基于BP神经网络的GNSS-R海面风速反演

doi:10.7527/S1000-6893.2019.23261

电子电气工程与控制

本期目录 | 过刊浏览 | 高级检索

前一篇 | 后一篇

基于BP神经网络的GNSS-R海面风速反演

高涵, 白照广, 范东栋

航天东方红卫星有限公司, 北京 100094

收稿日期:2019-07-02 修回日期:2019-07-22 出版日期:2019-12-15 发布日期:2019-08-29
通讯作者: 白照广 E-mail:13910027870@139.com

GNSS-R sea surface wind speed inversion based on BP neural network

GAO Han, BAI Zhaoguang, FAN Dongdong

DFH Satellite Co., Ltd., Beijing 100094, China

Received:2019-07-02 Revised:2019-07-22 Online:2019-12-15 Published:2019-08-29

摘要/Abstract

摘要： 针对GNSS-R进行海面风速反演过程中时频域相关物理量较多，数据耦合性强等问题，提出了基于反向传播（BP）神经网络反演海面风速的方法。建立反演过程中相关观测量与风速的对应关系，选取多观测量作为输入，对输入数据进行处理，设置神经元与激励函数，使用BP神经网络自适应调整拟合参数，将风速作为神经网络输出端的特征量提取。反演结果，风速≤ 20 m/s时，反演均方根误差RMSE=1.21 m/s，风速>20 m/s时反演均方根误差RMSE=2.54 m/s，反演结果优于使用时延相关曲线前沿斜率（LES）和时延多普勒相关功率均值（DDMA）方法得到的反演结果，且迭代次数较少，复杂度较低，证明该方法可以应用于GNSS-R海面风速反演。

关键词: GNSS-R, 海面风速, 反向传播(BP), 神经网络, 反演模型

Abstract: In the sea surface wind speed inversion of GNSS-R, the time-frequency domain related physical quantity is large, and the data coupling is strong. A method of inversion of sea surface wind speed based on Back-Propagation (BP) neural network is proposed. This paper establishes the corresponding relationship between the correlation observation and the wind speed in the inversion process. Selecting the multi-view measurement as the input, the input data are processed, the neuron and the excitation function are set. using the BP neural network, the fitting parameters are adaptively adjusted. And the wind speed is used as the extraction feature in the neural network. The inversion results show that when the wind speed is ≤ 20 m/s, the inversion Root Mean Square Error (RMSE) is 1.21 m/s, and the inversion RMSE is 2.54 m/s when the wind speed is >20 m/s. The result is better than the inversion results obtained by the Delay Leading Edge Slope and Delay-Doppler Average methods, and the number of iterations is small and the complexity is low, proving that the method can be applied to GNSS-R sea surface wind speed inversion.

Key words: GNSS-R, sea surface wind speed, Back-Propagation (BP), neural networks, inversion mode

中图分类号:

高涵, 白照广, 范东栋. 基于BP神经网络的GNSS-R海面风速反演[J]. 航空学报, 2019, 40(12): 323261-323261.

GAO Han, BAI Zhaoguang, FAN Dongdong. GNSS-R sea surface wind speed inversion based on BP neural network[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2019, 40(12): 323261-323261.

参考文献 30

[1]	MARTIN-NEIRA M. A passive reflectometry and interferometry system (PARIS) application to ocean altimetry[J]. ESA Journal, 1993, 17(4):331-355.
[2]	KATZBERG S J, GARRISON J L. Utilizing GPS to determine ionospheric delay over the ocean:NASA 4750[R]. Washington, D.C.:NASA, 1996.
[3]	GARRISON J L, KATZBERG S J, HILL M I. Effect of sea roughness on bistatical scattered range coded signals from the Global Positioning System[J]. Geophysical Research Letters, 1998, 25(13):2257-2260.
[4]	ZAVOROTNY V U, VORONOVICH A G. Bistatic radar scattering from an ocean surface in the small-slope approximation[C]//IEEE 1999 International Geoscience and Remote Sensing Symposium. Piscataway, NJ:IEEE Press, 1999:2419-2421.
[5]	ZAVOROTNY V U, VORONOVICH A G. Scattering of GPS signals from the ocean with wind remote sensing application[J]. IEEE Transactions on Geoscience and Remote Sensing, 2000, 38(2):951-964.
[6]	GARRISON J L, KOMJATHY A, ZAVOROTNY V U, et al. Wind speed measurement using forward scattered GPS signals[J]. IEEE Transactions on Geoscience & Remote Sensing, 2002, 40(1):50-65.
[7]	RODRIGUEZ-ALVAREZ N, AKOS D M, ZAVOROTNY V U, et al. Airborne GNSS-R wind retrievals using delay-Doppler maps[J]. IEEE Transactions on Geoscience and Remote Sensing, 2012, 51(1):626-641.
[8]	CLARIZIA M P, RUF C S, JALES P, et al. Spaceborne GNSS-R minimum variance wind speed estimator[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(11):6829-6843.
[9]	WANG F, YANG D, ZHANG B, et al. Wind speed retrieval using coastal ocean-scattered GNSS signals[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 9(11):1-12.
[10]	WANG F, YANG D, ZHANG B, et al. Waveform-based spaceborne GNSS-R wind speed observation:Demonstration and analysis using UK TechDemoSat-1 data[J]. Advances in Space Research, 2018, 61(6):1573-1587.
[11]	KASANTIKUL K, YANG D, WANG Q, et al. A novel wind speed estimation based on the integration of an artificial neural network and a particle filter using BeiDou GEO reflectometry[J]. Sensors, 2018, 18(10):3350.
[12]	HAUPT S E, PASINI A, MARZBAN C. Artificial intelligence methods in the environmental sciences[M]. Berlin:Springer, 2009:359.
[13]	马建文, 李启青,哈斯巴干,等.遥感数据智能处理方法与程序设计[M]. 北京:科学出版社, 2010. MA J W, LI Q Q, HASBAGAN, et al. Intelligent processing method and program design of remote sensing data[M]. Beijing:Science Press, 2010(in Chinese).
[14]	周旺旺, 姚佩阳, 张杰勇, 等. 基于深度神经网络的空中目标作战意图识别[J]. 航空学报, 2018, 39(11):322468. ZHOU W W,YAO P Y,ZHANG J Y,et al. Combat intention recognition for aerial targets based on deep neu-ral network[J]. Acta Aeronautica et Astronautica Sinica,2018,39(11):322468(in Chinese).
[15]	GLEASON S, RUF C S, CLARIZIA M P, et al. Calibration and unwrapping of the normalized scattering cross section for the cyclone global navigation satellite system[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(5):2495-2509.
[16]	GLOROT X, BORDES A, BENGIO Y. Deep sparse rectifier neural networks[C]//International Conference on Artificial Intelligence and Statistics, 2011:315-323.
[17]	KINGMA D P, BA J. Adam:A method for stochastic optimization[J]. Computer Science, 2014:1-5.
[18]	RODRIGUEZ-ALVAREZ N, GARRISON J L. Generalized linear observables for ocean wind retrieval from calibrated GNSS-R delay-Doppler maps[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(2):1142-1155.
[19]	CLARIZIA M P, RUF C S. Wind speed retrieval algorithm for the Cyclone Global Navigation Satellite System (CYGNSS) mission[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(8):4419-4432.
[20]	SCOTT G. Remote sensing of ocean, ice and land surfaces using bistatically scattered GNSS signals from low earth orbit[D]. Surrey:University of Surrey, 2006.
[21]	ALONSO-ARROYO A, ZAVOROTNY V U, CAMPS A. Sea ice detection using U.K.TDS-1 GNSS-R data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(9):4989-5001.
[22]	TYE J, JALES P, UNWIN M, et al. The first application of stare processing to retrieve mean square slope using the SGR-ReSI GNSS-R experiment on TDS-1[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017, 9(10):4669-4677.
[23]	杨东凯, 李伟强, 杨威. 北斗系统在海风海浪探测中的应用研究[J]. 导航定位学报, 2014, 2(2):97-101. YANG D K, LI W Q, YANG W. Application of Beidou system in sea wind wave detection[J]. Journal of Navigation and Positioning, 2014, 2(2):97-101(in Chinese).
[24]	LI W, FABRA F, YANG D, et al. Initial results of typhoon wind speed observation using coastal GNSS-R of BeiDou GEO satellite[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 9(10):4720-4729.
[25]	JUAN M H, ADRIANO C, NEREIDA R A, et al. PAU/GNSS-R:Implementation, performance and first results of a real-time delay-doppler map reflectometer using global navigation satellite system signals[J]. Sensors, 2008, 8(5):3005-3019.
[26]	CARRENO-LUENGO H, CAMPS A, RAMOS-PéREZ I, et al. Experimental evaluation of GNSS reflectometry altimetric precision using the P(Y) and C/A signals[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7(5):1493-1500.
[27]	万定生, 胡玉婷, 任翔. 带反馈输入BP神经网络的应用研究[J]. 计算机工程与设计, 2010, 31(2):398-400. WAN D S, HU Y T, REN X. Application research of BP neural network with feedback input[J]. Computer Engineering and Design, 2010, 31(2):398-400(in Chinese).
[28]	HAGAN M T, DEMUTH H B.神经网络设计[M]. 戴葵, 译. 北京:机械工业出版社, 2002. HAGAN M T, DEMUTH H B. Neural network design[M]. DAI K, translated. Beijing:Mechanical Industry Press, 2002(in Chinese).
[29]	VALERIANO T T B, ROLIM G S, BISPO R C, et al. Evaluation of air temperature and rainfall from ECMWF and NASA gridded data for southeastern Brazil[J]. Theoretical and Applied Climatology, 2019, 137(3-4):1925-1938.
[30]	魏海坤, 徐嗣鑫, 宋文忠. 神经网络的泛化理论和泛化方法[J]. 自动化学报, 2001, 27(6):806-815. WEI H K, XU S X, SONG W Z. Generalization theory and generalization method of neural networks[J]. Acta Automatica Sinica, 2001, 27(6):806-815(in Chinese).

E-mail：hkxb@buaa.edu.cn

关于我们

期刊社服务

专业学科

封面文章

友情链接

主管单位：中国科学技术协会主办单位：中国航空学会北京航空航天大学

基于BP神经网络的GNSS-R海面风速反演

GNSS-R sea surface wind speed inversion based on BP neural network

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献 30

相关文章 15

编辑推荐

Metrics

本文评价

[1]	胡伟, 万文章, 陈谋. 基于神经网络和干扰观测器的UAV自动着舰控制[J]. 航空学报, 2022, 43(S1): 726963-726963.
[2]	陈博, 岳凯, 王如生, 胡明南. 基于学习策略的多速率多传感器融合定位方法[J]. 航空学报, 2022, 43(S1): 726904-726904.
[3]	王宇斐, 刘骁佳, 刘欢, 曹立俊, 罗志强. 孪生神经网络在航天产品电性能测试方面的应用[J]. 航空学报, 2022, 43(S1): 727048-727048.
[4]	王子玲, 熊振宇, 顾祥岐. 可见光与SAR多源遥感图像关联学习算法[J]. 航空学报, 2022, 43(S1): 727239-727239.
[5]	杨特, 杨智春, 梁舒雅, 康在飞, 贾有. 平稳随机载荷的信号特征提取与深度神经网络识别[J]. 航空学报, 2022, 43(9): 225952-225952.
[6]	刘佳奇, 冯蕴雯, 路成, 薛小锋, 潘维煌. 基于智能神经网络的航空发动机运行安全分析[J]. 航空学报, 2022, 43(9): 625375-625375.
[7]	韩淞宇, 邵海东, 姜洪开, 张笑阳. 基于提升卷积神经网络的航空发动机高速轴承智能故障诊断[J]. 航空学报, 2022, 43(9): 625479-625479.
[8]	邵怡韦, 陈嘉宇, 林翠颖, 万程, 葛红娟, 石智龙. 小训练样本下齿轮箱故障诊断:一种基于改进深度森林的方法[J]. 航空学报, 2022, 43(8): 625429-625429.
[9]	熊伟, 朱洪峰, 崔亚奇. 在线学习的循环自适应机动目标跟踪算法[J]. 航空学报, 2022, 43(5): 325250-325250.
[10]	董珍一, 林莉, 雷明凯, 马志远. 基于BPNN的封严涂层孔隙分布均匀性超声表征[J]. 航空学报, 2022, 43(5): 425294-425294.
[11]	王因翰, 范世鹏, 吴广, 王江, 何绍溟. 基于GRU的敌方拦截弹制导律快速辨识方法[J]. 航空学报, 2022, 43(2): 325024-325024.
[12]	奕建苗, 邓枫, 覃宁, 刘学强. 快速预测跨声速流场的深度学习方法[J]. 航空学报, 2022, 43(11): 526747-526747.
[13]	蔡国飙, 张百一, 贺碧蛟, 翁惠焱, 刘立辉. 真空羽流智能化计算[J]. 航空学报, 2022, 43(10): 527352-527352.
[14]	王辉, 贾自凯, 金忍, 林德福, 范军芳, 徐超. 无人机视觉引导对接过程中的协同目标检测[J]. 航空学报, 2022, 43(1): 324854-324854.
[15]	李昂, 聂党民, 温祥西, 韩宝华, 曾裕景. 管制-飞行状态相依网络演化过程[J]. 航空学报, 2021, 42(9): 324726-324726.