Transferring spectroscopic stellar labels to 217 million Gaia DR3 XP stars with SHBoost
arXiv:2407.06963 · doi:10.1051/0004-6361/202451427
Abstract
In this paper, we explore the feasibility of using machine learning regression as a method of extracting basic stellar parameters and line-of-sight extinctions from spectro-photometric data. We built a stable gradient-boosted random-forest regressor (xgboost), trained on spectroscopic data, capable of producing output parameters with reliable uncertainties from Gaia DR3 data (most notably the low-resolution XP spectra), without ground-based spectroscopic observations. Using Shapley additive explanations, we interpret how the predictions for each star are influenced by each data feature. For the training and testing of the network, we used high-quality parameters obtained from the StarHorse code for a sample of around eight million stars observed by major spectroscopic stellar surveys, complemented by curated samples of hot stars, very metal-poor stars, white dwarfs, and hot sub-dwarfs. The training data cover the whole sky, all Galactic components, and almost the full magnitude range of the Gaia DR3 XP sample of more than 217 million objects that also have reported parallaxes. We have achieved median uncertainties of 0.20 mag in V-band extinction, 0.01 dex in logarithmic effective temperature, 0.20 dex in surface gravity, 0.18 dex in metallicity, and in mass (over the full Gaia DR3 XP sample, with considerable variations in precision as a function of magnitude and stellar type). We succeeded in predicting competitive results based on Gaia DR3 XP spectra compared to classical isochrone or spectral-energy distribution fitting methods we employed in earlier works, especially for parameters and , along with the metallicity values. Finally, we showcase some potential applications of this new catalogue, including extinction maps, metallicity trends in the Milky Way, and extended maps of young massive stars, metal-poor stars, and metal-rich stars). [abridged]
A&A, accepted. 13 pages, 13 figures + references & appendices. Data available at https://data.aip.de/projects/shboost2024.html
References in corpus (64)
- Array Programming with NumPy
- The Gaia mission
- The Astropy Project: Sustaining and Growing a Community-oriented Open-source Project and the Latest Major Release (v5.0) of the Core Package
- Gaia Data Release 3: Summary of the content and survey properties
- Estimating distances from parallaxes. V: Geometric and photogeometric distances to 1.47 billion stars in Gaia Early Data Release 3
- The Radial Velocity Experiment (RAVE): first data release
- The GALAH Survey: Scientific Motivation
- astroquery: An Astronomical Web-Querying Package in Python
- Painting a portrait of the Galactic disc with its stellar clusters
- Gaia-2MASS 3D maps of Galactic interstellar dust within 3 kpc
- Improving the open cluster census. II. An all-sky cluster catalogue with Gaia DR3
- A catalogue of white dwarfs in Gaia EDR3
- Dawes Review 4: Spiral Structures in Disc Galaxies
- Photo-astrometric distances, extinctions, and astrophysical parameters for Gaia EDR3 stars brighter than G=18.5
- Gaia Data Release 3: Processing and validation of BP/RP low-resolution spectral data
- Gaia Data Release 3: Analysis of the Gaia BP/RP spectra using the General Stellar Parameterizer from Photometry
- Updated Gaia-2MASS 3D maps of Galactic interstellar dust
- Gaia Data Release 3: External calibration of BP/RP low-resolution spectroscopic data
- Gaia Data Release 3: Apsis II -- Stellar Parameters
- Parameters of 220 million stars from Gaia BP/RP spectra
- Gaia Data Release 3: Mapping the asymmetric disc of the Milky Way
- Robust Data-driven Metallicities for 175 Million Stars from Gaia XP Spectra
- Galactic spiral structure revealed by Gaia EDR3
- Hunting for open clusters in \textit{Gaia} DR2: the Galactic anticentre
- Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
- The Gaia-ESO Public Spectroscopic Survey: Motivation, implementation, GIRAFFE data processing, analysis, and final data products
- Three-dimensional extinction maps: Inverting inter-calibrated extinction catalogues
- The Poor Old Heart of the Milky Way
- Four-hundred Very Metal-Poor Stars Studied with LAMOST and Subaru. II. Elemental abundances
- A classifier for spurious astrometric solutions in Gaia EDR3
- Internal calibration of Gaia BP/RP low-resolution spectra
- StarHorse results for spectroscopic surveys + Gaia DR3: Chrono-chemical populations in the solar vicinity, the genuine thick disk, and young-alpha rich stars
- On the Milky Way spiral arms from open clusters in Gaia EDR3
- Stellar labels for hot stars from low-resolution spectra - I. the HotPayne method and results for 330,000 stars from LAMOST DR6
- The Pristine Inner Galaxy Survey (PIGS) I: Tracing the kinematics of metal-poor stars in the Galactic bulge
- Quantifying stellar radial migration in an N-body simulation: blurring, churning, and the outer regions of galaxy discs
- Cloud and Star Formation in Disk Galaxy Models with Feedback
- The population of hot subdwarf stars studied with Gaia -- IV. Catalogues of hot subluminous stars based on Gaia EDR3
- Survey of Surveys I: The largest catalogue of radial velocities for the Galaxy
- Assessment of [Fe/H] determinations for FGK stars in spectroscopic surveys
- The Alma catalog of OB stars. II. A cross-match with Gaia DR2 and an updated map of the solar neighbourhood
- Spectroscopic age estimates for APOGEE red-giant stars: Precise spatial and kinematic trends with age in the Galactic disc
- Mapping Luminous Hot Stars in the Galaxy
- The Pristine survey III: Spectroscopic confirmation of an efficient search for extremely metal-poor stars
- The Pristine Inner Galaxy Survey (PIGS) II: Uncovering the most metal-poor populations in the inner Milky Way
- Chemo-kinematics of the Milky Way spiral arms and bar resonances: connection to ridges and moving groups in the Solar vicinity
- Stellar Metallicities from SkyMapper Photometry II: Precise photometric metallicities of 280,000 giant stars with [Fe/H] in the Milky Way
- Photometric redshift-aided classification using ensemble learning
- High resolution spectroscopic follow-up of the most metal-poor candidates from SkyMapper DR1.1
- Discovery of the local counterpart of disc galaxies at z > 4: The oldest thin disc of the Milky Way using Gaia-RVS
- Carbon-Enhanced Metal-Poor star candidates from BP/RP Spectra in DR3
- Identification of BASS DR3 Sources as Stars, Galaxies and Quasars by XGBoost
- Information content of BP/RP spectra in Gaia DR3
- A LAMOST BHB Catalog and Kinematics Therein I: Catalog and Halo Properties
- Analysing spectral lines in Gaia low-resolution spectra
- Identification, mass and age of primary red clump stars from spectral features derived with the LAMOST DR7
- The Gaia-ESO Survey: Chemical evolution of Mg and Al in the Milky Way with Machine-Learning
- Estimating from Gaia low-resolution BP/RP spectra using the ExtraTrees algorithm
- Random Forest classification of Gaia DR3 white dwarf-main sequence spectra: a feasibility study
- Exploring the structure and kinematics of the Milky Way through A stars
- Classification of the \emph{Fermi}-LAT Blazar Candidates of Uncertain type using eXtreme Gradient Boosting
- SpectroTranslator: a deep-neural network algorithm to homogenize spectroscopic parameters
- A machine learning approach to photometric metallicities of giant stars
- A method for identifying metal-poor stars with Gaia BP/RP spectra
Cited by in corpus (11)
- Kepler meets Gaia DR3: homogeneous extinction-corrected color-magnitude diagram and binary classification
- The Alma catalogue of OB stars. III. A cross-match with Gaia DR3 and an extension based on new spectral classifications
- Metallicities of old open clusters: A new Galactic map
- Stellar masses and mass ratios for Gaia open cluster members
- Asteroseismology of four eccentric double-lined spectroscopic eclipsing binaries
- Stellar age determination using deep neural networks: Isochrone ages for 1.3 million stars, based on BaSTI, MIST, PARSEC, Dartmouth and SYCLIST evolutionary grids
- Modelling the Milky Way's exoplanet population based on cosmological galaxy simulations
- Mapping the Milky Way with Gaia Bp/Rp spectra-IV: the broken and asymmetric density profile of the stellar disk traced by a large sample of red clumps
- The Stellar Abundances and Galactic Evolution Survey (SAGES). IV. Surface Gravity Estimation and Giant-Dwarf Separation with the DDO51 Filter
- The impact of stellar rotations and binaries on the shape of upper main sequence near turn off in open cluster NGC\,6067
- Light Curve Analysis Of W-uma Type Binary Systems Rz Umi, Oq Uma, Lp Uma