Spectra Recognition Model for O-type Stars Based on Data Augmentation

It is a problematic issue in astronomy to recognize and classify O-type spectra comprehensively. The neural network is a popular recognition model based on data-driven. The number of O-stars collected in LAMOST is less than 1% of AFGK stars, and there are only 127 O-type data in the data release seven version. Therefore, there are not enough O-type samples available for recognition models. As a result, the existing neural network models are not effective in identifying such rare stars spectra. This paper proposed a novel spectra recognition model (called LCGAN model) to solve this problem with data augmentation, which is based on Locally Connected Generative Adversarial Network (LCGAN) . The LCGAN introduced the locally connected convolution and two timescale update rule to generate O-type stars' spectra. In addition, LCGAN model adopted residual and attention mechanisms to recognize O-type spectra. To evaluate the performance of proposed models, we conducted a comparative experiment using a stellar spectral data set, which consists of more than 40000 spectra, collected by the large sky area multi-object fiber spectroscopic telescope (LAMOST). The experimental results showed that the LCGAN model could generate meaningful generated O-type spectra. In our validation data set, the recognition accuracy of the data enhanced recognition model can reach 93.67%, 8.66% higher than that of the non data enhanced identification model, which lays a good foundation for further analysis of astronomical spectra.