Predicting the Redshift of γ-Ray-loud AGNs Using Supervised Machine Learning
(2021) In Astrophysical Journal 920(2).- Abstract
Active galactic nuclei (AGNs) are very powerful galaxies characterized by extremely bright emissions coming from their central massive black holes. Knowing the redshifts of AGNs provides us with an opportunity to determine their distance to investigate important astrophysical problems, such as the evolution of the early stars and their formation, along with the structure of early galaxies. The redshift determination is challenging because it requires detailed follow-up of multiwavelength observations, often involving various astronomical facilities. Here we employ machine-learning algorithms to estimate redshifts from the observed γ-ray properties and photometric data of γ-ray-loud AGNs from the Fourth Fermi-LAT Catalog. The prediction... (More)
Active galactic nuclei (AGNs) are very powerful galaxies characterized by extremely bright emissions coming from their central massive black holes. Knowing the redshifts of AGNs provides us with an opportunity to determine their distance to investigate important astrophysical problems, such as the evolution of the early stars and their formation, along with the structure of early galaxies. The redshift determination is challenging because it requires detailed follow-up of multiwavelength observations, often involving various astronomical facilities. Here we employ machine-learning algorithms to estimate redshifts from the observed γ-ray properties and photometric data of γ-ray-loud AGNs from the Fourth Fermi-LAT Catalog. The prediction is obtained with the Superlearner algorithm using a LASSO-selected set of predictors. We obtain a tight correlation, with a Pearson correlation coefficient of 71.3% between the inferred and observed redshifts and an average Δz norm = 11.6 10-4. We stress that, notwithstanding the small sample of γ-ray-loud AGNs, we obtain a reliable predictive model using Superlearner, which is an ensemble of several machine-learning models.
(Less)
- author
- Dainotti, Maria Giovanna
; Bogdan, Malgorzata
LU
; Narendra, Aditya
; Gibson, Spencer James
; Miasojedow, Blazej
; Liodakis, Ioannis
; Pollo, Agnieszka
; Nelson, Trevor
; Wozniak, Kamil
; Nguyen, Zooey
and Larsson, Johan
LU
(Less) - organization
- publishing date
- 2021-10-20
- type
- Contribution to journal
- publication status
- published
- subject
- in
- Astrophysical Journal
- volume
- 920
- issue
- 2
- article number
- 118
- publisher
- American Astronomical Society
- external identifiers
-
- scopus:85118108847
- ISSN
- 0004-637X
- DOI
- 10.3847/1538-4357/ac1748
- language
- English
- LU publication?
- yes
- additional info
- Publisher Copyright: © 2021. The American Astronomical Society. All rights reserved..
- id
- 40fc5f0c-6497-4ad8-84bc-5a8f07b6d92b
- date added to LUP
- 2021-11-16 11:23:53
- date last changed
- 2022-11-24 01:22:54
@article{40fc5f0c-6497-4ad8-84bc-5a8f07b6d92b,
abstract = {{<p>Active galactic nuclei (AGNs) are very powerful galaxies characterized by extremely bright emissions coming from their central massive black holes. Knowing the redshifts of AGNs provides us with an opportunity to determine their distance to investigate important astrophysical problems, such as the evolution of the early stars and their formation, along with the structure of early galaxies. The redshift determination is challenging because it requires detailed follow-up of multiwavelength observations, often involving various astronomical facilities. Here we employ machine-learning algorithms to estimate redshifts from the observed γ-ray properties and photometric data of γ-ray-loud AGNs from the Fourth Fermi-LAT Catalog. The prediction is obtained with the Superlearner algorithm using a LASSO-selected set of predictors. We obtain a tight correlation, with a Pearson correlation coefficient of 71.3% between the inferred and observed redshifts and an average Δz norm = 11.6 10-4. We stress that, notwithstanding the small sample of γ-ray-loud AGNs, we obtain a reliable predictive model using Superlearner, which is an ensemble of several machine-learning models.</p>}},
author = {{Dainotti, Maria Giovanna and Bogdan, Malgorzata and Narendra, Aditya and Gibson, Spencer James and Miasojedow, Blazej and Liodakis, Ioannis and Pollo, Agnieszka and Nelson, Trevor and Wozniak, Kamil and Nguyen, Zooey and Larsson, Johan}},
issn = {{0004-637X}},
language = {{eng}},
month = {{10}},
number = {{2}},
publisher = {{American Astronomical Society}},
series = {{Astrophysical Journal}},
title = {{Predicting the Redshift of γ-Ray-loud AGNs Using Supervised Machine Learning}},
url = {{http://dx.doi.org/10.3847/1538-4357/ac1748}},
doi = {{10.3847/1538-4357/ac1748}},
volume = {{920}},
year = {{2021}},
}