海表面盐度的高精度预测模型  

High-Precision Prediction Model for Sea Surface Salinity

作　　者：王颖超 柳青青 李洪平[1] 赵红[3] WANG Ying-chao;LIU Qing-qing;LI Hong-ping;ZHAO Hong(Department of Marine Technology,Ocean University of China,Qingdao 266100,China;Business College,Qingdao University,Qingdao 266100,China;School of Mathematical Sciences,Ocean University of China,Qingdao 266100,China)

机构地区：[1]中国海洋大学信息科学与工程学院,山东青岛266100 [2]青岛大学商学院,山东青岛266100 [3]中国海洋大学数学科学学院,山东青岛266100

出　　处：《海洋科学进展》2021年第1期37-44,共8页Advances in Marine Science

基　　金：国家自然科学基金项目——稳健主成分回归的数值方法研究(11871444)。

摘　　要：为了建立高精度的海洋表面盐度预测模型,采用BP神经网络的方法,针对SMOS卫星level 1C级亮度温度数据和辅助数据建立了一种海表面盐度预测模型,以ARGO浮标观测值作为海表盐度实测值来检验新模型预测结果的准确度,同时利用验证集对模型的精度进行验证。结果表明:通过新模型预测的海表盐度(SSS0)比SMOS卫星的3个粗糙度模型盐度产品(SSS1,SSS2,SSS3)精度高;SSS0,SSS1,SSS2,SSS3与ARGO浮标实测盐度(SSS ARGO)的均方根误差分别为0.8473,2.0417,2.0288和2.0805,平均绝对误差分别为0.7553,1.4226,1.4216和1.4566,SSS0与SSS ARGO的均方根误差和绝对平均误差值都明显小于SSS1,SSS2和SSS3与SSS ARGO的;由此可见,建立的海表盐度预测模型精度较高。新模型为海表盐度的反演算法提供了新思路。To build a high-precision ocean surface salinity prediction model,the back propagation(BP)neural network method is utilized to establish a sea surface salinity prediction model based on soil moisture and ocean salinity(SMOS)satellite level 1C brightness and temperature data and auxiliary data.The array for real-time geostrophic oceanography(ARGO)buoy observations are used as the measured value of sea surface salinity to test the accuracy of the new model s prediction results,and the verification set is used to verify the accuracy of the model.The results show that the sea surface salinity predicted by the new model(referred to as SSS0)is more accurate than the three roughness model salinity products of soil moisture ocean salinity(SMOS)satellites(referred to as SSS1,SSS2,and SSS3).The accuracy of the root mean square errors of SSS0,SSS1,SSS2,SSS3 compared to SSS ARGO are 0.8473,2.0417,2.0288 and 2.0805,and the absolute average errors are 0.7553,1.4226,1.4216 and 1.4566.Both of the root mean square error and absolute average error of SSS0 are significantly smaller than SSS1,SSS2,and SSS3.Therefore,it shows that the sea surface salinity prediction model established in this paper has higher accuracy,and it provides a novel way for generating the sea surface salinity inversion algorithm.

关 键 词：海表盐度 BP神经网络 SMOS卫星 ARGO浮标 

分 类 号：P731.11[天文地球—海洋科学]