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

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.

23 pages and 31 figures. The published version of MNRAS

References in corpus (62)

• Theoretical Modeling of Starburst Galaxies
• Ensemble deep learning: A review
• Overview of the SDSS-IV MaNGA Survey: Mapping Nearby Galaxies at Apache Point Observatory
• The Sixteenth Data Release of the Sloan Digital Sky Surveys: First Release from the APOGEE-2 Southern Survey and Full Release of eBOSS Spectra
• The SDSS-IV extended Baryon Oscillation Spectroscopic Survey: Overview and Early Data
• An Analysis of the Shapes of Interstellar Extinction Curves. V. The IR-Through-UV Curve Morphology
• Spectral Classification and Redshift Measurement for the SDSS-III Baryon Oscillation Spectroscopic Survey
• AGN wind scaling relations and the co-evolution of black holes and galaxies
• The Sloan Digital Sky Survey Quasar Catalog: Sixteenth Data Release
• APOGEE Data and Spectral Analysis from SDSS Data Release 16: Seven Years of Observations Including First Results from APOGEE-South
• Overview of the Instrumentation for the Dark Energy Spectroscopic Instrument
• The Sloan Digital Sky Survey Quasar Catalog: Fourteenth Data Release
• The Sloan Digital Sky Survey Quasar Catalog: twelfth data release
• 4MOST: Project overview and information for the First Call for Proposals
• The Eighteenth Data Release of the Sloan Digital Sky Surveys: Targeting and First Spectra from SDSS-V
• A Test of the Cosmological Principle with Quasars
• The luminosities, sizes and velocity dispersions of Brightest Cluster Galaxies: Implications for formation history
• Star-galaxy Classification Using Deep Convolutional Neural Networks
• Semi-empirical analysis of Sloan Digital Sky Survey galaxies: II. The bimodality of the galaxy population revisited
• The wide-field, multiplexed, spectroscopic facility WEAVE: Survey design, overview, and simulated implementation
• Deep learning of multi-element abundances from high-resolution spectroscopic data
• A new library of theoretical stellar spectra with scaled-solar and alpha-enhanced mixtures
• Photometric redshifts from SDSS images using a Convolutional Neural Network
• ProSpect: Generating Spectral Energy Distributions with Complex Star Formation and Metallicity Histories
• Photometric redshift estimation via deep learning
• Galaxy Types in the Sloan Digital Sky Survey Using Supervised Artificial Neural Networks
• Uncertainties in Parameters Estimated with Neural Networks: Application to Strong Gravitational Lensing
• Alert Classification for the ALeRCE Broker System: The Light Curve Classifier
• An Application of Deep Neural Networks in the Analysis of Stellar Spectra
• SDSS-IV MaStar -- A Large and Comprehensive Empirical Stellar Spectral Library: First Release
• Deep Extragalactic VIsible Legacy Survey (DEVILS): SED Fitting in the D10-COSMOS Field and the Evolution of the Stellar Mass Function and SFR-$M_{\star }$ relation
• SDSS-IV DR17: Final Release of MaNGA PyMorph Photometric and Deep Learning Morphological Catalogs
• SKYNET: an efficient and robust neural network training tool for machine learning in astronomy
• Finding Strong Gravitational Lenses in the DESI DECam Legacy Survey
• Galaxy And Mass Assembly (GAMA): A forensic SED reconstruction of the cosmic star formation history and metallicity evolution by galaxy type
• A comprehensive and uniform sample of broad-line active galactic nuclei from the SDSS DR7
• The DESI Survey Validation: Results from Visual Inspection of the Quasar Survey Spectra
• Deep Learning of Quasar Spectra to Discover and Characterize Damped Lya Systems
• 4MOST Consortium Survey 7: Wide-Area VISTA Extragalactic Survey (WAVES)
• High-quality strong lens candidates in the final Kilo Degree survey footprint
• Photometry of high-redshift blended galaxies using deep learning
• Testing Convolutional Neural Networks for finding strong gravitational lenses in KiDS
• Redshift Measurement and Spectral Classification for eBOSS Galaxies with the Redmonster Software
• The final SDSS-IV/SPIDERS X-ray point source spectroscopic catalogue
• Classification of Broad Absorption Line Quasars with a Convolutional Neural Network
• 4MOST Consortium Survey 10: The Time-Domain Extragalactic Survey (TiDES)
• The Completed SDSS-IV extended Baryon Oscillation Spectroscopic Survey: A Catalogue of Strong Galaxy-Galaxy Lens Candidates
• GAlaxy Light profile convolutional neural NETworks (GaLNets). I. fast and accurate structural parameters for billion galaxy samples
• Assessing the performance of LTE and NLTE synthetic stellar spectra in a machine learning framework
• Galaxy classification: deep learning on the OTELO and COSMOS databases
• 4MOST Consortium Survey 6: Active Galactic Nuclei
• Photometric redshift estimates using Bayesian neural networks in the CSST survey
• 4MOST Consortium Survey 3: Milky Way Disc and Bulge Low-Resolution Survey (4MIDABLE-LR)
• Galaxy morphoto-Z with neural Networks (GaZNets). I. Optimized accuracy and outlier fraction from Imaging and Photometry
• Using deep Residual Networks to search for galaxy-Lyα emitter lens candidates based on spectroscopic-selection
• The Gaia-ESO Survey: Preparing the ground for 4MOST & WEAVE galactic surveys. Chemical evolution of lithium with machine learning
• LeMoN: Lens Modelling with Neural networks -- I. Automated modelling of strong gravitational lenses with Bayesian Neural Networks
• 4MOST Consortium Survey 4: Milky Way Disc and Bulge High-Resolution Survey (4MIDABLE-HR)
• 4MOST Consortium Survey 9: One Thousand and One Magellanic Fields (1001MC)
• 4MOST Consortium Survey 5: eROSITA Galaxy Cluster Redshift Survey
• 4MOST Consortium Survey 1: The Milky Way Halo Low-Resolution Survey
• Galaxy Spectra neural Networks (GaSNets). I. Searching for strong lens candidates in eBOSS spectra using Deep Learning

Cited by in corpus (6)

• Optimal, fast, and robust inference of reionization-era cosmology with the 21cmPIE-INN
• Galaxy Spectra Networks (GaSNet). III. Generative pre-trained network for spectrum reconstruction, redshift estimate and anomaly detection
• Inferring redshift and galaxy properties via a multi-task neural net with probabilistic outputs: An application to simulated MOONS spectra
• SpecPT (Spectroscopy Pre-trained Transformer) Model for Extragalactic Spectroscopy: I. Architecture and Automated Redshift Measurement
• CSST Slitless Spectra: Target Detection and Classification with YOLO
• Bayesian classification of astronomical spectra with class uncertainties