Report
View in EDS

Photometric Redshifts Probability Density Estimation from Recurrent Neural Networks in the DECam Local Volume Exploration Survey Data Release 2

Bibliographic Details
Title: Photometric Redshifts Probability Density Estimation from Recurrent Neural Networks in the DECam Local Volume Exploration Survey Data Release 2
Authors: Teixeira, G., Bom, C. R., Santana-Silva, L., Fraga, B. M. O., Darc, P., Teixeira, R., Wu, J. F., Ferguson, P. S., Martínez-Vázquez, C. E., Riley, A. H., Drlica-Wagner, A., Choi, Y., Mutlu-Pakdil, B., Pace, A. B., Sakowska, J. D., Stringfellow, G. S.
Publication Year: 2024
Collection: Astrophysics
Subject Terms: Astrophysics - Instrumentation and Methods for Astrophysics
More Details: Photometric wide-field surveys are imaging the sky in unprecedented detail. These surveys face a significant challenge in efficiently estimating galactic photometric redshifts while accurately quantifying associated uncertainties. In this work, we address this challenge by exploring the estimation of Probability Density Functions (PDFs) for the photometric redshifts of galaxies across a vast area of 17,000 square degrees, encompassing objects with a median 5$\sigma$ point-source depth of $g$ = 24.3, $r$ = 23.9, $i$ = 23.5, and $z$ = 22.8 mag. Our approach uses deep learning, specifically integrating a Recurrent Neural Network architecture with a Mixture Density Network, to leverage magnitudes and colors as input features for constructing photometric redshift PDFs across the whole DECam Local Volume Exploration (DELVE) survey sky footprint. Subsequently, we rigorously evaluate the reliability and robustness of our estimation methodology, gauging its performance against other well-established machine learning methods to ensure the quality of our redshift estimations. Our best results constrain photometric redshifts with the bias of $-0.0013$, a scatter of $0.0293$, and an outlier fraction of $5.1\%$. These point estimates are accompanied by well-calibrated PDFs evaluated using diagnostic tools such as Probability Integral Transform and Odds distribution. We also address the problem of the accessibility of PDFs in terms of disk space storage and the time demand required to generate their corresponding parameters. We present a novel Autoencoder model that reduces the size of PDF parameter arrays to one-sixth of their original length, significantly decreasing the time required for PDF generation to one-eighth of the time needed when generating PDFs directly from the magnitudes.
Comment: 22 pages, 14 figures
Document Type: Working Paper
Access URL: http://arxiv.org/abs/2408.15243
Accession Number: edsarx.2408.15243
Database: arXiv
FullText Text:
  Availability: 0
CustomLinks:
  – Url: http://arxiv.org/abs/2408.15243
    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=20240827&spage=&pages=&title=Photometric Redshifts Probability Density Estimation from Recurrent Neural Networks in the DECam Local Volume Exploration Survey Data Release 2&atitle=Photometric%20Redshifts%20Probability%20Density%20Estimation%20from%20Recurrent%20Neural%20Networks%20in%20the%20DECam%20Local%20Volume%20Exploration%20Survey%20Data%20Release%202&aulast=Teixeira%2C%20G.&id=DOI:
    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.2408.15243
RelevancyScore: 1112
AccessLevel: 3
PubType: Report
PubTypeId: report
PreciseRelevancyScore: 1112.24548339844
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Photometric Redshifts Probability Density Estimation from Recurrent Neural Networks in the DECam Local Volume Exploration Survey Data Release 2
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Teixeira%2C+G%2E%22">Teixeira, G.</searchLink><br /><searchLink fieldCode="AR" term="%22Bom%2C+C%2E+R%2E%22">Bom, C. R.</searchLink><br /><searchLink fieldCode="AR" term="%22Santana-Silva%2C+L%2E%22">Santana-Silva, L.</searchLink><br /><searchLink fieldCode="AR" term="%22Fraga%2C+B%2E+M%2E+O%2E%22">Fraga, B. M. O.</searchLink><br /><searchLink fieldCode="AR" term="%22Darc%2C+P%2E%22">Darc, P.</searchLink><br /><searchLink fieldCode="AR" term="%22Teixeira%2C+R%2E%22">Teixeira, R.</searchLink><br /><searchLink fieldCode="AR" term="%22Wu%2C+J%2E+F%2E%22">Wu, J. F.</searchLink><br /><searchLink fieldCode="AR" term="%22Ferguson%2C+P%2E+S%2E%22">Ferguson, P. S.</searchLink><br /><searchLink fieldCode="AR" term="%22Martínez-Vázquez%2C+C%2E+E%2E%22">Martínez-Vázquez, C. E.</searchLink><br /><searchLink fieldCode="AR" term="%22Riley%2C+A%2E+H%2E%22">Riley, A. H.</searchLink><br /><searchLink fieldCode="AR" term="%22Drlica-Wagner%2C+A%2E%22">Drlica-Wagner, A.</searchLink><br /><searchLink fieldCode="AR" term="%22Choi%2C+Y%2E%22">Choi, Y.</searchLink><br /><searchLink fieldCode="AR" term="%22Mutlu-Pakdil%2C+B%2E%22">Mutlu-Pakdil, B.</searchLink><br /><searchLink fieldCode="AR" term="%22Pace%2C+A%2E+B%2E%22">Pace, A. B.</searchLink><br /><searchLink fieldCode="AR" term="%22Sakowska%2C+J%2E+D%2E%22">Sakowska, J. D.</searchLink><br /><searchLink fieldCode="AR" term="%22Stringfellow%2C+G%2E+S%2E%22">Stringfellow, G. S.</searchLink>
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2024
– Name: Subset
  Label: Collection
  Group: HoldingsInfo
  Data: Astrophysics
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Astrophysics+-+Instrumentation+and+Methods+for+Astrophysics%22">Astrophysics - Instrumentation and Methods for Astrophysics</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Photometric wide-field surveys are imaging the sky in unprecedented detail. These surveys face a significant challenge in efficiently estimating galactic photometric redshifts while accurately quantifying associated uncertainties. In this work, we address this challenge by exploring the estimation of Probability Density Functions (PDFs) for the photometric redshifts of galaxies across a vast area of 17,000 square degrees, encompassing objects with a median 5$\sigma$ point-source depth of $g$ = 24.3, $r$ = 23.9, $i$ = 23.5, and $z$ = 22.8 mag. Our approach uses deep learning, specifically integrating a Recurrent Neural Network architecture with a Mixture Density Network, to leverage magnitudes and colors as input features for constructing photometric redshift PDFs across the whole DECam Local Volume Exploration (DELVE) survey sky footprint. Subsequently, we rigorously evaluate the reliability and robustness of our estimation methodology, gauging its performance against other well-established machine learning methods to ensure the quality of our redshift estimations. Our best results constrain photometric redshifts with the bias of $-0.0013$, a scatter of $0.0293$, and an outlier fraction of $5.1\%$. These point estimates are accompanied by well-calibrated PDFs evaluated using diagnostic tools such as Probability Integral Transform and Odds distribution. We also address the problem of the accessibility of PDFs in terms of disk space storage and the time demand required to generate their corresponding parameters. We present a novel Autoencoder model that reduces the size of PDF parameter arrays to one-sixth of their original length, significantly decreasing the time required for PDF generation to one-eighth of the time needed when generating PDFs directly from the magnitudes.<br />Comment: 22 pages, 14 figures
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: Working Paper
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="http://arxiv.org/abs/2408.15243" linkWindow="_blank">http://arxiv.org/abs/2408.15243</link>
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsarx.2408.15243
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.2408.15243
RecordInfo BibRecord:
  BibEntity:
    Subjects:
      – SubjectFull: Astrophysics - Instrumentation and Methods for Astrophysics
        Type: general
    Titles:
      – TitleFull: Photometric Redshifts Probability Density Estimation from Recurrent Neural Networks in the DECam Local Volume Exploration Survey Data Release 2
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Teixeira, G.
      – PersonEntity:
          Name:
            NameFull: Bom, C. R.
      – PersonEntity:
          Name:
            NameFull: Santana-Silva, L.
      – PersonEntity:
          Name:
            NameFull: Fraga, B. M. O.
      – PersonEntity:
          Name:
            NameFull: Darc, P.
      – PersonEntity:
          Name:
            NameFull: Teixeira, R.
      – PersonEntity:
          Name:
            NameFull: Wu, J. F.
      – PersonEntity:
          Name:
            NameFull: Ferguson, P. S.
      – PersonEntity:
          Name:
            NameFull: Martínez-Vázquez, C. E.
      – PersonEntity:
          Name:
            NameFull: Riley, A. H.
      – PersonEntity:
          Name:
            NameFull: Drlica-Wagner, A.
      – PersonEntity:
          Name:
            NameFull: Choi, Y.
      – PersonEntity:
          Name:
            NameFull: Mutlu-Pakdil, B.
      – PersonEntity:
          Name:
            NameFull: Pace, A. B.
      – PersonEntity:
          Name:
            NameFull: Sakowska, J. D.
      – PersonEntity:
          Name:
            NameFull: Stringfellow, G. S.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 27
              M: 08
              Type: published
              Y: 2024
ResultId 1