O-type Stars Stellar Parameter Estimation Using Recurrent Neural Networks
This work addresses stellar parameter estimation for astronomers, but it is incremental as it builds on prior machine learning comparisons by focusing on recurrent neural networks and low-S/N data.
The paper tackles the problem of estimating luminosity, effective temperature, and surface gravity for O-type stars from optical spectra, achieving results by testing recurrent neural networks on stellar spectra with low signal-to-noise ratios below 20 S/N.
In this paper, we present a deep learning system approach to estimating luminosity, effective temperature, and surface gravity of O-type stars using the optical region of the stellar spectra. In previous work, we compare a set of machine learning and deep learning algorithms in order to establish a reliable way to fit a stellar model using two methods: the classification of the stellar spectra models and the estimation of the physical parameters in a regression-type task. Here we present the process to estimate individual physical parameters from an artificial neural network perspective with the capacity to handle stellar spectra with a low signal-to-noise ratio (S/N), in the $<$20 S/N boundaries. The development of three different recurrent neural network systems, the training process using stellar spectra models, the test over nine different observed stellar spectra, and the comparison with estimations in previous works are presented. Additionally, characterization methods for stellar spectra in order to reduce the dimensionality of the input data for the system and optimize the computational resources are discussed.