基于BP神经网络模型的哨兵SAR反演风速偏差校正  

Calibration of Sentinel-1 SAR retrieved wind speed based on BP neural network model

作　　者：倪晗玥 董昌明 刘振波 杨劲松 李晓辉 任林 NI Hanyue;DONG Changming;LIU Zhenbo;YANG Jingsong;LI Xiaohui;REN Lin(School of Oceanography,Shanghai Jiao Tong University,Shanghai 200240,China;Second Institute of Oceanography,MNR,State Key Laboratory of Satellite Ocean Environment Dynamics,Hangzhou 310012,China;School of Marine Sciences,Nanjing University of Information Science&Technology,Nanjing 210044,China)

机构地区：[1]上海交通大学海洋学院,上海200240 [2]自然资源部第二海洋研究所卫星海洋环境动力学国家重点实验室,浙江杭州310012 [3]南京信息工程大学海洋科学学院,江苏南京210044

出　　处：《海洋学研究》2024年第3期75-87,共13页Journal of Marine Sciences

基　　金：国家自然科学基金项目(42306200,42306216);国家重点研发计划项目(2022YFC3103101)。

摘　　要：该文基于美国国家浮标资料中心(National Data Buoy Center,NDBC)浮标观测数据对哨兵一号搭载的合成孔径雷达(synthetic aperture radar,SAR)反演风速数据进行精度分析,并利用BP神经网络(back propagation neural network)对SAR反演风速的偏差进行校正;同时针对环境要素、BP神经网络训练输入的样本量以及神经网络结构参数设计了敏感性试验;最后将SAR标量风场数据转换为用u、v矢量表示的风场数据,并对u向风和v向风分别进行了精度分析和校正。实验结果表明:SAR反演风速相较于浮标观测数据出现了低估现象;经过BP神经网络校正后,SAR反演风速数据的精度得到了改善,风速的平均偏差绝对值从0.78 m s下降到0.04 m s,均方根误差从1.98 m s下降到了1.77 m s;敏感性试验表明输入质量较差的环境要素数据时BP神经网络的校正效果有所下降,而增加训练集样本量能改善校正效果;将标量风场数据转换为u、v矢量风场数据后的校正结果也显示BP神经网络具有较好的校正效果。An accuracy analysis of wind speed data retrieved from Sentinel-1 synthetic aperture radar(SAR)was conducted based on buoy observations from the National Data Buoy Center(NDBC).A back propagation(BP)neural network was utilized to correct the deviation in the SAR-derived wind speeds.Sensitivity experiments were designed for environmental factors,the number of training samples for BP neural network input,and neural network structure parameters.Finally,the SAR wind field data were converted into u and v vector wind data,and the accuracy analysis and correction were performed separately for u and v wind components.The experiment finds that the SAR-derived wind speed is underestimated compared to the buoy data.After calibration using BP neural network,the accuracy of SAR-derived wind speed data is improved,and the absolute value of bias of wind speed decreases from 0.78 m s to 0.04 m s,the RMSE of wind speed decreases from 1.98 m s to 1.77 m s.The sensitivity experiments suggest that low quality environmental factors input data will decrease the calibration effect of BP neural network,and increasing the sample size of the training set can improve that.The calibration results of converted u and v vector wind field data also show that the BP neural network has good correction effect.

关 键 词：哨兵一号卫星 SAR风速资料 NDBC浮标 BP神经网络 偏差校正 敏感性试验 标量风场 矢量风场 

分 类 号：P732[天文地球—海洋科学] TP183[自动化与计算机技术—控制理论与控制工程]