Home > Research > Publications & Outputs > Galaxy Spectra neural Network (GaSNet). II. Usi...

Links

Text available via DOI:

View graph of relations

Galaxy Spectra neural Network (GaSNet). II. Using deep learning for spectral classification and redshift predictions

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Galaxy Spectra neural Network (GaSNet). II. Using deep learning for spectral classification and redshift predictions. / Zhong, Fucheng; Napolitano, Nicola R; Heneka, Caroline et al.
In: Monthly Notices of the Royal Astronomical Society, Vol. 532, No. 1, 31.07.2024, p. 643-665.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Zhong, F, Napolitano, NR, Heneka, C, Li, R, Bauer, FE, Bouche, N, Comparat, J, Kim, Y-L, Krogager, J-K, Longhetti, M, Loveday, J, Roukema, BF, Rouse, BL, Salvato, M, Tortora, C, Assef, RJ, Cassarà, LP, Costantin, L, Croom, SM, Davies, LJM, Fritz, A, Guiglion, G, Humphrey, A, Pompei, E, Ricci, C, Sifón, C, Tempel, E & Zafar, T 2024, 'Galaxy Spectra neural Network (GaSNet). II. Using deep learning for spectral classification and redshift predictions', Monthly Notices of the Royal Astronomical Society, vol. 532, no. 1, pp. 643-665. https://doi.org/10.1093/mnras/stae1461

APA

Zhong, F., Napolitano, N. R., Heneka, C., Li, R., Bauer, F. E., Bouche, N., Comparat, J., Kim, Y.-L., Krogager, J.-K., Longhetti, M., Loveday, J., Roukema, B. F., Rouse, B. L., Salvato, M., Tortora, C., Assef, R. J., Cassarà, L. P., Costantin, L., Croom, S. M., ... Zafar, T. (2024). Galaxy Spectra neural Network (GaSNet). II. Using deep learning for spectral classification and redshift predictions. Monthly Notices of the Royal Astronomical Society, 532(1), 643-665. https://doi.org/10.1093/mnras/stae1461

Vancouver

Zhong F, Napolitano NR, Heneka C, Li R, Bauer FE, Bouche N et al. Galaxy Spectra neural Network (GaSNet). II. Using deep learning for spectral classification and redshift predictions. Monthly Notices of the Royal Astronomical Society. 2024 Jul 31;532(1):643-665. Epub 2024 Jun 27. doi: 10.1093/mnras/stae1461

Author

Zhong, Fucheng ; Napolitano, Nicola R ; Heneka, Caroline et al. / Galaxy Spectra neural Network (GaSNet). II. Using deep learning for spectral classification and redshift predictions. In: Monthly Notices of the Royal Astronomical Society. 2024 ; Vol. 532, No. 1. pp. 643-665.

Bibtex

@article{3727526445804b2b9b0b1ad0d503ce93,
title = "Galaxy Spectra neural Network (GaSNet). II. Using deep learning for spectral classification and redshift predictions",
abstract = "The size and complexity reached by the large sky spectroscopic surveys require efficient, accurate, and flexible automated tools for data analysis and science exploitation. We present the Galaxy Spectra Network/GaSNet-II, a supervised multinetwork deep learning tool for spectra classification and redshift prediction. GaSNet-II can be trained to identify a customized number of classes and optimize the redshift predictions. Redshift errors are determined via an ensemble/pseudo-Monte Carlo test obtained by randomizing the weights of the network-of-networks structure. As a demonstration of the capability of GaSNet-II, we use 260k Sloan Digital Sky Survey spectra from Data Release 16, separated into 13 classes including 140k galactic, and 120k extragalactic objects. GaSNet-II achieves 92.4 per cent average classification accuracy over the 13 classes and mean redshift errors of approximately 0.23 per cent for galaxies and 2.1 per cent for quasars. We further train/test the pipeline on a sample of 200k 4MOST (4-metre Multi-Object Spectroscopic Telescope) mock spectra and 21k publicly released DESI (Dark Energy Spectroscopic Instrument) spectra. On 4MOST mock data, we reach 93.4 per cent accuracy in 10-class classification and mean redshift error of 0.55 per cent for galaxies and 0.3 per cent for active galactic nuclei. On DESI data, we reach 96 per cent accuracy in (star/galaxy/quasar only) classification and mean redshift error of 2.8 per cent for galaxies and 4.8 per cent for quasars, despite the small sample size available. GaSNet-II can process ∼40k spectra in less than one minute, on a normal Desktop GPU. This makes the pipeline particularly suitable for real-time analyses and feedback loops for optimization of Stage-IV survey observations.",
author = "Fucheng Zhong and Napolitano, {Nicola R} and Caroline Heneka and Rui Li and Bauer, {Franz Erik} and Nicolas Bouche and Johan Comparat and Young-Lo Kim and Jens-Kristian Krogager and Marcella Longhetti and Jonathan Loveday and Roukema, {Boudewijn F} and Rouse, {Benedict L} and Mara Salvato and Crescenzo Tortora and Assef, {Roberto J} and Cassar{\`a}, {Letizia P} and Luca Costantin and Croom, {Scott M} and Davies, {Luke J M} and Alexander Fritz and Guillaume Guiglion and Andrew Humphrey and Emanuela Pompei and Claudio Ricci and Crist{\'o}bal Sif{\'o}n and Elmo Tempel and Tayyaba Zafar",
year = "2024",
month = jul,
day = "31",
doi = "10.1093/mnras/stae1461",
language = "English",
volume = "532",
pages = "643--665",
journal = "Monthly Notices of the Royal Astronomical Society",
issn = "0035-8711",
publisher = "OXFORD UNIV PRESS",
number = "1",

}

RIS

TY - JOUR

T1 - Galaxy Spectra neural Network (GaSNet). II. Using deep learning for spectral classification and redshift predictions

AU - Zhong, Fucheng

AU - Napolitano, Nicola R

AU - Heneka, Caroline

AU - Li, Rui

AU - Bauer, Franz Erik

AU - Bouche, Nicolas

AU - Comparat, Johan

AU - Kim, Young-Lo

AU - Krogager, Jens-Kristian

AU - Longhetti, Marcella

AU - Loveday, Jonathan

AU - Roukema, Boudewijn F

AU - Rouse, Benedict L

AU - Salvato, Mara

AU - Tortora, Crescenzo

AU - Assef, Roberto J

AU - Cassarà, Letizia P

AU - Costantin, Luca

AU - Croom, Scott M

AU - Davies, Luke J M

AU - Fritz, Alexander

AU - Guiglion, Guillaume

AU - Humphrey, Andrew

AU - Pompei, Emanuela

AU - Ricci, Claudio

AU - Sifón, Cristóbal

AU - Tempel, Elmo

AU - Zafar, Tayyaba

PY - 2024/7/31

Y1 - 2024/7/31

N2 - The size and complexity reached by the large sky spectroscopic surveys require efficient, accurate, and flexible automated tools for data analysis and science exploitation. We present the Galaxy Spectra Network/GaSNet-II, a supervised multinetwork deep learning tool for spectra classification and redshift prediction. GaSNet-II can be trained to identify a customized number of classes and optimize the redshift predictions. Redshift errors are determined via an ensemble/pseudo-Monte Carlo test obtained by randomizing the weights of the network-of-networks structure. As a demonstration of the capability of GaSNet-II, we use 260k Sloan Digital Sky Survey spectra from Data Release 16, separated into 13 classes including 140k galactic, and 120k extragalactic objects. GaSNet-II achieves 92.4 per cent average classification accuracy over the 13 classes and mean redshift errors of approximately 0.23 per cent for galaxies and 2.1 per cent for quasars. We further train/test the pipeline on a sample of 200k 4MOST (4-metre Multi-Object Spectroscopic Telescope) mock spectra and 21k publicly released DESI (Dark Energy Spectroscopic Instrument) spectra. On 4MOST mock data, we reach 93.4 per cent accuracy in 10-class classification and mean redshift error of 0.55 per cent for galaxies and 0.3 per cent for active galactic nuclei. On DESI data, we reach 96 per cent accuracy in (star/galaxy/quasar only) classification and mean redshift error of 2.8 per cent for galaxies and 4.8 per cent for quasars, despite the small sample size available. GaSNet-II can process ∼40k spectra in less than one minute, on a normal Desktop GPU. This makes the pipeline particularly suitable for real-time analyses and feedback loops for optimization of Stage-IV survey observations.

AB - The size and complexity reached by the large sky spectroscopic surveys require efficient, accurate, and flexible automated tools for data analysis and science exploitation. We present the Galaxy Spectra Network/GaSNet-II, a supervised multinetwork deep learning tool for spectra classification and redshift prediction. GaSNet-II can be trained to identify a customized number of classes and optimize the redshift predictions. Redshift errors are determined via an ensemble/pseudo-Monte Carlo test obtained by randomizing the weights of the network-of-networks structure. As a demonstration of the capability of GaSNet-II, we use 260k Sloan Digital Sky Survey spectra from Data Release 16, separated into 13 classes including 140k galactic, and 120k extragalactic objects. GaSNet-II achieves 92.4 per cent average classification accuracy over the 13 classes and mean redshift errors of approximately 0.23 per cent for galaxies and 2.1 per cent for quasars. We further train/test the pipeline on a sample of 200k 4MOST (4-metre Multi-Object Spectroscopic Telescope) mock spectra and 21k publicly released DESI (Dark Energy Spectroscopic Instrument) spectra. On 4MOST mock data, we reach 93.4 per cent accuracy in 10-class classification and mean redshift error of 0.55 per cent for galaxies and 0.3 per cent for active galactic nuclei. On DESI data, we reach 96 per cent accuracy in (star/galaxy/quasar only) classification and mean redshift error of 2.8 per cent for galaxies and 4.8 per cent for quasars, despite the small sample size available. GaSNet-II can process ∼40k spectra in less than one minute, on a normal Desktop GPU. This makes the pipeline particularly suitable for real-time analyses and feedback loops for optimization of Stage-IV survey observations.

U2 - 10.1093/mnras/stae1461

DO - 10.1093/mnras/stae1461

M3 - Journal article

VL - 532

SP - 643

EP - 665

JO - Monthly Notices of the Royal Astronomical Society

JF - Monthly Notices of the Royal Astronomical Society

SN - 0035-8711

IS - 1

ER -