基于光变曲线的空间碎片基本形状分类
作者:
作者单位:

1.中国科学院紫金山天文台南京210023;2.中国科学院空间目标与碎片观测重点实验室南京210023;3.中国科学院大学北京100049)

作者简介:

通讯作者:

中图分类号:

P128;

基金项目:

国家自然科学基金项目(11533010)资助


The Basic Shape Classification of Space Debris with Light Curves
Author:
Affiliation:

1. Purple Mountain Observatory, Chinese Academy of Sciences, Nanjing 210023;2. Key Laboratory for Space Object and Debris Observation, Chinese Academy of Sciences, Nanjing 210023;3. University of Chinese Academy of Sciences, Beijing 100049;

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    将未编目的空间碎片正确分类是空间态势感知的重要组成部分. 基于光变曲线, 通过仿真和实测实验, 探讨了空间碎片基本类型的机器学习分类方法. 在数据集中的仿真光变来自形状或材料不同的4类碎片, 实测光变从Mini-Mega TORTORA (MMT)数据库中提取, 实验以深度神经网络作为分类模型, 并和其他机器学习方法进行了比较. 结果显示深度卷积网络优于其他算法, 在仿真实验中对不同材料的圆柱体都能准确识别, 对其余两类卫星的识别率在90%左右; 实测实验中对火箭体和失效卫星的2分类准确率超过99%, 然而在进一步的型号/平台分类中, 准确率有所降低.

    Abstract:

    We study the machine learning method for classifying the basic shape of space debris in both simulated and observed data experiments, where light curves are used as the input features. In the dataset for training and testing, simulated light curves are derived from four types of debris within different shapes and materials. Observed light curves are extracted from Mini-Mega TORTORA (MMT) database which is a publicly accessible source of space object photometric records. The experiments employ the deep convolutional neural network, make comparisons with other machine learning algorithms, and the results show CNN (Convolutional Neural Network) is better. In simulational experiments, both types of cylinder can be distinguished perfectly, and two other types of satellite have around 90% probability to be classified. Rockets and disabled satellites can achieve 99% success rate in binary classification, but in further sub-classes classifications, the rate becomes relatively lower.

    参考文献
    相似文献
    引证文献
引用本文

鹿瑶,赵长印.基于光变曲线的空间碎片基本形状分类[J].天文学报,2020,(6):50-63.

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2020-03-27
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2020-12-04
  • 出版日期: