基于深度神经网络的海表盐度反演  

Sea Surface Salinity Inversion Based on DNN Model

作　　者：高明 黄贤源 王芳[1] 张海龙 赵红霞[1] 高溪远 GAO Ming;HUANG Xian-yuan;WANG Fang;ZHANG Hai-long;ZHAO Hong-xia;GAO Xi-yuan(Combat Service Support Brigade of the Chinese People’s Armed Police Force,Beijing 100081,China;Unit 92859 of the PLA,Tianjin 300000,China)

机构地区：[1]中国人民武装警察部队作战勤务保障大队,北京100081 [2]中国人民解放军部队92859部队,天津300000

出　　处：《海洋科学进展》2022年第3期496-504,共9页Advances in Marine Science

摘　　要：海表盐度(Sea Surface Salinity,SSS)是研究海洋对全球气候影响的重要参量,欧洲航天局(European Space Agency,ESA)设计研发的SMOS(Soil Moisture and Ocean Salinity)是专用于探测海水盐度的卫星之一。受射频干扰(Radio Frequency Interference,RFI)等因素的影响,SMOS卫星盐度产品的精度难以达到预期效果。为了提高SMOS卫星海表盐度产品精度,本文提出一种基于深度神经网络的海表盐度反演算法。以太平洋中部海域(150°E~180°,5°~30°N)为研究区域,利用Argo浮标实测盐度数据为参考真值,将SMOS卫星L1C、L2级产品与Argo盐度数据进行时空匹配。并根据海洋遥感和辐射传输理论,选取亮温(Brightness Temperature,TB)、海表温度(Sea Surface Temperature,SST)、降雨率(Rain Rate,RR)、波高(Significant Wave Height,SWH)、纬向风速(Zonal Wind Speed,ZWS)、经向风速(Meridional Wind Speed,MWS)和蒸发量(Evaporation,Eva)七个影响盐度的重要参数,利用K折交叉验证法,构建了深度神经网络(Deep Neural Network,DNN)模型,对SMOS卫星L2级数据进行反演。实验结果表明,利用本文算法计算得到的海表盐度数据平均绝对误差为0.159,均方根误差为0.195,均明显优于SMOS盐度产品精度,本文提出的算法能够提供更精准的海表盐度产品。Sea Surface Salinity is an important parameter to learn oceans’impact on the global climate.SMOS(Soil Moisture and Ocean Salinity)developed by the European Space Agency is one of the satellites dedicated to measuring ocean salinity.However,due to influences like Radio Frequency Interference(RFI),the accuracy of SMOS salinity products hardly achieve the expected results.In order to improve the accuracy of the sea surface salinity products,a deep neural network based sea surface salinity retrieval algorithm is proposed in this paper.The experiment takes the central Pacific Ocean(150°E-180°,5°-30°N)as the research area,using the Argo measured salinity data as the reference.First,SMOS L1C and L2 level products are matched in time and space with the Argo salinity data.Then,according to the ocean remote sensing and radiative transfer theory,seven parameters that affect ocean salinity are selected,including Brightness Temperature(TB),Sea Surface Temperature(SST),Rainfall Rate(RR),Significant Wave Height(SWH),Zonal Wind Speed(ZWS),Meridional Wind Speed(MWS)and Evaporation(Eva).The DNN(Deep Neural Network)is developed and optimized with the K-fold cross-validation method.And the sea surface salinity data is retrieved using Argo salinity as the ground-truth.The experiments show that the mean absolute error of the sea surface salinity data obtained by the algorithm proposed in this paper is 0.159,and the root mean square error is 0.195,which are better than the accuracy of SMOS salinity products.

关 键 词：SMOS卫星 海表盐度反演 深度神经网络 

分 类 号：P731.12[天文地球—海洋科学]