Deep learning in quasar physics

被引：0

作者：

Nia, F. Rastegar ^{[1
,2
,3
,4
]}

Mirtorabi, M. T. ^{[1
]}

Moradi, R. ^{[4
,5
,6
]}

Wang, Y. ^{[4
,5
,6
]}

Sadr, A. Vafaei ^{[7
,8
]}

机构：

[1] Alzahra Univ Vanak, Phys Dept, Tehran 1993891176, Iran

[2] Univ Roma La Sapienza, ICRA, Piazzale Aldo Moro 5, I-00185 Rome, Italy

[3] Univ Roma La Sapienza, Dipartimento Fis, Piazzale Aldo Moro 5, I-00185 Rome, Italy

[4] ICRANet, Piazza Repubbl 10, I-65122 Pescara, Italy

[5] Sapienza Univ Roma, ICRA, Dipartimento Fis, I-00185 Rome, Italy

[6] INAF, I-00136 Rome, Italy

[7] Univ Geneva, Dept Phys Theor, Geneva, Switzerland

[8] Univ Geneva, Ctr Astroparticle Phys, Geneva, Switzerland

来源：

SIXTEENTH MARCEL GROSSMANN MEETING | 2023年

关键词：

Quasar; Deep learning; CNN; SDSS; PHOTOMETRIC REDSHIFTS; STELLAR SPECTRA; NEURAL-NETWORKS; GALAXIES; CLASSIFICATION;

D O I：

暂无

中图分类号：

P1 [天文学];

学科分类号：

0704 ;

摘要：

In view of increasing data volume of existing and upcoming telescopes/detectors we here apply the 1-dimensional convolutional neural network (CNN) to estimate the redshift of (high-)redshifts quasars in Sloan Digital Sky Survey IV (SDSS-IV) quasar catalog from DR16 of eBOSS. Our CNN takes the flux of the quasars as an array and their redshift as labels. We here evidence that new structure of the network, and augmenting the training set, provide a high precision result in estimating the redshift of quasars.

引用

页码：382 / 390

页数：9

共 50 条

[31] Physics Informed Deep Learning for Traffic State Estimation
Huang, Jiheng
Agarwal, Shaurya
2020 IEEE 23RD INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC), 2020,
[32] Physics-informed deep learning for digital materials
Zhang, Zhizhou
Gu, Grace X.
THEORETICAL AND APPLIED MECHANICS LETTERS, 2021, 11 (01)
[33] DEEP LEARNING WITH ULTRASOUND PHYSICS FOR FETAL SKULL SEGMENTATION
Cerrolaza, Juan J.
Sinclair, Matthew
Li, Yuanwei
Gomez, Alberto
Ferrante, Enzo
Matthew, Jaqueline
Gupta, Chandni
Knight, Caroline L.
Rueckert, Daniel
2018 IEEE 15TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI 2018), 2018, : 564 - 567
[34] Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations
Raissi, Maziar
JOURNAL OF MACHINE LEARNING RESEARCH, 2018, 19
[35] The Quasar Luminosity Function at z ∼ 5 via Deep Learning and Bayesian Information Criterion
Shin, Suhyun
Im, Myungshin
Kim, Yongjung
ASTROPHYSICAL JOURNAL, 2022, 937 (01):
[36] Intuitive physics learning in a deep-learning model inspired by developmental psychology
Piloto, Luis S.
Weinstein, Ari
Battaglia, Peter
Botvinick, Matthew
NATURE HUMAN BEHAVIOUR, 2022, 6 (09) : 1257 - +
[37] Intuitive physics learning in a deep-learning model inspired by developmental psychology
Luis S. Piloto
Ari Weinstein
Peter Battaglia
Matthew Botvinick
Nature Human Behaviour, 2022, 6 : 1257 - 1267
[38] Quasar candidates in the Hubble Deep Field
Conti, A
Kennefick, JD
Martini, P
Osmer, PS
ASTRONOMICAL JOURNAL, 1999, 117 (02): : 645 - 657
[39] THE COMPLETENESS OF THE BRACCESI DEEP QUASAR SURVEY
CRISTIANI, S
VERONCETTY, MP
VERON, P
ASTRONOMY & ASTROPHYSICS, 1984, 135 (01): : 122 - 128
[40] The SDSS quasar survey(s): Probing the physics of quasars
Richards, GT
Hall, PB
Strauss, MA
Vanden Berk, DE
Schneider, DP
Reichard, TA
MULTIWAVELENGTH AGN SURVEYS, 2004, : 47 - 52

← 1 2 3 4 5 →