PHAS Colloquia

Conditional Variational AutoEncoders in stellar Spectroscopy

by Prof. Marwan Gebran (Saint Mary’s College)

America/Chicago
12Marwan GebranMarwan GebranMarwan GebranMarwan GebranMaMarsfdd (ESB1)

12Marwan GebranMarwan GebranMarwan GebranMarwan GebranMaMarsfdd

ESB1

Description

I will be introducing a spectra generation tool based on Conditional Variational AutoEncoders. The model is trained on a grid of SYNSPEC spectra and ATLAS model atmospheres. The network is capable of synthesizing a spectrum in any spectra range and around two orders of magnitude faster than line-by-line radiative transfer. 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.