Galaxy Spectra neural Network (GaSNet). II. Using Deep Learning for Spectral Classification and Redshift Predictions - Université de Lyon
Journal Articles Monthly Notices of the Royal Astronomical Society: Letters Year : 2024

Galaxy Spectra neural Network (GaSNet). II. Using Deep Learning for Spectral Classification and Redshift Predictions

Fucheng Zhong
  • Function : Author
Nicola R. Napolitano
  • Function : Author
Caroline Heneka
  • Function : Author
Rui Li
  • Function : Author
Franz Erik Bauer
  • Function : Author
Johan Comparat
  • Function : Author
Young-Lo Kim
  • Function : Author
Marcella Longhetti
  • Function : Author
Jonathan Loveday
  • Function : Author
Boudewijn F. Roukema
  • Function : Author
Benedict L. Rouse
  • Function : Author
Mara Salvato
  • Function : Author
Crescenzo Tortora
  • Function : Author
Roberto J. Assef
  • Function : Author
Letizia P. Cassarà
  • Function : Author
Luca Costantin
  • Function : Author
Scott Croom
  • Function : Author
Luke J M Davies
  • Function : Author
Alexander Fritz
  • Function : Author
Guillaume Guiglion
  • Function : Author
Emanuela Pompei
  • Function : Author
Andrew Humphrey
  • Function : Author
Claudio Ricci
  • Function : Author
Cristóbal Sifón
  • Function : Author
Elmo Tempel
  • Function : Author
Tayyaba Zafar
  • Function : Author

Abstract

Large sky spectroscopic surveys have reached the scale of photometric surveys in terms of sample sizes and data complexity. These huge datasets require efficient, accurate, and flexible automated tools for data analysis and science exploitation. We present the Galaxy Spectra Network/GaSNet-II, a supervised multi-network 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 for classified objects in each of them. It also provides redshift errors, using a network-of-networks that reproduces a Monte Carlo test on each spectrum, by randomizing their weight initialization. As a demonstration of the capability of the deep learning pipeline, 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% average classification accuracy over the 13 classes (larger than 90% for the majority of them), and an average redshift error of approximately 0.23% for galaxies and 2.1% for quasars. We further train/test the same pipeline to classify spectra and predict redshifts for a sample of 200k 4MOST mock spectra and 21k publicly released DESI spectra. On 4MOST mock data, we reach 93.4% accuracy in 10-class classification and an average redshift error of 0.55% for galaxies and 0.3% for active galactic nuclei. On DESI data, we reach 96% accuracy in (star/galaxy/quasar only) classification and an average redshift error of 2.8% for galaxies and 4.8% 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 of Stage-IV survey observations and an ideal tool for feedback loops aimed at night-by-night survey strategy optimization.
Fichier principal
Vignette du fichier
stae1461.pdf (48.19 Mo) Télécharger le fichier
Origin Publisher files allowed on an open archive

Dates and versions

hal-04299139 , version 1 (08-11-2024)

Licence

Identifiers

Cite

Fucheng Zhong, Nicola R. Napolitano, Caroline Heneka, Rui Li, Franz Erik Bauer, et al.. Galaxy Spectra neural Network (GaSNet). II. Using Deep Learning for Spectral Classification and Redshift Predictions. Monthly Notices of the Royal Astronomical Society: Letters, 2024, 532, pp.643-665. ⟨hal-04299139⟩
55 View
1 Download

Altmetric

Share

More