The Use of Conditional Variational Autoencoders in Generating Stellar Spectra

We present a conditional variational autoencoder (CVAE) that generates stellar spectra covering 4000 ≤ Teff ≤ 11,000 K, 2.0≤logg≤5.0 dex, −1.5≤[M/H]≤+1.5 dex, vsini≤300 km/s, ξt between 0 and 4 km/s, and for any instrumental resolving powers less than 115,000. The spectra can be calculated in the wavelength range 4450–5400 Å. Trained on a grid of SYNSPEC spectra, the network synthesizes a spectrum in around two orders of magnitude faster than line-by-line radiative transfer. We validate the CVAE on 104 test spectra unseen during training. Pixel-wise statistics yield a median absolute residual of <1.8×10−3 flux units with no wavelength-dependent bias. A residual error map across the parameters plane shows ⟨|ΔF|⟩<2×10−3 everywhere, and marginal diagnostics versus Teff, logg, vesini, ξt, and [M/H] reveal no relevant trends. These results demonstrate that the CVAE can serve as a drop-in, physics-aware surrogate for radiative transfer codes, enabling real-time forward modeling in stellar parameter inference and offering promising tools for spectra synthesis for large astrophysical data analysis.