基于人工神经网络的近地面光学湍流估算  

Estimation of Surface Layer Optical Turbulence Using Artificial Neural Network

作　　者：陈小威 朱文越[1,2] 钱仙妹 罗涛[1,2] 孙刚 刘庆 李学彬 翁宁泉 Chen Xiaowei;Zhu Wenyue;Qian Xianmei;Luo Tao;Sun Gang;Liu Qing;Li Xuebin;Weng Ningquan(Key Laboratory of Atmospheric Optics,Anhui Institute of Optics and Fine Mechanics,Hefei Institutes of Physical Science,Chinese Academy of Sciences,Hefei,Anhui 230031,China;Anhui Laboratory of Advanced Laser Technology,Hefei,Anhui 230037,China)

机构地区：[1]中国科学院合肥物质科学研究院安徽光学精密机械研究所大气光学重点实验室,安徽合肥230031 [2]先进激光技术安徽省实验室,安徽合肥230037

出　　处：《光学学报》2020年第24期9-15,共7页Acta Optica Sinica

基　　金：科工局国防基础科研计划;先进激光技术安徽省实验室主任基金(20191002);脉冲功率激光技术国家重点实验室主任基金(SKL2020ZR08);中国科学院科技创新重点实验室基金(CXJJ-19S028)。

摘　　要：通过构建人工神经网络模型估算中国西北高原地区近地面光学湍流。对多层感知器(MLP)的结构进行优化,其输入层包括10个特征,隐含层包括40个神经元。探讨已建多层感知器的性能,结果表明:当训练集和测试集来自同一地区时,模型的平均相对误差为1.34%,折射率结构常数的实测值和估计值的拟合优度为0.94;当训练集和测试集来自不同地区时,多层感知器的泛化能力需进一步提高。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.

关 键 词：大气光学 光学湍流 多层感知器 估计精度 

分 类 号：P427.1[天文地球—大气科学及气象学]