SVRM-assisted soil moisture retrieval method using reflected signal from BeiDou GEO satellites
-
摘要: 提出了一种支持向量回归机(SVRM)辅助的北斗地球静止轨道(GEO)卫星反射信号土壤湿度反演方法。使用全球导航卫星系统反射信号(GNSS-R)右旋圆极化(RHCP)天线和左旋圆极化(LHCP)天线接收体制进行了地基实验,采集了北斗GEO卫星直射、反射信号原始数据,并从中提取直射、反射信号的相关功率,结合北斗GEO卫星的高度角与方位角信息作为输入,烘干称重法获取的土壤湿度作为输出对使用径向基(RBF)核函数的ε-SVRM进行了训练。独立测试集上的结果表明,SVRM辅助的北斗GEO卫星反射信号土壤湿度反演方法获取的土壤湿度结果与烘干称重法获取的土壤湿度参考值误差控制在3%以内,线性回归方程决定系数为0.897 9,均方根误差RMSE为1.492 6%,证明了该方法具有良好的泛化特性,实际应用中效果良好。
-
关键词:
- 北斗 /
- 地球静止轨道(GEO)卫星 /
- 全球导航卫星系统反射信号(GNSS-R) /
- 支持向量回归机(SVRM) /
- 土壤湿度 /
- 遥感探测
Abstract: We propose a support vector regression machine (SVRM)-assisted soil moisture retrieval method using the reflected signal from BeiDou geosynchronous orbit (GEO) satellites. This method uses a right hand circular polarization (RHCP) antenna and a left hand circular polarization (LHCP) antenna to gain the direct and reflected signal's power data from the BeiDou GEO satellites, respectively. Furthermore, it uses the direct and reflected signal power, BeiDou GEO satellites' elevation angle and azimuth angle as the input features and uses the soil moisture data which is obtained by oven-drying method as the output target of the ε-SVRM which uses a radial basis function (RBF) kernel function. The collected data is separated into two sets randomly:one as training set and the other as test set. The test results show that the error between retrieval model's prediction and the value of oven-drying method is less than 3%; the regression coefficient of determination is 0.897 9; the root mean square error (RMSE) is 1.492 6%, which proves that this method has good generalization ability and the practical results meet the application requirement. -
[1] 刘经南,邵连军,张训械.GNSS-R研究进展及其关键技术[J].武汉大学学报:信息科学版,2007,32(11):955-960. LIU J N,SHAO L J,ZHANG X X.Advances in GNSS-R studies and key technologies[J].Geomatics and Information Science of Wuhan University,2007,32(11):955-960(in Chinese). [2] 王迎强,严卫,符养,等.机载GPS反射信号土壤湿度测量技术[J].遥感学报,2009,13(4):670-685. WANG Y Q,YAN W,FU Y,et al.Soil moisture determination of reflected GPS signals from aircraft platform[J].Journal of Remote Sensing,2009,13(4):670-685(in Chinese). [3] MASTERS D,AXELRAD P,KATZBERG S.Initial results of land-reflected GPS bistatic radar measurements in SMEX02[J].Remote Sensing of Environment,2004,92(4):507-520. [4] 关止,赵凯,宋冬生.利用反射GPS信号遥感土壤湿度[J].地球科学进展,2006,21(7):747-750. GUAN Z,ZHAO K,SONG D S.Measuring soil moisture using reflected GPS signals[J].Advances in Earth Science,2006,21(7):747-750(in Chinese). [5] 严颂华,张训械.基于GNSS-R信号的土壤湿度反演研究[J].电波科学学报,2010,25(1):8-13. YAN S H,ZHANG X X.Retrieving soil moisture based on GNSS-R signals[J].Chinese Journal of Radio Science,2010,25(1):8-13(in Chinese). [6] 张训械,严颂华.利用GNSS-R反射信号估计土壤湿度[J].全球定位系统,2009(3):1-6. ZHANG X X,YAN S H.Soil moisture estimation using GPS reflected signals[J].GNSS World of China,2009(3):1-6(in Chinese). [7] WAN W,LI H,CHEN X W,et al.Preliminary calibration of GPS signals and its effects on soil moisture estimation[J].Acta Meteorologica Sinica,2013,27(2):221-232. [8] WAN W,BAI W,ZHAO L,et al.Initial results of China's GNSS-R airborne campaign:Soil moisture retrievals[J].Science Bulletin,2015,60(10):964-971. [9] 宋学忠,徐爱功,杨东凯,等.GNSS反射信号在土壤湿度测量中的应用[J].测绘通报,2013(11):61-64. SONG X Z,XU A G,YANG D K,et al.Details of soil moisture measuring utilizing GNSS reflected signals[J].Bulletin of Surveying and Mapping,2013(11):61-64(in Chinese). [10] RODRIGUEZ-ALVAREZ N,BOSCH-LLUIS X,CAMPS A,et al.Soil moisture retrieval using GNSS-R techniques:Experimental results over a bare soil field[J].IEEE Transactions on Geoscience & Remote Sensing,2009,47(11):3616-3624. [11] VAPNIK V N.The nature of statistical learning theory[M].New York:Springer Verlag Press,1995:133-136. [12] MARTíN-NEIRA M.A passive peflectometry and interferometry system (PARIS):Application to ocean altimetry[J].ESA Journal,1993,17:331-355. [13] 熊文成.含水含盐土壤介电特性及反演研究[D].北京:中国科学院遥感应用研究所,2005:14-15. XIONG W C.Studies on microwave dielectric behavior of moist salt soil and inversion of the moisture and salt content[D].Beijing:Institute of Remote Sensing Applications Chinese Academy of Sciences,2005:14-15(in Chinese). [14] DOBSON M C,ULABY F T,HALLIKAINEN M T,et al.Microwave dielectric behavior of wet soil-Part Ⅱ:Dielectric mixing models[J].IEEE Transactions on Geoscience & Remote Sensing,1985,GE-23(1):35-46. [15] HALLIKAINEN M T,ULABY F T,DOBSON M C,et al.Microwave dielectric behavior of wet soil-Part 1:Empirical models and experimental observations[J].IEEE Transactions on Geoscience & Remote Sensing,1985,GE-23(1):25-34. [16] TOPP G C,DAVIS J L,ANNAN A P.Electromagnetic determination of soil water content:Measurements in coaxial transmission lines[J].Water Resources Research,1980,16(3):574-582. [17] WANG J R,SCHMUGGE T J.An empirical model for the complex dielectric permittivity of soils as a function of water content[J].IEEE Transactions on Geoscience & Remote Sensing,1980,GE-18(4):288-295. [18] SMOLA A J,SCHÖLKOPF B.A tutorial on support vector regression[J].Statistics & Computing,2004,14(3):199-222. [19] VAPNIK V N.Statistical learning theory[M].New York:Wiley,1998:460-471. [20] BISHOP C M.Pattern recognition and machine learning[M].New York:Springer,2006:291-320. [21] 杨东凯,张其善.GNSS反射信号处理基础与实践[M].北京:电子工业出版社,2012:92. YANG D K,ZHANG Q S.GNSS reflected signal processing:Fundamentals and applications[M].Beijing:Publishing House of Electronics Industry,2012:92(in Chinese).
点击查看大图
计量
- 文章访问数: 1102
- HTML全文浏览量: 62
- PDF下载量: 666
- 被引次数: 0