量子电子学报 ›› 2022, Vol. 39 ›› Issue (5): 786-794.doi: 10.3969/j.issn.1007-5461.2022.05.012

• 量子光学 • 上一篇    下一篇

基于深度学习的量子信号大气衰减系数预测

李天秀, 石 磊∗ , 王俊辉, 李佳豪   

  1. ( 空军工程大学信息与导航学院, 陕西 西安 710077 )
  • 收稿日期:2021-03-10 修回日期:2021-04-13 出版日期:2022-09-28 发布日期:2022-09-28
  • 通讯作者: E-mail: slfly2012@163.com E-mail:E-mail: slfly2012@163.com
  • 作者简介:李天秀 ( 1997 - ), 女, 辽宁沈阳人, 研究生, 主要从事量子密钥分发方面的研究。 E-mail: 997311434@qq.com
  • 基金资助:
    Supported by National Natural Science Foundation of China (国家自然科学基金, 61971436)

Prediction of atmospheric attenuation coefficient of quantum signal based on deep learning

LI Tianxiu, SHI Lei ∗ , WANG Junhui, LI Jiahao   

  1. ( College of Information and Navigation, Air Force Engineering University, Xi’an 710077, China )
  • Received:2021-03-10 Revised:2021-04-13 Published:2022-09-28 Online:2022-09-28

摘要: 针对空间量子通信系统中大气信道环境随气象条件实时改变的特性, 提出了基于深度学习的量子信号 大气衰减系数预测方法。实验基于西安地区气象数据, 分别使用了误差反向传播神经网络 (BPNN)、长短期记 忆网络 (LSTM)、门限循环单元 (GRU) 三种神经网络模型进行数据预测, 并进行了分析比较。结果表明三种神 经网络模型均可以有效实现预测, 并能达到 80% 的数据拟合度, 其中 LSTM 和 GUR 网络的整体预测能力较强, 但三种网络模型均在峰值处产生较大误差。该预测方案为空间量子通信中各类针对大气信道的补偿手段和智 能参数优化提供了基础。

关键词: 量子光学, 空间量子通信, 深度学习, 神经网络

Abstract: To deal with the real time changing of atmospheric channel with meteorological conditions in space quantum communication system, a prediction method of atmospheric attenuation coefficient of quantum signals based on deep learning is proposed. The experiment is based on meteorological data set of Xi’an, and three neural network models, namely BPNN, LSTM and GRU, are built for analysis and comparison. The results show that all the three neural network models can accomplish prediction effectively with over 80% data fitting rate, among which LSTM and GUR have better performance. Meanwhile, three network models all produce large errors at the peak value. The prediction scheme provides a basis for further research in various compensation methods and intelligent parameter optimization for atmospheric channels in space quantum communication.

Key words: quantum optics, space quantum communication, deep learning, neural network

中图分类号: