Predicted spectral type of white dwarf

Magnetic white dwarfs were identified via Zeeman splitting, and first-order magnetic field strengths were estimated when possible. Machine-learning classifications are highly accurate (>90% for spectral types included in their training sets), despite the low resolution of Gaia spectra. We determine the true nature of objects classified as "massive DBs" to be largely composed of magnetic white dwarfs and warm DQs, with only 5 of 112 observed objects (4.46%) confirmed as genuine DBs.

Warm DQs are found along the Gaia Q branch and exhibit unusually high tangential velocities. We provide spectral classifications for 255 white dwarfs and demonstrate that Random Forest algorithms reliably classify low-resolution Gaia spectra for the main spectral types. We also determine the nature of objects classified as "massive DBs" and identify a large population of magnetic white dwarfs and carbon-rich objects.

Several rare subtypes are identified, including 2 DAB, 1 DBAZ, 1 DZAB, 2 DZBA, 14 DAH, 1 DAQ, 1 DQZA, 4 hot and 29 warm DQ stars, along with 63 magnetic white dwarfs. The location and kinematics of warm DQs are consistent with previous studies, supporting their proposed origin as merger remnants.