Random Forest classification of Gaia DR3 white dwarf-main sequence spectra: A feasibility study

Abstract

Aims. The third Gaia data release provides low-resolution spectra for around 200 million sources. It is expected that a sizeable fraction of them contain a white dwarf (WD), neither isolated, or in a binary system with a main-sequence (MS) companion, that is a white dwarf-main sequence (WDMS) binary. Taking advantage of a consolidated Random Forest algorithm used in the classification of WDs, we extend it to study the feasibility of classifying Gaia WDMS binary spectra. Methods. The Random Forest algorithm is first trained with a set of synthetic spectra generated by combining individual WD and MS spectra for the full range of effective temperatures and surface gravities. Moreover, with the aid of a detailed population synthesis code, we simulate the Gaia spectra for the abovementioned populations. For evaluating the performance of the models, a set of metrics are applied to our classifications. Results. Our results show that for resolving powers above ~300 the accuracy of the classification depends exclusively on the S/R of the spectra, while below that value the S/R should be increased as the resolving power is reduced to maintain a certain accuracy. The algorithm is then applied to the already classified SDSS WDMS catalog, revealing that the automated classification exhibits an accuracy comparable (or even higher) to previous classification methods. Finally, we simulate the Gaia spectra, showing that our algorithm is able to correctly classify nearly 80% the synthetic WDMS spectra. Conclusions. Our algorithm represents a useful tool in the analysis and classification of real Gaia WDMS spectra. Even for those spectra dominated by the flux of the MS stars, the algorithm reaches a high degree of accuracy (60%).