Main > Acta Optica Sinica >  Volume 40 >  Issue 24 >  Page 2401002 > Article
  • Abstract
  • Abstract
  • View Summary
  • Figures (8)
  • Tables (0)
  • Equations (0)
  • References (21)
  • Get PDF(in Chinese)
  • Paper Information
  • Received: Aug. 3, 2020

    Accepted: Sep. 19, 2020

    Posted: Dec. 1, 2020

    Published Online: Nov. 23, 2020

    The Author Email: Zhu Wenyue (zhuwenyue@aiofm.ac.cn), Qian Xianmei (qianxianmei@aiofm.ac.cn)

    DOI: 10.3788/AOS202040.2401002

  • Get Citation
  • Copy Citation Text

    Xiaowei Chen, Wenyue Zhu, Xianmei Qian, Tao Luo, Gang Sun, Qing Liu, Xuebin Li, Ningquan Weng. Estimation of Surface Layer Optical Turbulence Using Artificial Neural Network[J]. Acta Optica Sinica, 2020, 40(24): 2401002

    Download Citation

  • Category
  • Atmospheric Optics and Oceanic Optics
  • Share
Acta Optica Sinica, Vol. 40, Issue 24, 2401002 (2020)

Estimation of Surface Layer Optical Turbulence Using Artificial Neural Network

Chen Xiaowei1,2, Zhu Wenyue1,2,*, Qian Xianmei1,2,**, Luo Tao1,2, Sun Gang1,2, Liu Qing1,2, Li Xuebin1,2, and Weng Ningquan1,2

Author Affiliations

  • 1Key Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics,Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, Anhui 230031, China
  • 2Anhui Laboratory of Advanced Laser Technology, Hefei, Anhui 230037, China

Abstract

This paper presents an estimate of surface layer optical turbulence in Northwest China using an artificial neural network. We optimize the configuration of the multilayer perceptron (MLP), including 10 features in the input layer and 40 neurons in the hidden layer. The performance of the constructed MLP is investigated. The results show that when the training set and testing set are from the same site, the mean relative error of the model is 1.34%. The goodness of fit between measured and estimated refractive index structure constants is 0.94. We propose that when the training set and testing set come from different sites, the generalization ability of the MLP should be enhanced.

keywords

Please Enter Your Email: