arXiv2026
The importance of massive stars cannot be overstated: they are powerful probes of the early universe, play a vital role in the chemical and mechanical evolution of their host environments and their end products allow us to study the most extreme physics in the universe. Obtaining accurate stellar and surface parameters for large samples of massive stars is vital to our understanding of how they evolve, and how their births, lives and deaths affect their surroundings. With the large volume of data expected from upcoming spectroscopic surveys, computational limitations will likely be the most important bottleneck impeding our progress. To address this and dramatically decrease computing times, we aim to develop a robust emulator for the FASTWIND radiative transfer and spectral synthesis code. Additionally, we aim to explore alternative fitting methods that have not been feasible until now due to computational costs. We calculate a set of FASTWIND synthetic spectra of OB-type stars, and we train a collection of neural networks to emulate these models. We also develop the open-source python package SpecFANN, which provides users with a suite of fitting methods that can be used with these or other user-generated neural networks. The majority of the trained neural networks reach average accuracies of better than ~0.01-0.1% for photospheric lines and better than ~0.1-1% for wind lines. SpecFANN is able to obtain robust and accurate stellar parameters that are consistent with the literature for a sample of 52 early-type stars. Using SpecFANN we find that we can achieve the same fit in ~1/360,000 of the time when compared to alternative techniques that rely on on-the-fly FASTWIND computations. We have demonstrated that neural networks offer a viable path forward to address the computational limitations of our current atmosphere analysis and stellar parameter determination methods for hot stars.