基于高分五号卫星DPC和AERONET站点数据的地表BPDF模型对比分析

Comparative Analysis of BPDF Land Surface Models Based on DPC Measurements of Gaofen-5 Satellite and Data of AERONET Sites

大气气溶胶卫星偏振遥感探测中,地表偏振反射率估计是最重要的不确定因素之一,是气溶胶反演过程中地气解耦的重要环节。基于高分五号卫星大气气溶胶多角度偏振探测仪(DPC)近红外波段865 nm的多角度偏振观测数据,利用全球地基气溶胶监测网(AERONET)站点的气溶胶产品AOD L2.0与DPC数据进行时空匹配,筛选气溶胶光学厚度(AOD)低值数据,以减小气溶胶的影响,获取地表多角度偏振反射率数据。针对8种典型地表类型,基于DPC多角度偏振数据定量比较分析了Nadal-Bréon模型、Waquet模型、Maignan模型、Litvinov模型和Xie-Cheng模型5个半经验地表双向偏振反射分布函数(BPDF)模型的性能。研究结果表明,Litvinov模型和Nadal-Bréon模型所得的结果与实测数据可以较好地吻合,两个模型与DPC实测数据的相关性系数均值分别为0.958和0.952,均方根误差均值分别为0.202%和0.223%。研究结果为基于DPC数据估算地表偏振反射率提供了BPDF模型参考,为利用DPC多角度偏振数据反演气溶胶参数等应用提供了先验数据支持。

The polarized reflectance estimation of land surfaces is one of the most important uncertainties in the polarized remote sensing detection of atmospheric aerosol by satellites and thus becomes an important link in the land-atmosphere decoupling during aerosol inversion.The directional polarized measurements of atmospheric aerosol in the near-infrared band(865 nm)by a directional polarimetric camera(DPC)aboard the GaoFen(GF-5)satellite are spatiotemporally matched with the aerosol product AOD L2.0 of the sites of the worldwide ground-based aerosol monitoring website AERONET.Data corresponding to small aerosol optical depth(AOD)values are thereby screened out to reduce the influence of aerosol and further to obtain directional polarized reflectance data of the land surface.The performance of five semiempirical bidirectionally polarized reflectance distribution function(BPDF)models of land surfaces for eight typical land surface types is quantitatively compared using the DPC measurements.The models compared included the Nadal-Bréon model,the Waquet model,the Maignan model,the Litvinov model,and the Xie-Cheng model.The comparison shows that the results of the Litvinov and Nadal-Bréon models agree well with the DPC measurements.Specifically,the average correlation coefficients of the results of the two models with the DPC measurements reach 0.958 and 0.952,respectively,and the corresponding average root-mean-square errors(RMSEs)are 0.202%and 0.223%,respectively.The research results serve as a reference concerning BPDF models for polarized reflectance estimation of land surfaces with DPC data and provide prior data support for applications such as the inversion of aerosol parameters with DPC data.