基于神经网络反演FY-3E GNSS-R海面有效波高的固有误差分析

doi:10.13474/j.cnki.11-2246.2025.1017

测绘通报 ›› 2025, Vol. 0 ›› Issue (10): 100-105,132.doi: 10.13474/j.cnki.11-2246.2025.1017

• 学术研究 • 上一篇

基于神经网络反演FY-3E GNSS-R海面有效波高的固有误差分析

余辉^1,2,3, 杜起飞^1,3, 夏俊明^1,3, 黄飞雄^1,3, 尹聪^1,3, 白伟华^1,3

1. 中国科学院国家空间科学中心, 北京 100190;
2. 上海卫星工程研究所, 上海 201109;
3. 中国科学院大学, 北京 100049

收稿日期:2025-02-25 发布日期:2025-10-31
通讯作者: 夏俊明。E-mail:xiajunming@nssc.ac.cn
作者简介:余辉(1986-),男,博士,高级工程师,主要研究方向为星载海洋微波遥感应用。E-mail:yuhui20@mails.ucas.ac.cn
基金资助:
中国科学院青年创新促进会项目(Y2020152);国家自然科学基金(42104032;42074042);中国科学院青年交叉团队项目(JCTD-2021-10);风云卫星先行计划(FY-APP-2022.0108)

Intrinsic error analysis of sea surface significant wave height retrieval from FY-3E GNSS-R based on neural network inversion

YU Hui^1,2,3, DU Qifei^1,3, XIA Junming^1,3, HUANG Feixiong^1,3, YIN Cong^1,3, BAI Weihua^1,3

1. National Space Science Center, Chinese Academy of Sciences, Beijing 100190, China;
2. Shanghai Institution of Satellite Engineering, Shanghai 201109, China;
3. University of Chinese Academy of Sciences, Beijing 100049, China

Received:2025-02-25 Published:2025-10-31

摘要/Abstract

摘要： 风云三号(FY-3E)卫星搭载的全球卫星导航掩星探测仪器Ⅱ(GNOS Ⅱ)在轨获取的全球卫星导航系统反射信号遥感(GNSS-R)数据已实现海面风速、土壤湿度、海冰覆盖、海冰厚度等产品的业务化生产,并具备海面有效波高产品反演潜力。本文采用神经网络(NN)技术,基于FY-3E卫星GNOS Ⅱ提供的北斗卫星导航系统反射(BDS-R)和全球定位系统反射(GPS-R)数据,构建了海浪有效波高反演模型,采用三配对数据分析方法分析了BDS-R和GPS-R反演海面有效波高的固有误差。研究结果表明,单独利用ECMWF数据评估的BDS-R和GPS-R有效波高反演精度分别为0.43和0.46m,单独利用国家数据浮标中心(NDBC)的浮标数据评估的BDS-R和GPS-R有效波高反演精度分别为0.45和0.50m,采用三配对数据分析方法评估的BDS-R和GPS-R有效波高固有误差分别为0.40和0.43m,三配对数据分析方法有效降低了对比数据自身误差对评估结果的影响,BDS-R的有效波高反演精度整体优于GPS-R约7%。本文研究结果为FY-3 GNOS Ⅱ有效波高的业务应用提供参考。

关键词: 风云三号E星, GNOS-Ⅱ, GNSS-R, 有效波高, 神经网络, 三配对分析法

Abstract: The global navigation satellite occultation sounder Ⅱ (GNOS Ⅱ), carried by the Fengyun-3 satellite, has achieved operational products such as sea surface wind speed, soil moisture, sea ice coverage and sea ice thickness based on the global navigation satellite system reflectometry (GNSS-R)data acquired in orbit.This study employs neural network (NN)technology to develop an SWH inversion model using Beidou Navigation Satellite System reflectometry (BDS-R)and Global Positioning System reflectometry (GPS-R)data provided by GNOS Ⅱ on the FY-3E satellite.A triplet comparison analysis method is adopted to compare and analyze the inherent errors in SWH inversion based on BDS-R and GPS-R data.The research results indicate that the inversion accuracy of BDS-R for significant wave height, assessed solely with data from the European Centre for Medium-Range Weather Forecasts (ECMWF)is 0.43 meters, compared to 0.46 meters for GPS-R.When validated independently using buoy data from the National Data Buoy Center (NDBC), the inversion accuracies for BDS-R and GPS-R are 0.45 and 0.50 meters, respectively.Using the triplet comparison analysis method, the inherent errors in SWH inversion for BDS-R and GPS-R are estimated to be 0.40 and 0.43 meters.This method effectively reduces the impact of inherent errors in the comparison data on the assessment results.Overall, the inversion accuracy of BDS-R for SWH is approximately 7%better than that of GPS-R.The findings of this study provide a reference for the operational application of SWH retrievals from FY-3 GNOS Ⅱ.

Key words: FY-3E satellite, GNOS Ⅱ, GNSS-R, signific wave height, neutral network, triple collocation analysis

中图分类号:

P229

余辉, 杜起飞, 夏俊明, 黄飞雄, 尹聪, 白伟华. 基于神经网络反演FY-3E GNSS-R海面有效波高的固有误差分析[J]. 测绘通报, 2025, 0(10): 100-105,132.

YU Hui, DU Qifei, XIA Junming, HUANG Feixiong, YIN Cong, BAI Weihua. Intrinsic error analysis of sea surface significant wave height retrieval from FY-3E GNSS-R based on neural network inversion[J]. Bulletin of Surveying and Mapping, 2025, 0(10): 100-105,132.

参考文献

[1] [ASGARIMEHR M,WICKERT J,REICH S. TDS-1 GNSS reflectometry:development and validation of forward scattering winds[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2018,11(11):4534-4541. [2] RUF C S,ATLAS R,CHANG P S,et al. New ocean winds satellite mission to probe hurricanes and tropical convection[J]. Bulletin of the American Meteorological Society,2016,97(3):385-395. [3] JING Cheng,NIU Xinliang,DUAN Chongdi,et al. Sea surface wind speed retrieval from the first Chinese GNSS-R mission:technique and preliminary results[J]. Remote Sensing,2019,11(24):3013. [4] YANG Guanglin,BAI Weihua,WANG Jinsong,et al. FY3E GNOS Ⅱ GNSS reflectometry:mission review and first results[J]. Remote Sensing,2022,14(4):988. [5] HUANG Feixiong,SUN Yueqiang,XIA Junming,et al. Progress on the GNSS-R product from Fengyun-3 missions[C] //Proceedings of 2024 IGARSS IEEE International Geoscience and Remote Sensing Symposium.Athens,Greece:IEEE, 2024:6717-6720. [6] HUANG Feixiong,XIA Junming,YIN Cong,et al. Assessment of FY-3E GNOS-II GNSS-R global wind product[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2022,15:7899-7912. [7] YIN Cong,XIA Junming,HUANG Feixiong,et al. Sea ice detection with FY3E GNOS II GNSS reflectometry[C] //Proceedings of 2021 IEEE Specialist Meeting on Reflectometry Using GNSS and Other Signals of Opportunity (GNSS+R). Beijing:IEEE,2021:36-38. [8] XIE Yunjian,YAN Qingyun. Stand-alone retrieval of sea ice thickness from FY-3E GNOS-R data[J]. IEEE Geoscience and Remote Sensing Letters,2024,21:1-5. [9] PENG Qin,JIN Shuanggen. Significant wave height estimation from space-borne cyclone-GNSS reflectometry[J]. Remote Sensing,2019,11(5):584. [10] YANG Shuai,JIN Shuanggen,JIA Yan,et al. Significant wave height estimation from joint CYGNSS DDMA and LES observations[J]. Sensors,2021,21(18):6123. [11] BU Jinwei,YU Kegen. A new integrated method of CYGNSS DDMA and LES measurements for significant wave height estimation[J]. IEEE Geoscience and Remote Sensing Letters,2022,19:1-5. [12] 布金伟,余科根,韩帅. 星载GNSS-R海浪有效波高反演模型构建[J]. 测绘学报,2022,51(9):1920-1930. [13] MAHESHWARI M,KUMAR A,CHAKRABORTY A,et al. Application of the neural network on the GNSS-reflectometry data for the estimation of the significant wave height[C] //Proceedings of 2022 URSI Regional Conference on Radio Science (USRI-RCRS). Indore:IEEE,2022:1-4. [14] 张云,肖盛,姜丽菲,等. 基于多变量机器学习的CYGNSS有效波高反演模型[J]. 北京航空航天大学学报,2023,51(5):1503-1513. [15] WANG Feng,YANG Dongkai,YANG Lei. Retrieval and assessment of significant wave height from CYGNSS mission using neural network[J]. Remote Sensing,2022,14(15):3666. [16] CAI Min,CHENG Xing,HE Shanbao,et al. A deep neural networks-based significant wave height inversion method for GNSS-R signals[C] //Proceedings of 2024 International Conference on Neural Networks,Information and Communication (NNICE). Guangzhou:IEEE,2024:1208-1211. [17] BU Jinwei,YU Kegen,NI Jun,et al. Combining ERA5 data and CYGNSS observations for the joint retrieval of global significant wave height of ocean swell and wind wave:a deep convolutional neural network approach[J]. Journal of Geodesy,2023,97(8):81. [18] BU Jinwei,WANG Qiulan,NI Jun. Estimating sea surface swell height using a hybrid model combining CNN,ConvLSTM,and FCN based on spaceborne GNSS-R data from the CYGNSS mission[J]. GPS Solutions,2024,28(3):133. [19][BU Jinwei,WANG Qiulan,LIU Xinyu,et al. Ocean swell height estimation from spaceborne GNSS-R data using tree model based machine learning methods[C] //Proceedings of 2024 IEEE/OES Thirteenth Current,Waves and Turbulence Measurement (CWTM). Wanchese:IEEE,2024:1-5. [20] GRUBER A,DORIGO W A,CROW W,et al. Triple collocation-based merging of satellite soil moisture retrievals[J]. IEEE Transactions on Geoscience and Remote Sensing,2017,55(12):6780-6792. [21] 刘帅,林文明,鲁云飞. CYGNSS海面风速固有误差与时空分布特征[J]. 空间科学学报,2022,42(5):1029-1037.

基于神经网络反演FY-3E GNSS-R海面有效波高的固有误差分析

Intrinsic error analysis of sea surface significant wave height retrieval from FY-3E GNSS-R based on neural network inversion

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	王玉, 李泽辰, 梁菘元, 石雪. 基于神经网络优化Canny算子的海岸线提取方法[J]. 测绘通报, 2025, 0(9): 84-90.
[2]	迟晋浙, 刘纪平, 徐胜华, 王勇, 王琢璐. 自适应门控机制嵌入图神经网络的下一个POI推荐[J]. 测绘通报, 2025, 0(7): 90-96.
[3]	王贻朋, 徐大伟, 魏明阳, 李波, 胡慧敏, 杨明生, 徐玉玲. 多传感器数据融合的边坡滑坡预警模型与应用[J]. 测绘通报, 2025, 0(7): 169-173.
[4]	刘松焕, 李朝奎, 田沁, 江岭. 基于投影和特征激活的实景三维玻璃幕墙分割[J]. 测绘通报, 2025, 0(5): 84-88.
[5]	赵辰瑞, 连增增, 田亚林, 贺刘辉, 陈浩, 王鹏辉, 王孟奇. BiLSTM-Chan算法在超宽带室内定位中的应用[J]. 测绘通报, 2025, 0(5): 100-105.
[6]	孙凯, 徐青, 张瑞鑫, 苏友能. 改进特征金字塔池化的遥感影像障碍物提取[J]. 测绘通报, 2025, 0(4): 90-95.
[7]	苟长龙, 庞敏, 杨扬. 改进的U-Net卷积网络在遥感影像地物分类中的应用[J]. 测绘通报, 2025, 0(3): 150-155.
[8]	谢巴图, 胡佳睿, 潘俊. 基于双路全局信息优化网络的遥感影像海陆分割算法[J]. 测绘通报, 2025, 0(3): 52-58,86.
[9]	张广伟. 一种探地雷达与深度学习的隧道衬砌健康评价方法[J]. 测绘通报, 2025, 0(3): 122-126,149.
[10]	吴昂道, 唐旭, 张骋. 融合GRNN神经网络的ZHD模型构建及其在中国区域PWV反演中的应用[J]. 测绘通报, 2025, 0(10): 87-93.
[11]	范晶晶, 胡帆, 原辉, 张娜, 孟晓凯, 王帅. 架空输电线路覆冰厚度图卷积神经网络预测模型构建与应用[J]. 测绘通报, 2025, 0(1): 12-15.
[12]	周康胜, 杨德宏, 韩杨, 周鹏, 姜昀呈. 基于kNDVI的时空演变、预测及生态安全格局构建——以水土流失的黄土高原为例[J]. 测绘通报, 2024, 0(8): 115-121.
[13]	王一帆, 李增科, 蒋诗政, 陈远, 黄林超, 吉丽娅, 邓伟昉. 基于人工神经网络的UWB坐标误差一步改正模型[J]. 测绘通报, 2024, 0(7): 77-82.
[14]	程振豪, 赵冬青, 郭文卓, 赖路广, 李林阳. 一种融合5G CSI和地磁的集成学习定位方法[J]. 测绘通报, 2024, 0(7): 12-16.
[15]	田亚林, 连增增, 王鹏辉, 王孟奇, 陆力. 基于KF-LSTM的UWB室内定位算法[J]. 测绘通报, 2024, 0(7): 95-99,151.