基于SVR的旱区稀疏植被覆盖下土壤水分遥感反演

doi:10.12082/dqxxkx.2019.180685

地球信息科学学报 ›› 2019, Vol. 21 ›› Issue (8): 1275-1283.doi: 10.12082/dqxxkx.2019.180685

基于SVR的旱区稀疏植被覆盖下土壤水分遥感反演

王雅婷¹,孔金玲^2,^*(),杨亮彦¹,李健锋¹,张文博¹

^1. 长安大学地球科学与资源学院,西安 710054
^2. 长安大学地质工程与测绘学院,西安 710054

收稿日期:2018-12-25 修回日期:2019-04-26 出版日期:2019-08-25 发布日期:2019-08-25
作者简介:王雅婷（1993-）,女,山东烟台人,硕士生,主要从事定量遥感反演研究。E-mail: ytwang_chd@126.com
基金资助:
国家自然科学基金项目(41272246)

Remote Sensing Inversion of Soil Moisture in Vegetation-Sparse Arid Areas based on SVR

WANG Yating¹,KONG Jinling^2,^*(),YANG Liangyan¹,LI Jianfeng¹,ZHANG Wenbo¹

^1. School of Earth Science and Resources, Chang'an University, Xi'an 710054, China
^2. School of Geological Engineering and Geomatics, Chang'an University, Xi'an 710054, China

Received:2018-12-25 Revised:2019-04-26 Online:2019-08-25 Published:2019-08-25
Contact: KONG Jinling
Supported by:
National Natural Science Foundation of China(41272246)

摘要/Abstract

摘要：

中国西北半干旱区降水稀少、蒸散强烈,土壤水分作为重要的生态因子,影响着土壤-大气界面的能量平衡。支持向量回归模型具有估算精度高、可处理非线性问题、泛化能力强等优点,近年来被应用于土壤水分反演研究中,但已有模型极少考虑地表粗糙度因素的影响,导致反演精度受到一定限制。因此,本文以内蒙古乌审旗为研究区,采用水云模型去除地表稀疏植被覆盖的影响,提取全极化Radarsat-2 SAR影像裸土后向散射系数（ $σ soil 0$ ）,并利用AIEM模型和Oh模型建立后向散射系数数据库,采用LUT法模拟地表有效粗糙度参数,构建基于支持向量回归的土壤水分反演模型,并系统地对比分析了不同极化方式的后向散射系数作为数据源的土壤水分反演结果。研究结果表明：不考虑粗糙度参数的单数据源作为模型参数时,同极化数据反演结果比交叉极化具有更高的反演精度;当模型参数为考虑粗糙度的多源数据时,不同极化数据的反演精度均有所提高,其中数据源为 $σ vv 0$ 和粗糙度参数时,反演结果最好（R ²=0.917,MAE=3.980%,RMSE=5.187%）。研究结果可为旱区稀疏植被覆盖地表土壤水分的遥感监测提供技术支持。

关键词: SVR, Radarsat-2, AIEM模型, 有效粗糙度参数, 土壤水分反演, 西北半干旱区, 内蒙古乌审旗, 稀疏植被

Abstract:

In the arid and semi-arid regions of northwest China, the precipitation is scarce and evapotranspiration is intense. Soil moisture, as an important ecological factor, affects the energy balance of soil-atmosphere interface. In recent years, Support Vector Regression(SVR) model has been applied in soil moisture inversion for its merits including, high estimation accuracy, good ability to deal with non-linear processing and strong generalization ability. However, existing models rarely consider the influence of surface roughness, which limits of inversion accuracy. Taking the Uxin Banner of Ordos city of Inner Mongolia as a study area, this study aims to construct a suitable soil moisture inversion model through combining Radarsat-2 synthetic aperture radar(SAR) data and GF-1 data. To extract backscattering coefficient of bare soil( $σ soil 0$ ) from the full polarization Radarsat-2 SAR data, we used Water-Cloud model(WCM) to remove the influence of vegetation-sparse layer on the radar backscattering coefficient. Meanwhile, we constructed backscattering coefficient database of bare soil by using Advanced Integrated Equation Model(AIEM) and Oh Model, and used Look Up Table (LUT) method to simulate effective surface roughness parameters such as root mean square height(S) and correlation length(L). Finally, the soil moisture model was built based on support vector regression, and the soil moisture inversion results of different data sources under the backscattering coefficients of different polarization modes were systematically compared and analyzed. The results showed that the inversion accuracy of the co-polarization data (VV polarization or HH polarization) was higher than that of the cross-polarization data(VH polarization or HV polarization) when the single data source without considering the roughness parameter was used as the model parameter. When the model parameter was the multi-source data with considering the roughness parameter, the inversion accuracy of different polarization data was improved. When the data source was $σ vv 0$ and roughness parameter, the inversion model had a higher precision, the correlation coefficient between inversion value and measured value was 0.917. The mean absolute error(MAE) and root mean square error(RMSE) were 3.980% and 5.187%, respectively. Our findings can serve as the technical support for remote sensing of surface soil moisture in vegetation-sparse arid areas.

Key words: SVR, Radarsat-2, AIEM model, effective roughness parameter, soil moisture inversion, semi-arid regions of northwest China, Uxin Banner of Inner Mongolia, vegetation-sparse

王雅婷,孔金玲,杨亮彦,李健锋,张文博. 基于SVR的旱区稀疏植被覆盖下土壤水分遥感反演[J]. 地球信息科学学报, 2019, 21(8): 1275-1283.DOI:10.12082/dqxxkx.2019.180685

WANG Yating,KONG Jinling,YANG Liangyan,LI Jianfeng,ZHANG Wenbo. Remote Sensing Inversion of Soil Moisture in Vegetation-Sparse Arid Areas based on SVR[J]. Journal of Geo-information Science, 2019, 21(8): 1275-1283.DOI:10.12082/dqxxkx.2019.180685

图/表 7

图1

图2

图3

图4

图5

表1

不同数据源的土壤水分反演精度对比

模型输入变量	R²	MAE/%	RMSE/%	模型输入变量	R²	MAE/%	RMSE/%
$σ vv 0$	0.874	4.550	6.200	$σ vv 0$ -Zs	0.917	3.980	5.187
$σ hh 0$	0.778	6.401	7.768	$σ hh 0$ -Zs	0.881	6.100	7.484
$σ vh 0$	0.256	10.121	15.094	$σ vh 0$ -Zs	0.660	8.676	10.520
$σ hv 0$	0.226	13.106	14.905	$σ hv 0$ -Zs	0.584	9.007	10.855

表1

图6

参考文献 19

[1]	Mladenova I E, Jackson T J, Njoku E , et al. Remote monitoring of soil moisture using passive microwave-based techniques: Theoretical basis and overview of selected algorithms for AMSR-E[J]. Remote Sensing of Environment, 2014,144(4):197-213.
[2]	胡蝶, 郭铌, 沙莎 , 等. 基于Radarsat-2 SAR数据反演定西裸露地表土壤水分[J]. 干旱气候, 2014,32(4):553-559.
	[ Hu D, Guo N, Sha S , et al. Retrieval of bare soil moisture based on radarsat-2 SAR in Dingxi of Gansu province[J]. Journal of Arid Meteorology, 2014,32(4):553-559. ]
[3]	杨涛, 宫辉力, 李小娟 , 等. 土壤水分遥感监测研究进展[J]. 生态学报, 2010,30(22):6264-6277.
	[ Yang T, Gong H L, Li X J , et al. Progress of soil moisture monitoring by remote sensing[J]. Acta Ecologica Sinica, 2010,30(22):6264-6277. ]
[4]	Kong J L, Yang J, Zhen P P , et al. A coupling model for soil moisture retrieval in sparse vegetation covered areas based on microwave and optical remote sensing data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018,56(12):7162-7173.
[5]	Khedri E, Hasanlou M, Tabatabaeenejad A. Estimating soil moisture using polsar data: a machine learning approach[J]. ISPRS-International Archives of the Photogrammetry,Remote Sensing and Spatial Information Sciences , 2017, XLII-4/W4:133-137.
[6]	Ahmad S, Kalra A, Stephen H . Estimating soil moisture using remote sensing data: A machine learning approach[J]. Advances in Water Resources, 2010,33(1):69-80. doi: 10.1016/j.advwatres.2009.10.008
[7]	曾旭婧, 邢艳秋, 单炜 , 等. 基于Sentinel-1A与Landsat 8数据的北黑高速沿线地表土壤水分遥感反演方法研究[J]. 中国生态农业学报, 2017,25(1):118-126.
	[ Zeng X J, Xing Y Q, Shan W , et al. Soil water content retrieval based on Sentinel-1A and Landsat 8 image for Bei'an-Heihe Expressway[J]. Chinese Journal of Eco-Agriculture, 2017,25(1):118-126. ]
[8]	姜红 , 玉素甫江·如素力,拜合提尼沙.阿布都克日木,等.基于支持向量机回归算法的土壤水分光学与微波遥感协同反演[J]. 地理与地理信息科学, 2017,33(6):30-36.
	[ Jiang H, Yusufujiang R, Baihetinisha A , et al. Soil moisture retrieval by synergizing optical and microwave remote sensing data based on support vector machine regression algorithm[J]. Geography and Geo-information Science, 2017,33(6):30-36. ]
[9]	Attema E P W, Ulaby F T . Vegetation modeled as a water cloud[J]. Radio Science, 1978,13(2):357-364.
[10]	Bindlish R, Barros A P . Parameterization of vegetation backscatter in radar-based, soil moisture estimation[J]. Remote Sensing of Environment, 2001,76(1):130-137.
[11]	Svoray T, Shoshany M . SAR-based estimation of areal aboveground biomass (AAB) of herbaceous vegetation in the semi-arid zone: A modification of the water-cloud model[J]. International Journal of Remote Sensing, 2010,23(19):4089-4100.
[12]	Fung A K, Chen K S . An update on the IEM surface backscattering model[J]. IEEE Geoscience and Remote Sensing Letters, 2004,1(2):75-77.
[13]	Oh Y, Sarabandi K, Ulaby F T . An empirical model and an inversion technique for radar scattering from bare soil surfaces[J]. IEEE Transaction on Geoscience and Remote Sensing, 1992,30(2):370-381.
[14]	Oh Y, Sarabandi K, Ulaby F T . Semi-empirical model of the ensemble-averaged differential mueller matrix for microwave backscattering from bare soil surfaces[J]. IEEE Transaction on Geoscience and Remote Sensing, 2002,40(6):1348-1355.
[15]	Lievens H , Verhoest N E C, Keyser E D.Effective roughness modelling as a tool for soil moisture retrieval from C- and L-band SAR[J]. Hydrology and Earth System Science, 2011,15(1):151-162.
[16]	孔金玲, 甄珮珮, 李菁菁 , 等. 基于新的组合粗糙度参数的土壤水分微波遥感反演[J]. 地理与地理信息科学, 2016,32(3):34-38.
	[ Kong J L, Zhen P P, Li J J , et al. Retrieval of soil moisture using microwave remote sensing data based on a new combined roughness parameter[J]. Geography and Geo-information Science, 2016,32(3):34-38. ]
[17]	孔金玲, 李菁菁, 甄珮珮 , 等. 微波与光学遥感协同反演旱区地表土壤水分研究[J]. 地球信息科学学报, 2016,18(6):857-863.
	[ Kong J L, Li J J, Zhen P P , et al. Inversion of soil moisture in arid area based on microwave and optical remote sensing data[J]. Journal of Geo-information Science, 2016,18(6):857-863. ]
[18]	王慧勤 . 基于支持向量机的短期风速预测方法研究[D]. 西安:西安科技大学, 2009.
	[ Wang H Q . Study on methods of short-term wind speed forecast based on support vector machine[D]. Xi'an. Xi'an University of Science and.Technology, 2009. ]
[19]	杨浩, 孟娜, 王婧 , 等. 基于支持向量机的京津冀城市群热环境时空形态模拟[J]. 地球信息科学学报, 2019,21(2):190-200.
	[ Yang H, Meng N, Wang J , et al. Spatial-temporal morphology simulation of Beijing-Tianjin-Hebei urban agglomeration thermal environment based on support vector machine[J]. Journal of Geo-information Science, 2019,21(2):190-200. ]

基于SVR的旱区稀疏植被覆盖下土壤水分遥感反演

Remote Sensing Inversion of Soil Moisture in Vegetation-Sparse Arid Areas based on SVR

RichHTML

PDF (PC)

赞

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 19

相关文章 2

Metrics

本文评价

推荐阅读 0

[1]	孔金玲, 李菁菁, 甄珮珮, 杨笑天, 杨晶, 吴哲超. 微波与光学遥感协同反演旱区地表土壤水分研究[J]. 地球信息科学学报, 2016, 18(6): 857-863.
[2]	魏小兰, 李震, 陈权. S波段雷达数据反演土壤水分的模拟分析和验证[J]. 地球信息科学学报, 2008, 10(1): 97-101,108.