Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Inferring the Redshift of More than 150 GRBs with a Machine-learning Ensemble Model

Dainotti, Maria Giovanna ; Taira, Elias ; Wang, Eric ; Lehman, Elias ; Narendra, Aditya ; Pollo, Agnieszka ; Madejski, Grzegorz M. ; Petrosian, Vahe ; Bogdan, Malgorzata LU and Dey, Apratim , et al. (2024) In Astrophysical Journal, Supplement Series 271(1).
Abstract

Gamma-ray bursts (GRBs), due to their high luminosities, are detected up to a redshift of 10, and thus have the potential to be vital cosmological probes of early processes in the Universe. Fulfilling this potential requires a large sample of GRBs with known redshifts, but due to observational limitations, only 11% have known redshifts (z). There have been numerous attempts to estimate redshifts via correlation studies, most of which have led to inaccurate predictions. To overcome this, we estimated GRB redshift via an ensemble-supervised machine-learning (ML) model that uses X-ray afterglows of long-duration GRBs observed by the Neil Gehrels Swift Observatory. The estimated redshifts are strongly correlated (a Pearson coefficient of... (More)

Gamma-ray bursts (GRBs), due to their high luminosities, are detected up to a redshift of 10, and thus have the potential to be vital cosmological probes of early processes in the Universe. Fulfilling this potential requires a large sample of GRBs with known redshifts, but due to observational limitations, only 11% have known redshifts (z). There have been numerous attempts to estimate redshifts via correlation studies, most of which have led to inaccurate predictions. To overcome this, we estimated GRB redshift via an ensemble-supervised machine-learning (ML) model that uses X-ray afterglows of long-duration GRBs observed by the Neil Gehrels Swift Observatory. The estimated redshifts are strongly correlated (a Pearson coefficient of 0.93) and have an rms error, namely, the square root of the average squared error <Δz2>, of 0.46 with the observed redshifts showing the reliability of this method. The addition of GRB afterglow parameters improves the predictions considerably by 63% compared to previous results in peer-reviewed literature. Finally, we use our ML model to infer the redshifts of 154 GRBs, which increase the known redshifts of long GRBs with plateaus by 94%, a significant milestone for enhancing GRB population studies that require large samples with redshift.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and , et al. (More)
; ; ; ; ; ; ; ; ; and (Less)
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
Astrophysical Journal, Supplement Series
volume
271
issue
1
article number
22
publisher
IOP Publishing
external identifiers
  • scopus:85188204802
ISSN
0067-0049
DOI
10.3847/1538-4365/ad1aaf
language
English
LU publication?
yes
id
e4a70b58-2813-434f-a020-cf97aeceddae
date added to LUP
2024-04-10 14:51:49
date last changed
2024-04-10 14:53:20
@article{e4a70b58-2813-434f-a020-cf97aeceddae,
  abstract     = {{<p>Gamma-ray bursts (GRBs), due to their high luminosities, are detected up to a redshift of 10, and thus have the potential to be vital cosmological probes of early processes in the Universe. Fulfilling this potential requires a large sample of GRBs with known redshifts, but due to observational limitations, only 11% have known redshifts (z). There have been numerous attempts to estimate redshifts via correlation studies, most of which have led to inaccurate predictions. To overcome this, we estimated GRB redshift via an ensemble-supervised machine-learning (ML) model that uses X-ray afterglows of long-duration GRBs observed by the Neil Gehrels Swift Observatory. The estimated redshifts are strongly correlated (a Pearson coefficient of 0.93) and have an rms error, namely, the square root of the average squared error &lt;Δz<sup>2</sup>&gt;, of 0.46 with the observed redshifts showing the reliability of this method. The addition of GRB afterglow parameters improves the predictions considerably by 63% compared to previous results in peer-reviewed literature. Finally, we use our ML model to infer the redshifts of 154 GRBs, which increase the known redshifts of long GRBs with plateaus by 94%, a significant milestone for enhancing GRB population studies that require large samples with redshift.</p>}},
  author       = {{Dainotti, Maria Giovanna and Taira, Elias and Wang, Eric and Lehman, Elias and Narendra, Aditya and Pollo, Agnieszka and Madejski, Grzegorz M. and Petrosian, Vahe and Bogdan, Malgorzata and Dey, Apratim and Bhardwaj, Shubham}},
  issn         = {{0067-0049}},
  language     = {{eng}},
  month        = {{03}},
  number       = {{1}},
  publisher    = {{IOP Publishing}},
  series       = {{Astrophysical Journal, Supplement Series}},
  title        = {{Inferring the Redshift of More than 150 GRBs with a Machine-learning Ensemble Model}},
  url          = {{http://dx.doi.org/10.3847/1538-4365/ad1aaf}},
  doi          = {{10.3847/1538-4365/ad1aaf}},
  volume       = {{271}},
  year         = {{2024}},
}