.png){kind=icon}
.png){kind=icon}
Return
A New Hybrid Machine Learning Method for Stellar Parameter Inference
.png){kind=icon}
OA
AI
DOI：10.3847/1538-4357/adcb47.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The advent of machine learning (ML) is revolutionary to numerous scientific disciplines, with a growing number of examples in astronomical spectroscopic inference, as ML is more powerful than traditional techniques. Here we introduce a hybrid ML (HML) method combining automatic differentiation, interpolation, and Bayesian optimization to infer stellar parameters of stellar spectra. We study T-eff, log(g), and [Fe/H], but this method could be extended to other parameters such as [alpha/Fe] (alpha element abundance), C/O (carbon-oxygen ratio), and f(sed) (sedimentation efficiency). We first use blase to semiempirically recast spectra into sets of Voigt profiles. blase is run on 1314 synthetic spectra from a rectilinear subset of the PHOENIX model grid (T-eff: [2300, 12,000] K, log(g): [2, 6], [Fe/H]: [-0.5, 0], lambda: [8038, 12849] & Aring;). For 128,723 detected features, we map stellar parameters to spectral line parameters using linear interpolation. This creates the PHOENIX generator, enabling parallelized spectral synthesis. Gaussian process minimization is used to infer stellar parameters by minimizing a rms loss function. Testing 210 noise-free models (T-eff: [3000, 11,000] K, log(g): [2, 6], [Fe/H]: [-0.5, 0]), we find inference errors: T-eff: 93 K, log(g): 0.24, and [Fe/H]: 0.056 for T-eff < 7000 K, and T-eff: 347 K, log(g): 0.26, and [Fe/H]: 0.16 for T-eff >= 7000 K. We also upload online an archive of blase models of the PHOENIX subset. This proof-of-concept study shows that semiempirical HML is a viable alternative to traditional approaches in spectroscopic inference.
Keywords:
CHEMICAL DISEQUILIBRIUM
DATA-DRIVEN
ATMOSPHERE
EVOLUTION
ASTROPY
METALLICITY
LIBRARY
PACKAGE
PROJECT
MODELS