# Recognition of M-type stars in the unclassified spectra of LAMOST DR5 using a hash learning method

## TL;DR

This paper introduces a hash learning method based on ML-PIL to identify M-type stars in low-quality spectra from LAMOST DR5, significantly improving recognition of these stars among unclassified spectra.

## Contribution

The study develops a novel binary nonlinear hashing algorithm using ML-PIL for effective spectral feature learning, enabling accurate detection of M-type stars in noisy spectra.

## Key findings

- Identified 11,410 M-type spectra from 642,178 unknown spectra.
- Provided a supplemental catalog of M-type stars for public release.
- Validated star classification with Gaia DR2 data and analyzed stellar properties.

## Abstract

Our study aims to recognize M-type stars which are classified as "UNKNOWN" due to bad quality in Large sky Area Multi-Object fibre Spectroscopic Telescope (LAMOST) DR5 V1. A binary nonlinear hashing algorithm based on Multi-Layer Pseudo Inverse Learning (ML-PIL) is proposed to effectively learn spectral features for the M-type star detection, which can overcome the bad fitting problem of template matching, particularly for low S/N spectra. The key steps and the performance of the search scheme are presented. A positive dataset is obtained by clustering the existing M-type spectra to train the ML-PIL networks. By employing this new method, we find 11,410 M-type spectra out of 642,178 "UNKNOWN" spectra, and provide a supplemental catalogue. Both the supplemental objects and released M-type stars in DR5 V1 are composed a whole M type sample, which will be released in the official DR5 to the public in June 2019, All the M-type stars in the dataset are classified to giants and dwarfs by two suggested separators: 1) color diagram of H versus J~K from 2MASS; 2) line indices CaOH versus CaH1, and the separation is validated with HRD derived from Gaia DR2. The magnetic activities and kinematics of M dwarfs are also provided with the EW of H_alpha emission line and the astrometric data from Gaia DR2 respectively.