Mapping the Diversity of Galaxy Spectra with Deep Unsupervised Machine Learning

Abstract

Modern spectroscopic surveys of galaxies such as MaNGA consist of millions of diverse spectra covering different regions of thousands of galaxies. We propose and implement a deep unsupervised machine learning method to summarize the entire diversity of MaNGA spectra onto a 15x15 map (DESOM-1), where neighbouring points on the map represent similar spectra. We demonstrate our method as an alternative to conventional full spectral fitting for deriving physical quantities, as well as their full probability distributions, much more efficiently than traditional resource-intensive Bayesian methods. Since spectra are grouped by similarity, the distribution of spectra onto the map for a single galaxy, i.e., its "fingerprint", reveals the presence of distinct stellar populations within the galaxy indicating smoother or episodic star-formation histories. We further map the diversity of galaxy fingerprints onto a second map (DESOM-2). Using galaxy images and independent measures of galaxy morphology, we confirm that galaxies with similar fingerprints have similar morphologies and inclination angles. Since morphological information was not used in the mapping algorithm, relating galaxy morphology to the star-formation histories encoded in the fingerprints is one example of how the DESOM maps can be used to make scientific inferences.

arXiv comment19 pages, 14 figures. Accepted in The Astronomical Journal

References in corpus (36)

• The Sloan Digital Sky Survey: Technical Summary
• On the variation of the Initial Mass Function
• The Dust Content and Opacity of Actively Star-Forming Galaxies
• The Origin of the Mass--Metallicity Relation: Insights from 53,000 Star-Forming Galaxies in the SDSS
• Correcting for the Effects of Interstellar Extinction
• Stellar Masses and Star Formation Histories for 10^5 Galaxies from the Sloan Digital Sky Survey
• The 2.5 m Telescope of the Sloan Digital Sky Survey
• Overview of the SDSS-IV MaNGA Survey: Mapping Nearby Galaxies at Apache Point Observatory
• Metallicity Calibrations and the Mass-Metallicity Relation for Star-Forming Galaxies
• A large stellar evolution database for population synthesis studies. I. Scaled solar models and isochrones
• Improving the full spectrum fitting method: accurate convolution with Gauss-Hermite functions
• Adaptive spatial binning of integral-field spectroscopic data using Voronoi tessellations
• CALIFA, the Calar Alto Legacy Integral Field Area survey: I. Survey presentation
• Modeling the Panchromatic Spectral Energy Distributions of Galaxies
• Stellar Population Inference with Prospector
• Strong Nebular Line Ratios in the Spectra of z~2-3 Star-forming Galaxies: First Results from KBSS-MOSFIRE
• The Sydney-AAO Multi-object Integral field spectrograph (SAMI)
• UV-extended E-MILES stellar population models: young components in massive early-type galaxies
• The MaNGA Integral Field Unit Fiber Feed System for the Sloan 2.5 m Telescope
• The Data Reduction Pipeline for the SDSS-IV MaNGA IFU Galaxy Survey
• Ages and metallicities of early-type galaxies in the SDSS: new insight into the physical origin of the colour-magnitude and the Mg2-sigmaV relations
• Marvin: A Toolkit for Streamlined Access and Visualization of the SDSS-IV MaNGA Data Set
• New Constraints on the Star Formation Histories and Dust Attenuation of Galaxies in the Local Universe from GALEX
• Are galactic star formation and quenching governed by local, global or environmental phenomena?
• Deep learning predictions of galaxy merger stage and the importance of observational realism
• Finding high-redshift strong lenses in DES using convolutional neural networks
• Convolutional neural network identification of galaxy post-mergers in UNIONS using IllustrisTNG
• Dimensionality Reduction of SDSS Spectra with Variational Autoencoders
• LensExtractor: A Convolutional Neural Network in Search of Strong Gravitational Lenses
• An Artificial Neural Network Approach For Ranking Quenching Parameters In Central Galaxies
• The UNAM-KIAS Catalog of Isolated Galaxies
• Two Growing Modes and the Morphology-Quiescence Relation in Galaxies
• A re-assessment of strong line metallicity conversions in the machine learning era
• Comparison of Multi-Class and Binary Classification Machine Learning Models in Identifying Strong Gravitational Lenses
• Classifying galaxy spectra at 0.5<z<1 with self-organizing maps
• An astronomical image content-based recommendation system using combined deep learning models in a fully unsupervised mode

Cited by in corpus (12)

• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• AstroCLIP: A Cross-Modal Foundation Model for Galaxies
• A review of unsupervised learning in astronomy
• Autoencoding Galaxy Spectra I: Architecture
• Stellar Populations With Optical Spectra: Deep Learning vs. Popular Spectrum Fitting Codes
• Stochastic Modelling of Star Formation Histories III. Constraints from Physically-Motivated Gaussian Processes
• Deriving the star formation histories of galaxies from spectra with simulation-based inference
• A representation learning approach to probe for dynamical dark energy in matter power spectra
• Galaxy Spectra Networks (GaSNet). III. Generative pre-trained network for spectrum reconstruction, redshift estimate and anomaly detection
• Automated quasar continuum estimation using neural networks: a comparative study of deep-learning architectures
• Navigating AGN variability with self-organizing maps
• The PAU Survey: Classifying low-z SEDs using Machine Learning clustering