GAME: GAlaxy Machine learning for Emission lines

Abstract

We present an updated, optimized version of GAME (GAlaxy Machine learning for Emission lines), a code designed to infer key interstellar medium physical properties from emission line intensities of UV/optical/far infrared galaxy spectra. The improvements concern: (a) an enlarged spectral library including Pop III stars; (b) the inclusion of spectral noise in the training procedure, and (c) an accurate evaluation of uncertainties. We extensively validate the optimized code and compare its performance against empirical methods and other available emission line codes (PYQZ and HII-CHI-MISTRY) on a sample of 62 SDSS stacked galaxy spectra and 75 observed HII regions. Very good agreement is found for metallicity. However, ionization parameters derived by GAME tend to be higher. We show that this is due to the use of too limited libraries in the other codes. The main advantages of GAME are the simultaneous use of all the measured spectral lines, and the extremely short computational times. We finally discuss the code potential and limitations.

arXiv comment11 pages, 8 figures (appendix: 7 pages, 10 figures). Accepted for publication in MNRAS

References in corpus (62)

• Scikit-learn: Machine Learning in Python
• The chemical composition of the Sun
• On the variation of the Initial Mass Function
• The Origin of the Mass--Metallicity Relation: Insights from 53,000 Star-Forming Galaxies in the SDSS
• [O III]/[N II] as an Abundance Indicator at High Redshift
• Metallicity Calibrations and the Mass-Metallicity Relation for Star-Forming Galaxies
• Rest-Frame Ultraviolet Spectra of z~3 Lyman Break Galaxies
• Using Strong Lines to Estimate Abundances in Extragalactic HII Regions and Starburst Galaxies
• The 'Forbidden' Abundance of Oxygen in the Sun
• AMAZE. I. The evolution of the mass-metallicity relation at z>3
• On the properties of massive Population III stars and metal-free stellar populations
• Line formation in solar granulation: IV. [O I], OI and OH lines and the photospheric O abundance
• Metallicities of 0.3<z<1.0 Galaxies in the GOODS-North Field
• The O3N2 and N2 abundance indicators revisited: improved calibrations based on CALIFA and Te-based literature data
• Photoelectric Emission from Interstellar Dust: Grain Charging and Gas Heating
• The applicability of FIR fine-structure lines as Star Formation Rate tracers over wide ranges of metallicities and galaxy types
• Gas metallicity diagnostics in star-forming galaxies
• Lyman-alpha and CIII] Emission in z=7-9 Galaxies: Accelerated Reionization Around Luminous Star Forming Systems?
• Evidence for PopIII-like stellar populations in the most luminous Lyman-$\alpha$ emitters at the epoch of re-ionisation: spectroscopic confirmation
• New calibrations for abundance determinations in HII regions
• The spectral evolution of the first galaxies. I. James Webb Space Telescope detection limits and color criteria for population III galaxies
• Physical Conditions in a Young, Unreddened, Low Metallicity Galaxy at High Redshift
• New fully empirical calibrations of strong-line metallicity indicators in star forming galaxies
• New Strong Line Abundance Diagnostics for \HII Regions: Effects of $\kappa$-Distributed Electron Energies and New Atomic Data
• Chemical abundances in high-redshift galaxies: A powerful new emission line diagnostic
• Extragalactic chemical abundances: do HII regions and young stars tell the same story? The case of the spiral galaxy NGC 300
• Spectroscopic detection of CIV in a galaxy at z=7.045: Implications for the ionizing spectra of reionization-era galaxies
• Oxygen and Nitrogen in Isolated Dwarf Irregular Galaxies
• Deriving model-based T${}_e$-consistent chemical abundances in ionised gaseous nebulae
• Ultraviolet Emission Lines in Young Low Mass Galaxies at z~2: Physical Properties and Implications for Studies at z>7
• The flat oxygen abundance gradient in the extended disk of M83
• Spectroscopic detections of CIII]1909 at z~6-7: A new probe of early star forming galaxies and cosmic reionisation
• On the [CII]-SFR relation in high redshift galaxies
• Keck HIRES Spectroscopy of Extragalactic HII Regions: C and O Abundances from Recombination Lines
• On the abundance discrepancy problem in HII regions
• Far-infrared Fine-Structure Line Diagnostics of Ultraluminous Infrared Galaxies
• Star Formation in Massive Clusters via the Wilkinson Microwave Anisotropy Probe and the Spitzer Glimpse Survey
• Heavy elements in Galactic and Magellanic Cloud HII regions: recombination-line versus forbidden-line abundances
• The localized chemical pollution in NGC 5253 revisited: Results from deep echelle spectrophotometry
• The Chemical Composition of the 30 Doradus Nebula Derived from VLT Echelle Spectrophotometry
• IZI: Inferring the Gas Phase Metallicity (Z) and Ionization Parameter (q) of Ionized Nebulae using Bayesian Statistics
• The oxygen abundance in the inner HII regions of M101. Implications for the calibration of strong-line metallicity indicators
• Ionized gaseous nebulae chemical abundance determination using the direct method
• Carbon and oxygen abundances from recombination lines in low-metallicity star-forming galaxies. Implications for chemical evolution
• Young stars and ionized nebulae in M83: comparing chemical abundances at high metallicity
• Chemical Composition of Two H II Regions in NGC 6822 Based on VLT Spectroscopy
• Metallicity Diagnostics with Infrared Fine-Structure Lines
• BOND: Bayesian Oxygen and Nitrogen abundance Determinations in giant H II regions using strong and semi-strong lines
• Far-infrared metallicity diagnostics: Application to local ultraluminous infrared galaxies
• Feature importance for machine learning redshifts applied to SDSS galaxies
• A Recalibration of Strong Line Oxygen Abundance Diagnostics via the Direct Method and Implications for the High Redshift Universe
• Chemical distribution of HII regions towards the Galactic anticentre
• Molecular clouds photoevaporation and FIR line emission
• On the far-infrared metallicity diagnostics: applications to high-redshift galaxies
• Sensitivity of PDR Calculations to Microphysical Details
• Mapping metals at high redshift with far-infrared lines
• Using photo-ionisation models to derive carbon and oxygen gas-phase abundances in the rest UV
• What can emission lines tell us?
• Inferring physical properties of galaxies from their emission line spectra
• Metallicities in the Outer Regions of Spiral Galaxies
• Studying distant galaxies: A Handbook of Methods and Analyses
• What can distant galaxies teach us about massive stars?

Cited by in corpus (19)

• Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
• Deep learning from 21-cm tomography of the Cosmic Dawn and Reionization
• Star formation rates and stellar masses from machine learning
• A Bayesian direct method implementation to fit emission line spectra: Application to the primordial He abundance determination
• A deep learning model to emulate simulations of cosmic reionization
• A re-assessment of strong line metallicity conversions in the machine learning era
• Deep learning for Sunyaev-Zel'dovich detection in Planck
• Machine Learning Approach to Integral Field Unit Spectroscopy Observations: I. HII Region Kinematics
• Neural networks: solving the chemistry of the interstellar medium
• The interstellar medium of dwarf galaxies: new insights from Machine Learning analysis of emission line spectra
• UV bright red-sequence galaxies: how do UV upturn systems evolve in redshift and stellar mass?
• Assessment of astronomical images using combined machine learning models
• Euclid preparation. LI. Forecasting the recovery of galaxy physical properties and their relations with template-fitting and machine-learning methods
• Inferring redshift and galaxy properties via a multi-task neural net with probabilistic outputs: An application to simulated MOONS spectra
• Bayesian decomposition of the Galactic multi-frequency sky using probabilistic autoencoders
• AGN dichotomy beyond radio loudness: a Gaussian Mixture Model analysis
• Automated quasar continuum estimation using neural networks: a comparative study of deep-learning architectures
• Euclid preparation. Estimating galaxy physical properties using CatBoost chained regressors with attention
• UV bright red-sequence galaxies: a comparative study between UV upturn and UV weak systems