An Application of Deep Neural Networks in the Analysis of Stellar Spectra

TL;DR

This paper demonstrates that a deep neural network, StarNet, can accurately determine stellar parameters from spectroscopic data, matching traditional methods' precision and extending applicability to synthetic spectra and other surveys.

Contribution

Introduction of StarNet, a deep neural network that efficiently analyzes stellar spectra and predicts stellar parameters with high accuracy, comparable to established pipelines.

Findings

StarNet achieves similar precision to APOGEE pipeline.

StarNet performs well on synthetic and real spectra across various S/N ratios.

Statistical uncertainties are comparable to independent optical spectrum analyses.

Abstract

Spectroscopic surveys require fast and efficient analysis methods to maximize their scientific impact. Here we apply a deep neural network architecture to analyze both SDSS-III APOGEE DR13 and synthetic stellar spectra. When our convolutional neural network model (StarNet) is trained on APOGEE spectra, we show that the stellar parameters (temperature, gravity, and metallicity) are determined with similar precision and accuracy as the APOGEE pipeline. StarNet can also predict stellar parameters when trained on synthetic data, with excellent precision and accuracy for both APOGEE data and synthetic data, over a wide range of signal-to-noise ratios. In addition, the statistical uncertainties in the stellar parameter determinations are comparable to the differences between the APOGEE pipeline results and those determined independently from optical spectra. We compare StarNet to other data-driven methods; for example, StarNet and the Cannon 2 show similar behaviour when trained with the same datasets, however StarNet performs poorly on small training sets like those used by the original Cannon. The influence of the spectral features on the stellar parameters is examined via partial derivatives of the StarNet model results with respect to the input spectra. While StarNet was developed using the APOGEE observed spectra and corresponding ASSET synthetic data, we suggest that this technique is applicable to other wavelength ranges and other spectral surveys.