Galaxy Spectra Networks (GaSNet). III. Generative pre-trained network for spectrum reconstruction, redshift estimate and anomaly detection

Abstract

Classification of spectra (1) and anomaly detection (2) are fundamental steps to guarantee the highest accuracy in redshift measurements (3) in modern all-sky spectroscopic surveys. We introduce a new Galaxy Spectra Neural Network (GaSNet-III) model that takes advantage of generative neural networks to perform these three tasks at once with very high efficiency. We use two different generative networks, an autoencoder-like network and U-Net, to reconstruct the rest-frame spectrum (after redshifting). The autoencoder-like network operates similarly to the classical PCA, learning templates (eigenspectra) from the training set and returning modeling parameters. The U-Net, in contrast, functions as an end-to-end model and shows an advantage in noise reduction. By reconstructing spectra, we can achieve classification, redshift estimation, and anomaly detection in the same framework. Each rest-frame reconstructed spectrum is extended to the UV and a small part of the infrared (covering the blueshift of stars). Owing to the high computational efficiency of deep learning, we scan the chi-squared value for the entire type and redshift space and find the best-fitting point. Our results show that generative networks can achieve accuracy comparable to the classical PCA methods in spectral modeling with higher efficiency, especially achieving an average of $>98\%$ classification across all classes ($>99.9\%$ for star), and $>99\%$ (stars), $>98\%$ (galaxies) and $>93\%$ (quasars) redshift accuracy under cosmology research requirements. By comparing different peaks of chi-squared curves, we define the ``robustness'' in the scanned space, offering a method to identify potential ``anomalous'' spectra. Our approach provides an accurate and high-efficiency spectrum modeling tool for handling the vast data volumes from future spectroscopic sky surveys.

17 pages and 16 figures. Submitted to MNRAS

References in corpus (46)

• 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 First Data Release of the Sloan Digital Sky Survey
• The SDSS-IV extended Baryon Oscillation Spectroscopic Survey: Overview and Early Data
• Spectral Classification and Redshift Measurement for the SDSS-III Baryon Oscillation Spectroscopic Survey
• The Sloan Lens ACS Survey. I. A Large Spectroscopically Selected Sample of Massive Early-Type Lens Galaxies
• The Sloan Digital Sky Survey Quasar Catalog: Sixteenth Data Release
• Overview of the Instrumentation for the Dark Energy Spectroscopic Instrument
• A Catalog of Spectroscopically Confirmed White Dwarfs from the Sloan Digital Sky Survey Data Release 4
• The Completed SDSS-IV extended Baryon Oscillation Spectroscopic Survey: measurement of the BAO and growth rate of structure of the luminous red galaxy sample from the anisotropic power spectrum between redshifts 0.6 and 1.0
• Full spectrum fitting with photometry in pPXF: stellar population versus dynamical masses, non-parametric star formation history and metallicity for 3200 LEGA-C galaxies at redshift z~0.8
• The Completed SDSS-IV extended Baryon Oscillation Spectroscopic Survey: BAO and RSD measurements from the anisotropic power spectrum of the Quasar sample between redshift 0.8 and 2.2
• Improved redshifts for SDSS quasar spectra
• Spectral Classification of Quasars in the Sloan Digital Sky Survey: Eigenspectra; Redshift and Luminosity Effects
• The Spectroscopic Data Processing Pipeline for the Dark Energy Spectroscopic Instrument
• Star-galaxy Classification Using Deep Convolutional Neural Networks
• Deep learning of multi-element abundances from high-resolution spectroscopic data
• Distributions of Galaxy Spectral Types in the Sloan Digital Sky Survey
• 4MOST - 4-metre Multi-Object Spectroscopic Telescope
• The Completed SDSS-IV extended Baryon Oscillation Spectroscopic Survey: measurement of the BAO and growth rate of structure of the emission line galaxy sample from the anisotropic power spectrum between redshift 0.6 and 1.1
• New 3-D gas density maps of NaI and CaII interstellar absorption within 300pc
• Machine Learning in Astronomy: a practical overview
• The weirdest SDSS galaxies: results from an outlier detection algorithm
• An Application of Deep Neural Networks in the Analysis of Stellar Spectra
• Robust Machine Learning Applied to Astronomical Datasets I: Star-Galaxy Classification of the SDSS DR3 Using Decision Trees
• Dimensionality Reduction of SDSS Spectra with Variational Autoencoders
• SPCANet: Stellar Parameters and Chemical Abundances Network for LAMOST-II Medium Resolution Survey
• Learning to Denoise Astronomical Images with U-nets
• Photometry of high-redshift blended galaxies using deep learning
• The VIMOS Public Extragalactic Redshift Survey (VIPERS). A Support Vector Machine classification of galaxies, stars and AGNs
• Redshift Measurement and Spectral Classification for eBOSS Galaxies with the Redmonster Software
• QuasarNET: Human-level spectral classification and redshifting with Deep Neural Networks
• Denoising Weak Lensing Mass Maps with Deep Learning
• A data-driven model for spectra: Finding double redshifts in the Sloan Digital Sky Survey
• The VIMOS Public Extragalactic Redshift Survey (VIPERS): spectral classification through Principal Component Analysis
• Autoencoding Galaxy Spectra I: Architecture
• Autoencoding Galaxy Spectra II: Redshift Invariance and Outlier Detection
• Mapping the Diversity of Galaxy Spectra with Deep Unsupervised Machine Learning
• Using deep Residual Networks to search for galaxy-Lyα emitter lens candidates based on spectroscopic-selection
• Deep Learning-based galaxy image deconvolution
• Deep Learning in Searching the Spectroscopic Redshift of Quasars
• Deriving the star formation histories of galaxies from spectra with simulation-based inference
• De-noising of galaxy optical spectra with autoencoders
• Galaxy Spectra neural Network (GaSNet). II. Using Deep Learning for Spectral Classification and Redshift Predictions
• Inferring redshift and galaxy properties via a multi-task neural net with probabilistic outputs: An application to simulated MOONS spectra
• Galaxy Spectra neural Networks (GaSNets). I. Searching for strong lens candidates in eBOSS spectra using Deep Learning
• Beyond Gaia DR3: Tracing the [$\alpha$/M]-[M/H] bimodality from the inner to the outer Milky Way disc with Gaia-RVS and convolutional neural networks

Cited by in corpus (4)

• SpecZoo: An AI-Powered Platform for Spectral Analysis and Visualization in Science and Education
• A CNN--Transformer Denoiser for low-$S/N$ Galaxy Spectra: Stellar Population Recovery in Synthetic Tests
• Accurate spectroscopic redshift estimation using non-negative matrix factorization: application to MUSE spectra
• Identification of gravitational lenses obscured by foreground light in the KiDS dataset using U-Nets and ResNets