An application of deep learning in the analysis of stellar spectra
| Autor: | Collin Kielty, Stephanie Monty, Spencer Bialek, Teaghan O'Briain, Farbod Jahandar, K. A. Venn, S. Fabbro |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Physics
Accuracy and precision 010504 meteorology & atmospheric sciences business.industry Pipeline (computing) Metallicity Deep learning Astrophysics::Instrumentation and Methods for Astrophysics Astronomy and Astrophysics 01 natural sciences Convolutional neural network Astronomical spectroscopy Synthetic data Space and Planetary Science 0103 physical sciences Range (statistics) Artificial intelligence business 010303 astronomy & astrophysics Astrophysics::Galaxy Astrophysics 0105 earth and related environmental sciences Remote sensing |
| Zdroj: | Monthly Notices of the Royal Astronomical Society. 475:2978-2993 |
| ISSN: | 1365-2966 0035-8711 |
| DOI: | 10.1093/mnras/stx3298 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|