White dwarf Random Forest classification through Gaia spectral coefficients

Abstract

The third data release of Gaia has provided approximately 220 million low resolution spectra. Among these, about 100,000 correspond to white dwarfs. The magnitude of this quantity of data precludes the possibility of performing spectral analysis and type determination by human inspection. In order to tackle this issue, we explore the possibility of utilising a machine learning approach, based on a Random Forest algorithm. We aim to analyze the viability of the Random Forest algorithm for the spectral classification of the white dwarf population within 100 pc from the Sun, based on the Hermite coefficients of Gaia spectra. We utilized the assigned spectral type from the Montreal White Dwarf Database for training and testing our Random Forest algorithm. Once validated, our algorithm model is applied to the rest of unclassified white dwarfs within 100 pc. First, we started by classifying the two major spectral type groups of white dwarfs: hydrogen-rich (DA) and hydrogen-deficient (non-DA). Next, we explored the possibility of classifying the various spectral subtypes, including in some cases the secondary spectral types. Our Random Forest classification presented a very high recall (>80%) for DA and DB white dwarfs, and a very high precision (>90%) for DB, DQ and DZ white dwarfs. As a result we have assigned a spectral type to 9,446 previously unclassified white dwarfs: 4,739 DAs, 76 DBs (60 of them DBAs), 4,437 DCs, 132 DZs and 62 DQs (9 of them DQpec). Despite the low resolution of Gaia spectra, the Random Forest algorithm applied to the Gaia spectral coefficients proves to be a highly valuable tool for spectral classification.

arXiv comment15 pages, 17 figures, 3 tables. Submitted to Astronomy & Astrophysics

References in corpus (32)

• Gaia Data Release 3: Summary of the content and survey properties
• VOSA: Virtual Observatory SED Analyzer. An application to the Collinder 69 open cluster
• Evolutionary and pulsational properties of white dwarf stars
• Gaia Early Data Release 3: The Gaia Catalogue of Nearby Stars
• The Chemical Composition of an Extrasolar Minor Planet
• A catalogue of white dwarfs in Gaia EDR3
• Gaia Data Release 3: Processing and validation of BP/RP low-resolution spectral data
• Gaia Data Release 3: External calibration of BP/RP low-resolution spectroscopic data
• Random forest automated supervised classification of Hipparcos periodic variable stars
• Core crystallization and pile-up in the cooling sequence of evolving white dwarfs
• The 100 pc White Dwarf Sample in the SDSS Footprint
• A cooling anomaly of high-mass white dwarfs
• $Gaia$ white dwarfs within 40 pc II: the volume-limited northern hemisphere sample
• Internal calibration of Gaia BP/RP low-resolution spectra
• A New Generation of Cool White Dwarf Atmosphere Models. IV. Revisiting the Spectral Evolution of Cool White Dwarfs
• $\text{Gaia}$ white dwarfs within 40 pc I: spectroscopic observations of new candidates
• Spectral classification of the 100 pc white dwarf population from Gaia-DR3 and the Virtual Observatory
• $\text{Gaia}$ white dwarfs within 40 pc III: spectroscopic observations of new candidates in the southern hemisphere
• From Hydrogen to Helium: The Spectral Evolution of White Dwarfs as Evidence for Convective Mixing
• Random Forest identification of the thin disk, thick disk and halo Gaia-DR2 white dwarf population
• Stellar Spectra Classification and Feature evaluation Based on Random Forest
• White dwarfs as Physics laboratories: lights and shadows
• Neural Network identification of halo white dwarfs
• The evolution of carbon-polluted white dwarfs at low effective temperatures
• A hidden population of white dwarfs with atmospheric carbon traces in the Gaia bifurcation
• Carbon dredge-up required to explain the Gaia white dwarf colour-magnitude bifurcation
• White dwarf spectral type-temperature distribution from Gaia-DR3 and the Virtual Observatory
• Data-Driven Selection and Spectral Classification of White Dwarf Stars
• Spectral feature extraction for DB white dwarfs through machine learning applied to new discoveries in the SDSS DR12 and DR14
• Analysing spectral lines in Gaia low-resolution spectra
• Random Forest Classification of Stars in the Galactic Centre
• Random Forest classification of Gaia DR3 white dwarf-main sequence spectra: a feasibility study

Cited by in corpus (8)

• The spectral evolution of white dwarfs: where do we stand?
• A Random Forest spectral classification of the Gaia 500-pc white dwarf population
• Identifying new high-confidence polluted white dwarf candidates using Gaia XP spectra and Self-Organizing Maps
• J-PLUS: The fraction of calcium white dwarfs along the cooling sequence
• PhotoD with LSST: Stellar Photometric Distances Out to the Edge of the Galaxy
• White Dwarf Stars in the Big Data Era
• Revisiting the Galactic age-metallicity relation from wide white dwarf-main-sequence binaries
• J-PLUS: Understanding outlier white dwarfs in the third data release via dimensionality reduction