Deep learning based photometric redshifts for the Kilo-Degree Survey Bright Galaxy Sample

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: William, Anjitha John, Jalan, Priyanka, Bilicki, Maciej, Hellwing, Wojciech A.
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918182740033536
author William, Anjitha John
Jalan, Priyanka
Bilicki, Maciej
Hellwing, Wojciech A.
author_facet William, Anjitha John
Jalan, Priyanka
Bilicki, Maciej
Hellwing, Wojciech A.
contents In cosmological analyses, precise redshift determination remains pivotal for understanding cosmic evolution. However, with only a fraction of galaxies having spectroscopic redshifts (spec-$z$s), the challenge lies in estimating redshifts for a larger number. To address this, photometry-based redshift (photo-$z$) estimation, employing machine learning algorithms, is a viable solution. Identifying the limitations of previous methods, this study focuses on implementing deep learning (DL) techniques within the Kilo-Degree Survey (KiDS) Bright Galaxy Sample for more accurate photo-$z$ estimations. Comparing our new DL-based model against prior `shallow' neural networks, we showcase improvements in redshift accuracy. Our model gives mean photo-$z$ bias $\langle Δz\rangle= 10^{-3}$ and scatter $\mathrm{SMAD}(Δz)=0.016$, where $Δz = (z_\mathrm{phot}-z_\mathrm{spec})/(1+z_\mathrm{spec})$. This research highlights the promising role of DL in revolutionizing photo-$z$ estimation.
format Preprint
id arxiv_https___arxiv_org_abs_2312_08043
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Deep learning based photometric redshifts for the Kilo-Degree Survey Bright Galaxy Sample
William, Anjitha John
Jalan, Priyanka
Bilicki, Maciej
Hellwing, Wojciech A.
Cosmology and Nongalactic Astrophysics
Astrophysics of Galaxies
Instrumentation and Methods for Astrophysics
In cosmological analyses, precise redshift determination remains pivotal for understanding cosmic evolution. However, with only a fraction of galaxies having spectroscopic redshifts (spec-$z$s), the challenge lies in estimating redshifts for a larger number. To address this, photometry-based redshift (photo-$z$) estimation, employing machine learning algorithms, is a viable solution. Identifying the limitations of previous methods, this study focuses on implementing deep learning (DL) techniques within the Kilo-Degree Survey (KiDS) Bright Galaxy Sample for more accurate photo-$z$ estimations. Comparing our new DL-based model against prior `shallow' neural networks, we showcase improvements in redshift accuracy. Our model gives mean photo-$z$ bias $\langle Δz\rangle= 10^{-3}$ and scatter $\mathrm{SMAD}(Δz)=0.016$, where $Δz = (z_\mathrm{phot}-z_\mathrm{spec})/(1+z_\mathrm{spec})$. This research highlights the promising role of DL in revolutionizing photo-$z$ estimation.
title Deep learning based photometric redshifts for the Kilo-Degree Survey Bright Galaxy Sample
topic Cosmology and Nongalactic Astrophysics
Astrophysics of Galaxies
Instrumentation and Methods for Astrophysics
url https://arxiv.org/abs/2312.08043