干旱区生态环境知识资源中心(Arid): 基于决策树的干旱区湿地信息自动提取以疏勒河流域为例

Arid

	基于决策树的干旱区湿地信息自动提取以疏勒河流域为例
其他题名	The Automatic Extraction of Wetland Information in Arid Zone based on Decision Tree Algorithm A Case Study in the Shule River Basin
	韩忻忆; 颉耀文
来源期刊	遥感技术与应用
ISSN	1004-0323
出版年	2015
卷号	30 期号:6 页码:1146-1152
中文摘要	以疏勒河流域为研究区,探讨了干旱区湿地的遥感影像自动提取方法。以Landsat 8卫星影像数据为主要数据源并辅以数字高程模型(DEM),利用改进的干旱区湿地指数(MAZWI)、归一化植被指数(NDVI)、地表反照率(Albedo)、灰度共生矩阵(GLCM)的非相似性分量等识别指数构建决策树模型,对研究区湿地进行提取,并将结果与最大似然分类结果进行对比。结果表明:该方法在一定程度上提高了湿地提取的精度,与最大似然分类结果相比总体精度和Kappa系数分别提高了6.52%和0.124。证明决策树法是干旱区水域湿地自动提取的一种有效手段。
英文摘要	Selecting the Shule River Basin which locates in the west of Gansu Province as the study area,the automated extraction method for wetlands in arid regions was discussed.Using the Landsat 8satellite images as the data sources,supported by the digital elevation model(DEM),the modified arid zone wetlands index(MAZWI),the normalized difference vegetation indices(NDVI)and the surface albedo,and the identification of dissimilarity index of the gray level co-occurrence matrix(GLCM),were used as the indicators to establish the decision tree model and the wetlands were extracted.Comparing with the results obtaining by the maximum likelihood supervised classification,it showed that the decision tree method based on the indices can improve the overall accuracy by 6.52%and the overall kappa coefficient by 0.1243.The results of this study suggested that the decision tree method based on indices is an effective tool for wetlands classification in arid zone.
中文关键词	干旱区湿地 ; 决策树 ; 信息提取 ; 遥感分类
英文关键词	Arid zone Decision tree Information extraction Remote sensing classification
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:5617955
来源机构	兰州大学
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/233560
作者单位	兰州大学资源环境学院, 兰州, 甘肃 730000, 中国
推荐引用方式 GB/T 7714	韩忻忆,颉耀文. 基于决策树的干旱区湿地信息自动提取以疏勒河流域为例[J]. 兰州大学,2015,30(6):1146-1152.
APA	韩忻忆,&颉耀文.(2015).基于决策树的干旱区湿地信息自动提取以疏勒河流域为例.遥感技术与应用,30(6),1146-1152.
MLA	韩忻忆,et al."基于决策树的干旱区湿地信息自动提取以疏勒河流域为例".遥感技术与应用 30.6(2015):1146-1152.