View in EDS HTML Full Text PDF Full Text

Template-fitting meets deep learning: redshift estimation using physics-guided neural networks.

Saved in:
Bibliographic Details
Title: Template-fitting meets deep learning: redshift estimation using physics-guided neural networks.
Authors: Ferrao, Jonas Chris1 (AUTHOR) jonasferrao21@gmail.com, Dias, Dickson1 (AUTHOR), Naik, Pranav1 (AUTHOR), D'cruz, Glory1 (AUTHOR), Naik, Anish1 (AUTHOR), Khandeparkar, Siya1 (AUTHOR), Dessai, Manisha Gokuldas Fal1 (AUTHOR)
Source: Journal of Astrophysics & Astronomy. 4/13/2026, Vol. 47 Issue 1, p1-13. 13p.
Subjects: Redshift, Spectral energy distribution, Long short-term memory, Deep learning, Convolutional neural networks, Artificial neural networks
Abstract: Accurate photometric redshift estimation is essential for large-scale cosmological surveys, enabling studies of galaxy evolution and the large-scale structure of the Universe, when spectroscopic measurements are impractical. Template fitting and machine learning are the two primary methods for estimating photometric redshifts, each with its own set of advantages and drawbacks. We present a hybrid framework that unifies the two through a Physics-Guided Neural Network (PGNN), integrating Spectral Energy Distribution (SED) templates with a multimodal deep learning architecture. The model combines Convolutional Neural Networks (CNNs) to extract morphological information from galaxy images, bidirectional LSTM (BiLSTM) layers to capture wavelength-ordered dependencies among photometric bands, and a cross-attention mechanism that adaptively fuses photometric and image-derived features for enhanced redshift inference. Bayesian layers further provide uncertainty estimates. Using the publicly available "GalaxiesML" dataset, which comprises ∼ 300,000 galaxies from the Hyper Suprime-Cam survey's PDR2 release, our method achieves an RMS error of 0.0942, a catastrophic outlier rate of 1.28%, and a bias of 0.0002, surpassing existing approaches on the same dataset. By embedding physical priors, spectral correlations, and cross-modal interactions within a unified architecture, this work establishes a robust, interpretable, and scalable framework for photometric redshift estimation in next-generation surveys such as LSST and Euclid. [ABSTRACT FROM AUTHOR]
Copyright of Journal of Astrophysics & Astronomy is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 192962932
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Template-fitting meets deep learning: redshift estimation using physics-guided neural networks.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Ferrao%2C+Jonas+Chris%22">Ferrao, Jonas Chris</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> jonasferrao21@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Dias%2C+Dickson%22">Dias, Dickson</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Naik%2C+Pranav%22">Naik, Pranav</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22D'cruz%2C+Glory%22">D'cruz, Glory</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Naik%2C+Anish%22">Naik, Anish</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Khandeparkar%2C+Siya%22">Khandeparkar, Siya</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Dessai%2C+Manisha+Gokuldas+Fal%22">Dessai, Manisha Gokuldas Fal</searchLink><relatesTo>1</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Journal+of+Astrophysics+%26+Astronomy%22">Journal of Astrophysics & Astronomy</searchLink>. 4/13/2026, Vol. 47 Issue 1, p1-13. 13p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Redshift%22">Redshift</searchLink><br /><searchLink fieldCode="DE" term="%22Spectral+energy+distribution%22">Spectral energy distribution</searchLink><br /><searchLink fieldCode="DE" term="%22Long+short-term+memory%22">Long short-term memory</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Convolutional+neural+networks%22">Convolutional neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Accurate photometric redshift estimation is essential for large-scale cosmological surveys, enabling studies of galaxy evolution and the large-scale structure of the Universe, when spectroscopic measurements are impractical. Template fitting and machine learning are the two primary methods for estimating photometric redshifts, each with its own set of advantages and drawbacks. We present a hybrid framework that unifies the two through a Physics-Guided Neural Network (PGNN), integrating Spectral Energy Distribution (SED) templates with a multimodal deep learning architecture. The model combines Convolutional Neural Networks (CNNs) to extract morphological information from galaxy images, bidirectional LSTM (BiLSTM) layers to capture wavelength-ordered dependencies among photometric bands, and a cross-attention mechanism that adaptively fuses photometric and image-derived features for enhanced redshift inference. Bayesian layers further provide uncertainty estimates. Using the publicly available "GalaxiesML" dataset, which comprises ∼ 300,000 galaxies from the Hyper Suprime-Cam survey's PDR2 release, our method achieves an RMS error of 0.0942, a catastrophic outlier rate of 1.28%, and a bias of 0.0002, surpassing existing approaches on the same dataset. By embedding physical priors, spectral correlations, and cross-modal interactions within a unified architecture, this work establishes a robust, interpretable, and scalable framework for photometric redshift estimation in next-generation surveys such as LSST and Euclid. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Journal of Astrophysics & Astronomy is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=192962932
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s12036-026-10144-5
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 13
        StartPage: 1
    Subjects:
      – SubjectFull: Redshift
        Type: general
      – SubjectFull: Spectral energy distribution
        Type: general
      – SubjectFull: Long short-term memory
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Convolutional neural networks
        Type: general
      – SubjectFull: Artificial neural networks
        Type: general
    Titles:
      – TitleFull: Template-fitting meets deep learning: redshift estimation using physics-guided neural networks.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Ferrao, Jonas Chris
      – PersonEntity:
          Name:
            NameFull: Dias, Dickson
      – PersonEntity:
          Name:
            NameFull: Naik, Pranav
      – PersonEntity:
          Name:
            NameFull: D'cruz, Glory
      – PersonEntity:
          Name:
            NameFull: Naik, Anish
      – PersonEntity:
          Name:
            NameFull: Khandeparkar, Siya
      – PersonEntity:
          Name:
            NameFull: Dessai, Manisha Gokuldas Fal
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 13
              M: 04
              Text: 4/13/2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 02506335
          Numbering:
            – Type: volume
              Value: 47
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: Journal of Astrophysics & Astronomy
              Type: main
ResultId 1