A method and system for identifying emission line stars based on LAMOST spectral data
CN120045996BActive Publication Date: 2026-03-03GUANGZHOU UNIVERSITY
-1 Cites -1 Cited by
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-22
- Publication Date
- 2026-03-03
Smart Images

Figure CN120045996B_ABST
Abstract
The application discloses a kind of based on LAMOST spectral data's emission line star identification method and system, the method includes: constructing LAMOST Dr9 in resolution spectral data and carrying out data preprocessing, obtain spectral data feature matrix;Based on deep residual network, shortcut residual path is introduced, and Hα-ResNet model is constructed;Hα-ResNet model is trained to two categories, and the two classification Hα-ResNet model after training is constructed and is identified to two categories, obtain emission line star sample data;Hα-ResNet model is trained to six categories after based on emission line star sample data pre-processing, and the six classification Hα-ResNet model after training is constructed and is identified to six categories, obtain emission line star identification result.The application can classify multiple emission line stars and improve the classification and identification accuracy of spectral data.The application is a kind of based on LAMOST spectral data's emission line star identification method and system, can be widely applied in astronomical data processing technical field.
Need to check novelty before this filing date? Find Prior Art