随机森林反演卫星遥感海表面盐度研究  

Satellite Sea Surface Salinity Retrieval Using Random Forest Model

作　　者：柳青青 孟朔羽 徐茗 李洪平[1] 刘海行 LIU Qingqing;MENG Shuoyu;XU Ming;LI Hongping;LIU Haixing(College of Information Science and Engineering,Ocean University of China,Qingdao 266100,China;College of Business,Qingdao University,Qingdao 266100,China;First Institution of Oceanography,MNR,Qingdao 266061,China)

机构地区：[1]中国海洋大学信息科学与工程学部,山东青岛266100 [2]青岛大学商学院,山东青岛266100 [3]自然资源部第一海洋研究所,山东青岛266061

出　　处：《武汉大学学报（信息科学版）》2023年第9期1538-1545,共8页Geomatics and Information Science of Wuhan University

基　　金：国家自然科学基金委-山东省联合基金(U1806205)。

摘　　要：海表面盐度是描述海洋状态、模拟海洋循环和检测气候变化的重要指标,对海洋研究意义重大。土壤湿度与海水盐度(soil moisture and ocean salinity,SMOS)卫星为全球海表面盐度分析提供了重要数据,但其整体精度尚未达到预期要求。基于海表面盐度遥感机理和SMOS卫星盐度反演基础理论,选取海表面盐度敏感因子,建立随机森林(random forest,RF)模型,并基于网格搜索算法优化模型参数,辅助提高SMOS卫星产品精度。其中基础RF得到的海表面盐度与Argo(array for real-time geostrophic oceanography)数据之间的平均绝对误差为0.08,均方根误差为0.15。而经网格搜索算法优化后的随机森林模型精度稍有所提升,其与Argo数据的绝对平均误差为0.08,均方根误差仅为0.14,且误差分布范围较小。两种模型均显著优于SMOS卫星Level 2级盐度产品。从机器学习与统计学理论出发,建立的高精度、高适应性的随机森林海表面盐度反演模型大幅提高了盐度精度,能够为相关海洋研究提供数据支撑。Objectives:SSS(sea surface salinity) is an important physical and chemical indicator describing ocean state,and is also one of the most critical variables in global water cycle.In order to achieve largescale and continuous observation of the ocean salinity,SMOS(soil moisture and ocean salinity) mission is launched by European Space Agency to access brightness temperature for SSS retrieval.However,researches have pointed out that the accuracy of SMOS ocean salinity products cannot fully achieve scientific expect.Thus,a novel and effective method is desired for improving SMOS salinity.Methods:This paper selects study area in the Southeast Pacific,where the region is relatively less affected by radio frequency interference.The downloaded array for real-time geostrophic oceanography SSS data,SMOS level2 ocean salinity products and the Auxiliary data in the whole year of 2018 are matched both temporally and spatially.Based on the remote sensing mechanism and radiation transfer theory,five variables,including the first Stokes parameter(TH+TV),SST,UN10,VN10 and Ω are selected as sensitive factors.The ocean salinity retrieval model based on random forest is first established,and GridSearchCV(GS) algorithm is applied to optimize superparameters of the initial model,which is able to improve SSS accuracy further.Results:The experiment results show that:(1) For objective measurement,the mean absolute error(MAE) and root mean square error(RMSE) are adopted to compare the accuracy of the produced SSS from two established models and the SMOS products,in terms of Argo in-situ SSS as reference.According to experiments,MAEs of basic RF(random forest) model and GS-RF model are both 0.08,which is evidently lower than SMOS SSS product's 0.66.Similarly,RMSEs of two models are also remarkable lower than SMOS's 0.93,while GS-RF model is 0.14,indicating its slight advantage over RF model,which is 0.15.(2) All SSS retrieved from RF model and GS-RF model distribute concentratedly around 36 psu,while SMOS ocean salinity product occasionall

关 键 词：SMOS卫星 海表面盐度 随机森林 网格搜索 参数优化 

分 类 号：P237[天文地球—摄影测量与遥感] P714[天文地球—测绘科学与技术]