干旱区生态环境知识资源中心(Arid): 基于SVM的绿洲荒漠交错带土壤水分与地下水埋深反演

Arid

	基于SVM的绿洲荒漠交错带土壤水分与地下水埋深反演
其他题名	Inversion of Soil Moisture and Shallow Groundwater Depth Based on SVM in Arid Oasis-Desert Ecotone
	张钧泳 1; 丁建丽1 ; 谭娇 2
来源期刊	农业机械学报
ISSN	1000-1298
出版年	2019
卷号	50 期号:3 页码:221-230
中文摘要	为深入研究浅层地下水、植被和土壤的相互作用,以新疆渭干河-库车河绿洲为研究区,通过Sentinel-1A数据和Landsat数据以及土壤含水率、地下水埋深数据,结合植被以及土壤条件,通过支持向量机模型(Support vector machine,SVM)定量反演研究区土壤水分以及地下水埋深信息.结果表明:0~10cm的土壤含水率与地下水埋深之间的相关性最高.通过地形校正C模型(Topographic correction model),得到温度植被干旱指数(Temperature vegetation drought index,TVDI)精度有所提高.建立不同参数的SVM模型反演地下水埋深可行,对于单因子建模,TVDI_(MSAVI)构建的模型精度最高,建模集R~2=0.74,均方根误差(Root mean square error,RMSE)为4.66%,验证集R~2=0.70,RMSE为4.65%.相比只考虑单因子(后向散射系数(sigma_(soil)~0)或TVDI),sigma_(soil)~0和TVDI_(MSAVI)组合共同作用于模型精度最好,建模集R~2=0.86,RMSE为4.16%,验证集R~2=0.92,RMSE为2.73%.利用最优模型参数结果反演土壤水分区域和地下水埋深区域,其结果精度较好.地下水埋深反演结果平均相对误差为8.23%,优于研究区以往研究18.06%的结果.
英文摘要	In order to further study the interaction between shallow groundwater, vegetation and soil of arid and semi-arid regions, the database of the Sentinel-1A, Landsat images, soil moisture and the groundwater depth were utilized to quantitatively analyze the information of soil moisture and groundwater depth in the study area by the model of support vector machine (SVM) regression algorithm. Furthermore, the comparison of optical remote sensing and microwave remote sensing collaborative inversion in soil moisture and groundwater depth was also analyzed. By the survey of soil moisture and groundwater depth in the study area, the results indicated that the highest accuracy in SVM model was the correlation between soil water content in 0~10cm and groundwater depth. The accuracy of temperature vegetation drought index (TVDI) was improved, through the C calibration model. It was feasible to invert the groundwater depth by SVM model with different parameters. For single factor modeling, the model constructed by TVDI_(MSAVI) had the highest accuracy and the R~2 of modeling set was 0.74, the value of RMSE was 4.66%, and the R~2 of verification set was 0.70, the value of RMSE was 4.65%, compared with only single factor (sigma_(soil)~0 or TVDI), sigma_(soil)~0 and TVDI_(MSAVI) combination work with the highest model accuracy, R~2 was 0.86, and RMSE was 4.16%, the R~2 of verification set was 0.92, and RMSE was 2.73%. The results of the optimal model parameters were used to retrieve the soil moisture and groundwater with good accurate. The average relative error of groundwater was 8.23%, which was better than the previous results of the study area of 18.06%.
中文关键词	地下水埋深 ; 土壤含水率 ; 支持向量机 ; T_s-VI特征空间
英文关键词	Sentinel-1A groundwater depth soil moisture content Sentinel-1A support vector machine T_s-VI feature space
语种	中文
国家	中国
收录类别	CSCD
WOS类目	REMOTE SENSING
WOS研究方向	Remote Sensing
CSCD记录号	CSCD:6448851
来源机构	新疆大学
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/239358
作者单位	1.新疆大学资源与环境科学学院;;新疆大学, ;;智慧城市与环境建模新疆自治区普通高校重点实验室, 乌鲁木齐;;乌鲁木齐, ;; 830046;;830046; 2.新疆大学;;新疆财经大学计算机科学与工程学院, 智慧城市与环境建模新疆自治区普通高校重点实验室;;, 乌鲁木齐;;乌鲁木齐, ;; 830046;;830032
推荐引用方式 GB/T 7714	张钧泳,丁建丽,谭娇. 基于SVM的绿洲荒漠交错带土壤水分与地下水埋深反演[J]. 新疆大学,2019,50(3):221-230.
APA	张钧泳,丁建丽,&谭娇.(2019).基于SVM的绿洲荒漠交错带土壤水分与地下水埋深反演.农业机械学报,50(3),221-230.
MLA	张钧泳,et al."基于SVM的绿洲荒漠交错带土壤水分与地下水埋深反演".农业机械学报 50.3(2019):221-230.