一种裸露土壤湿度反演方法Inversion of bare soil moisture based on least squares support vector machine
张清河,徐飞,朱国强
摘要(Abstract)：
针对目前土壤湿度反演方法研究较少且缺少实时性的现状,该文提出一种土壤湿度反演方法——最小二乘支持向量机技术。以积分方程模型为正向算法,数值模拟不同雷达参数(频率、入射角及极化)下后向散射系数随土壤含水量和地表粗糙度的变化情况。经过数据敏感性分析,选取C-波段和X-波段、小入射角下的同极化后向散射系数作为支持向量回归的训练样本信息;经过适当的训练,利用支持向量回归技术对土壤含水量进行了反演研究;并考虑通过多频率、多极化、多入射角数据的组合,消除地表粗糙度的影响,提高反演精度。模拟结果表明,该方法反演土壤湿度具有较高的精度和较好的实时性;同时,与人工神经网络方法的结果比较,证明了该方法的有效性,为土壤湿度的反演研究提供了一种方法。
关键词(KeyWords)： 积分方程模型;土壤湿度反演;最小二乘支持向量机;人工神经网络
基金项目(Foundation): 国家自然科学基金项目(61179025);; 湖北省教育厅自然科学重点项目(D20111201)
作者(Author): 张清河,徐飞,朱国强
DOI: 10.16251/j.cnki.1009-2307.2016.02.002
参考文献(References)：
- [1]DUBOIS P C,ZYL J J,ENGMAN T.Measuring soil moisture with imaging radar[C]//IEEE Transaction on Geoscience and Remote Sensing,1995,33(6):915-926.
- [2]OH Y,SARABANDI K,ULABY F T.An empirical model and inversion technique for radar scattering from bare soil surface[C]//IEEE Transaction on Geoscience and Remote Sensing,1992,30(2):370-382.
- [3]BINDISH R,BARROS A P.Multifrequency soil moisture inversion from SAR measurements with the use of IEM[J].Remote Sens.Environ.,2000,71(1):67-88.
- [4]RAO K S,RAJU S,WANG J R.Estimation of soil moisture and surface roughness parameters from backscattering coefficients[C]//IEEE Transaction on Geoscience and Remote Sensing,1993,31(31):1094-1099.
- [5]王悦泉,金亚秋.陆地表面粗糙度和土壤湿度多维参数同时反演的遗传算法[J].遥感学报,2000,4(2):90-94.
- [6]庞自振,廖静娟.基于遗传算法和雷达后向散射系数的地表参数反演研究[J].遥感技术与应用,2008,23(2):130-141.
- [7]NOTARNICOLA C,ANGIULLI M,POSA F.Soil moisture retrieval from remotely sensed data:neural network approach versua bayesian method[C]//IEEE Transaction on Geoscience and Remote Sensing,2008,46(2):547-557.
- [8]VAPNIK V.Statistical learning theory[M].New York:Wiley,1998.
- [9]CRISTIANINI N,TAYLOR J S.An introduction to support vector machine[M].U.K.:Cambridge Univ.Press,2000.
- [10]DREZET P M L,HARRISON R F.Support vector machines for system identification[C]//Control’98,UKACC International Conference,1998(1):688-692.
- [11]GESTEL T V,SUYKENS J A K,BAESTAENS D,et al.Financial time series prediction using least squares support vector machines within the evidence framework[C]//IEEE Transaction on Neural Networks,2001,12(4):809-821.
- [12]张清河,汪洋,陈将宏.基于支持向量机的复合柱体目标参数反演[J].电波科学学报,2012,27(6):1232-1237.
- [13]FUNG A K,LI Z,CHEN K S.Backscattering from a randomly rough dielectric surface[C]//IEEE Transaction on Geoscience and Remote Sensing,1992,30(2):356-369.
- [14]乌拉比,穆尔,冯健超.微波遥感(第二卷)[M].北京:科学出版社,1987.
- [15]HALLIKAINEN M T,ULABY F T,DOBSON M C,et al.Microwave dielectric behavior of wet soil-partⅠ:empirical models and experimental observations[C]//IEEE Transaction on Geoscience and Remote Sensing,1985,23(1):25-34.
- [16]OH Y.Quantitative retrieval of soil moisture content and surface roughness from multipolarized radar observations of bare soil surfaces[C]//IEEE Transaction on Geoscience and Remote Sensing,2004,42(3):596-601.