Inferring physical properties of galaxies from their emission line spectra

Abstract

We present a new approach based on Supervised Machine Learning (SML) algorithms to infer key physical properties of galaxies (density, metallicity, column density and ionization parameter) from their emission line spectra. We introduce a numerical code (called GAME, GAlaxy Machine learning for Emission lines) implementing this method and test it extensively. GAME delivers excellent predictive performances, especially for estimates of metallicity and column densities. We compare GAME with the most widely used diagnostics (e.g. R${}_{23}$, [NII]$\lambda$6584 / H$\alpha$ indicators) showing that it provides much better accuracy and wider applicability range. GAME is particularly suitable for use in combination with Integral Field Unit (IFU) spectroscopy, both for rest-frame optical/UV nebular lines and far-infrared/sub-mm lines arising from Photo-Dissociation Regions. Finally, GAME can also be applied to the analysis of synthetic galaxy maps built from numerical simulations.

arXiv comment14 pages, 11 figures, accepted for publication in MNRAS

References in corpus (50)

• Scikit-learn: Machine Learning in Python
• On the variation of the Initial Mass Function
• Star Formation in Galaxies Along the Hubble Sequence
• Starburst99: Synthesis Models for Galaxies with Active Star Formation
• Theoretical Modeling of Starburst Galaxies
• [O III]/[N II] as an Abundance Indicator at High Redshift
• Metallicity Calibrations and the Mass-Metallicity Relation for Star-Forming Galaxies
• Using Strong Lines to Estimate Abundances in Extragalactic HII Regions and Starburst Galaxies
• AMAZE. I. The evolution of the mass-metallicity relation at z>3
• The MAPPINGS III Library of Fast Radiative Shock Models
• On the properties of massive Population III stars and metal-free stellar populations
• A standard stellar library for evolutionary synthesis: I. Calibration of theoretical spectra
• Re-examining Larson's Scaling Relationships in Galactic Molecular Clouds
• ANNz: estimating photometric redshifts using artificial neural networks
• The applicability of FIR fine-structure lines as Star Formation Rate tracers over wide ranges of metallicities and galaxy types
• The Effects of Stellar Rotation. II. A Comprehensive Set of Starburst99 Models
• Realistic Ionizing Fluxes for Young Stellar Populations from 0.05 to twice solar metallicity
• Data Mining and Machine Learning in Astronomy
• Gas metallicity diagnostics in star-forming galaxies
• An Integrated Spectrophotometric Survey of Nearby Star-Forming Galaxies
• TPZ : Photometric redshift PDFs and ancillary information by using prediction trees and random forests
• Mocassin: A fully three-dimensional Monte Carlo photoionization code
• The dusty MOCASSIN: fully self-consistent 3D photoionisation and dust radiative transfer models
• On the [CII]-SFR relation in high redshift galaxies
• Eliminating Error in the Chemical Abundance Scale for Extragalactic HII Regions
• The MAGNUM survey: Positive feedback in the nuclear region of NGC 5643 suggested by MUSE
• Theoretical Modeling of Star-Forming Galaxies I. Emission Line Diagnostic Grids for Local and Low-Metallicity Galaxies
• IZI: Inferring the Gas Phase Metallicity (Z) and Ionization Parameter (q) of Ionized Nebulae using Bayesian Statistics
• The Spitzer View of Low-Metallicity Star Formation: III. Fine Structure Lines, Aromatic Features, and Molecules
• Robust Machine Learning Applied to Astronomical Datasets I: Star-Galaxy Classification of the SDSS DR3 Using Decision Trees
• ALMA reveals a chemically evolved submillimeter galaxy at z=4.76
• Metallicity Diagnostics with Infrared Fine-Structure Lines
• Fundamental Parameters of Main-Sequence Stars in an Instant with Machine Learning
• An empirical calibration of nebular abundances based on the sulphur emission lines
• Ionization Parameter as a Diagnostic of Radiation and Wind Pressures in H II Regions and Starburst Galaxies
• Anomaly detection for machine learning redshifts applied to SDSS galaxies
• A Hybrid Ensemble Learning Approach to Star-Galaxy Classification
• Machine Learning based photometric redshifts for the KiDS ESO DR2 galaxies
• Machine Learning and Cosmological Simulations I: Semi-Analytical Models
• Far-infrared line spectra of Seyfert galaxies from the Herschel-PACS Spectrometer
• Data augmentation for machine learning redshifts applied to SDSS galaxies
• Dust in the Extremely Metal-Poor Blue Compact Dwarf Galaxy IZw18: The Spitzer Mid-Infrared View
• Mapping metals at high redshift with far-infrared lines
• Stacking for machine learning redshifts applied to SDSS galaxies
• What can emission lines tell us?
• The New Frontier: Galactic-Scale Star Formation
• A machine-learning approach to measuring the escape of ionizing radiation from galaxies in the reionization epoch
• Star Formation Rate Determinations
• Robust Machine Learning Applied to Terascale Astronomical Datasets
• The Mid-Infrared Properties of Blue Compact Dwarf Galaxies

Cited by in corpus (15)

• Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
• The Herschel Dwarf Galaxy Survey: II. Physical conditions, origin of [CII] emission, and porosity of the multiphase low-metallicity ISM
• Deep learning from 21-cm tomography of the Cosmic Dawn and Reionization
• CPz: Classification-aided photometric-redshift estimation
• Machine learning technique for morphological classification of galaxies from the SDSS. I. Photometry-based approach
• Photometric redshift-aided classification using ensemble learning
• A probabilistic approach to emission-line galaxy classification
• GAME: GAlaxy Machine learning for Emission lines
• Machine Learning Approach to Integral Field Unit Spectroscopy Observations: I. HII Region Kinematics
• The interstellar medium of dwarf galaxies: new insights from Machine Learning analysis of emission line spectra
• Inferring redshift and galaxy properties via a multi-task neural net with probabilistic outputs: An application to simulated MOONS spectra
• Machine learning applications for the study of AGN physical properties using photometric observations
• Classifying spectra of emission-line regions with neural networks -- An application to integral field spectroscopic data of M33
• Automated quasar continuum estimation using neural networks: a comparative study of deep-learning architectures
• A Value-added Physical Properties Catalog for Low-redshift Galaxies from DESI Legacy Imaging Surveys DR10