy clustering with the Subaru Hyper Suprime-Cam first year public data release Nicola, Andrina; Alonso, David; Sánchez, Javier Journal of Cosmology and Astroparticle Physics, Vol. 2020, Issue 03 https://doi.org/10.1088/1475-7516/2020/03/044	journal	March 2020
The sizes, masses and specific star formation rates of massive galaxies at 1.3 < z < 1.5: strong evidence in favour of evolution via minor mergers McLure, R. J.; Pearce, H. J.; Dunlop, J. S. Monthly Notices of the Royal Astronomical Society, Vol. 428, Issue 2 https://doi.org/10.1093/mnras/sts092	journal	November 2012
TPZ: photometric redshift PDFs and ancillary information by using prediction trees and random forests Carrasco Kind, Matias; Brunner, Robert J. Monthly Notices of the Royal Astronomical Society, Vol. 432, Issue 2 https://doi.org/10.1093/mnras/stt574	journal	May 2013
High-velocity outflows from young star-forming galaxies in the UKIDSS Ultra-Deep Survey Bradshaw, E. J.; Almaini, O.; Hartley, W. G. Monthly Notices of the Royal Astronomical Society, Vol. 433, Issue 1 https://doi.org/10.1093/mnras/stt715	journal	May 2013
Galaxy And Mass Assembly (GAMA): end of survey report and data release 2 Liske, J.; Baldry, I. K.; Driver, S. P. Monthly Notices of the Royal Astronomical Society, Vol. 452, Issue 2 https://doi.org/10.1093/mnras/stv1436	journal	July 2015
Data augmentation for machine learning redshifts applied to Sloan Digital Sky Survey galaxies Hoyle, Ben; Rau, Markus Michael; Bonnett, Christopher Monthly Notices of the Royal Astronomical Society, Vol. 450, Issue 1 https://doi.org/10.1093/mnras/stv599	journal	April 2015
The Hyper Suprime-Cam SSP Survey: Overview and survey design Aihara, Hiroaki; Arimoto, Nobuo; Armstrong, Robert Publications of the Astronomical Society of Japan, Vol. 70, Issue SP1 https://doi.org/10.1093/pasj/psx066	journal	September 2017
Photometric redshifts for Hyper Suprime-Cam Subaru Strategic Program Data Release 1 Tanaka, Masayuki; Coupon, Jean; Hsieh, Bau-Ching Publications of the Astronomical Society of Japan, Vol. 70, Issue SP1 https://doi.org/10.1093/pasj/psx077	journal	October 2017
Second data release of the Hyper Suprime-Cam Subaru Strategic Program Aihara, Hiroaki; AlSayyad, Yusra; Ando, Makoto Publications of the Astronomical Society of Japan https://doi.org/10.1093/pasj/psz103	journal	October 2019
Synthetic Biological Signals Machine-Generated by GPT-2 Improve the Classification of EEG and EMG Through Data Augmentation Bird, Jordan J.; Pritchard, Michael; Fratini, Antonio IEEE Robotics and Automation Letters, Vol. 6, Issue 2 https://doi.org/10.1109/LRA.2021.3056355	journal	April 2021
The impact of non-Gaussian errors on weak lensing surveys Takada, Masahiro; Jain, Bhuvnesh Monthly Notices of the Royal Astronomical Society, Vol. 395, Issue 4 https://doi.org/10.1111/j.1365-2966.2009.14504.x	journal	June 2009
The WiggleZ Dark Energy Survey: survey design and first data release Drinkwater, Michael J.; Jurek, Russell J.; Blake, Chris Monthly Notices of the Royal Astronomical Society, Vol. 401, Issue 3 https://doi.org/10.1111/j.1365-2966.2009.15754.x	journal	January 2010
The Arizona CDFS Environment Survey (ACES): A Magellan/IMACS Spectroscopic Survey of the Chandra Deep Field-South: Arizona CDFS Environment Survey (ACES) Cooper, Michael C.; Yan, Renbin; Dickinson, Mark Monthly Notices of the Royal Astronomical Society, Vol. 425, Issue 3 https://doi.org/10.1111/j.1365-2966.2012.21524.x	journal	August 2012
FMOS near-IR spectroscopy ofHerschel-selected galaxies: star formation rates, metallicity and dust attenuation atz∼ 1 Roseboom, I. G.; Bunker, A.; Sumiyoshi, M. Monthly Notices of the Royal Astronomical Society, Vol. 426, Issue 3 https://doi.org/10.1111/j.1365-2966.2012.21777.x	journal	October 2012
4MOST: 4-metre Multi-Object Spectroscopic Telescope de Jong, Roelof S.; Barden, Sam; Bellido-Tirado, Olga SPIE Astronomical Telescopes + Instrumentation, SPIE Proceedings https://doi.org/10.1117/12.2055826	conference	July 2014
Deep vs. shallow networks: An approximation theory perspective Mhaskar, H. N.; Poggio, T. Analysis and Applications, Vol. 14, Issue 06 https://doi.org/10.1142/S0219530516400042	journal	October 2016
A Fast Learning Algorithm for Deep Belief Nets Hinton, Geoffrey E.; Osindero, Simon; Teh, Yee-Whye Neural Computation, Vol. 18, Issue 7 https://doi.org/10.1162/neco.2006.18.7.1527	journal	July 2006
A survey on Image Data Augmentation for Deep Learning Shorten, Connor; Khoshgoftaar, Taghi M. Journal of Big Data, Vol. 6, Issue 1 https://doi.org/10.1186/s40537-019-0197-0	journal	July 2019
Augmentor: An Image Augmentation Library for Machine Learning D. Bloice, Marcus; Stocker, Christof; Holzinger, Andreas The Journal of Open Source Software, Vol. 2, Issue 19 https://doi.org/10.21105/joss.00432	journal	November 2017
Warren S. McCulloch and Walter Pitts. A logical calculus of the ideas immanent in nervous activity. Bulletin of mathematical biophysics, vol. 5 (1943), pp. 115–133. Fitch, Frederic B. Journal of Symbolic Logic, Vol. 9, Issue 2 https://doi.org/10.2307/2268029	journal	June 1944
THE COSMOS2015 CATALOG: EXPLORING THE 1 < z < 6 UNIVERSE WITH HALF A MILLION GALAXIES Laigle, C.; McCracken, H. J.; Ilbert, O. The Astrophysical Journal Supplement Series, Vol. 224, Issue 2 https://doi.org/10.3847/0067-0049/224/2/24	journal	June 2016
THE 3D-HST SURVEY: HUBBLE SPACE TELESCOPE WFC3/G141 GRISM SPECTRA, REDSHIFTS, AND EMISSION LINE MEASUREMENTS FOR ∼100,000 GALAXIES Momcheva, Ivelina G.; Brammer, Gabriel B.; van Dokkum, Pieter G. The Astrophysical Journal Supplement Series, Vol. 225, Issue 2 https://doi.org/10.3847/0067-0049/225/2/27	journal	August 2016
LSST: From Science Drivers to Reference Design and Anticipated Data Products Ivezić, Željko; Kahn, Steven M.; Tyson, J. Anthony The Astrophysical Journal, Vol. 873, Issue 2 https://doi.org/10.3847/1538-4357/ab042c	journal	March 2019
Angular Correlation Function Estimators Accounting for Contamination from Probabilistic Distance Measurements Awan, Humna; Gawiser, Eric The Astrophysical Journal, Vol. 890, Issue 1 https://doi.org/10.3847/1538-4357/ab63c8	journal	February 2020
The FMOS-COSMOS Survey of Star-forming Galaxies at z ∼ 1.6. VI. Redshift and Emission-line Catalog and Basic Properties of Star-forming Galaxies Kashino, Daichi; Silverman, John D.; Sanders, David The Astrophysical Journal Supplement Series, Vol. 241, Issue 1 https://doi.org/10.3847/1538-4365/ab06c4	journal	March 2019
Core Cosmology Library: Precision Cosmological Predictions for LSST Chisari, Nora Elisa; Alonso, David; Krause, Elisabeth The Astrophysical Journal Supplement Series, Vol. 242, Issue 1 https://doi.org/10.3847/1538-4365/ab1658	journal	May 2019

Similar Records

Photometric classification and redshift estimation of LSST Supernovae

Journal Article · Wed Apr 18 20:00:00 EDT 2018 · Monthly Notices of the Royal Astronomical Society · OSTI ID:1439475

Improving Photometric Redshift Estimates with Training Sample Augmentation

Journal Article · Sun May 12 20:00:00 EDT 2024 · The Astrophysical Journal. Letters · OSTI ID:2349559

PHOTOMETRIC REDSHIFTS IN THE HAWAII-HUBBLE DEEP FIELD-NORTH (H-HDF-N)

Journal Article · Wed Dec 31 23:00:00 EST 2014 · Astrophysical Journal, Supplement Series · OSTI ID:22340125

Related Subjects

79 ASTRONOMY AND ASTROPHYSICS
cosmology
galaxy distances
large-scale structure of the universe
observational cosmology
surveys

Using a Neural Network Classifier to Select Galaxies with the Most Accurate Photometric Redshifts

Citation Formats

References (54)

Similar Records

Related Subjects