Taxonomic analysis of asteroids with artificial neural networks

We study the surface composition of asteroids with visible and/or infrared spectroscopy. For example, asteroid taxonomy is based on the spectral features or multiple color indices in visible and near-infrared wavelengths. The composition of asteroids gives key information to understand their origin and evolution. However, we lack compositional information for faint asteroids due to limits of ground-based observational instruments. In the near future, the Chinese Space Survey telescope (CSST) will provide multiple colors and spectroscopic data for asteroids of apparent magnitude brighter than 25 mag and 23 mag, respectively. For the aim of analysis of the CSST spectroscopic data, we applied an algorithm using artificial neural networks (ANNs) to establish a preliminary classification model for asteroid taxonomy according to the design of the survey module of CSST. Using the SMASS II spectra and the Bus-Binzel taxonomy system, our ANN classification tool composed of 5 individual ANNs is constructed, and the accuracy of this classification system is higher than 92 %. As the first application of our ANN tool, 64 spectra of 42 asteroids obtained in 2006 and 2007 by us with the 2.16-m telescope in the Xinglong station (Observatory Code 327) of National Astronomical Observatory of China are analyzed. The predicted labels of these spectra using our ANN tool are found to be reasonable when compared to their known taxonomic labels. Considering the accuracy and stability, our ANN tool can be applied to analyse the CSST asteroid spectra in the future.

Investigation of stellar magnetic activity using variational autoencoder based on low-resolution spectroscopic survey

We apply the variational autoencoder (VAE) to the LAMOST-K2 low-resolution spectra to detect the magnetic activity of the stars in the K2 field. After the training on the spectra of the selected inactive stars, the VAE model can efficiently generate the synthetic reference templates needed by the spectral subtraction procedure, without knowing any stellar parameters. Then we detect the peculiar spectral features, such as chromospheric emissions, strong nebular emissions and lithium absorptions, in our sample. We measure the emissions of the chromospheric activity indicators, H$\alpha$ and Ca$~{\rm {\small II}}$ infrared triplet (IRT) lines, to quantify the stellar magnetic activity. The excess emissions of H$\alpha$ and Ca$~{\rm {\small II}}$ IRT lines of the active stars are correlated well to the rotational periods and the amplitudes of light curves derived from the K2 photometry. We degrade the LAMOST spectra to simulate the slitless spectra of the planned China Space Station Telescope (CSST) and apply the VAE to the simulated data. For cool active stars, we reveal a good agreement between the equivalent widths (EWs) of H$\alpha$ line derived from the spectra with two resolutions. The result indicates the ability of identifying the magnetically active stars in the future CSST survey, which will deliver an unprecedented large database of low-resolution spectra as well as simultaneous multi-band photometry of stars.