干旱区生态环境知识资源中心(Arid): 基于决策树的干旱区盐碱化土壤信息提取方法研究

Arid

	基于决策树的干旱区盐碱化土壤信息提取方法研究
其他题名	Extraction of Salinized Soil Information in Arid Area Based on the Decision Tree
	姜亮亮; 刘海隆; 安小艳; 任艳群
来源期刊	土壤通报
ISSN	0564-3945
出版年	2014
卷号	45 期号:4 页码:801-808
中文摘要	土壤盐碱化是制约干旱区植被生长最主要的生态环境地质问题,也是土地资源利用的主要障碍因子之一。利用遥感数据准确自动的提取盐碱化土壤信息对土壤的盐碱化的提取和动态监测具有重要意义。以新疆石河子150团为研究区域,使用2010年8月和2005年7月的ETM数据提取归一化植被指数(NDVI)、第一主成分(PC1),分别作为非盐碱化土壤和盐碱化土壤信息提取的主要特征变量,然后用改进归一化差异水体指数(MNDWI)、TM7、Mean作为辅助特征变量,结合研究区的实地考察和典型土样的遥感信息以及与缨帽变化(K-T)对比分析来确定各个特征变量的阀值,利用决策树,对研究区遥感图像进行了分类。研究结果显示,基于决策树的干旱区盐碱化土壤信息提取方法是可行的并能达到较高的精度。
英文摘要	The soil salinization was the major ecological environmental geological problem which was constraining vegetation growth in arid area. It was also one of major constraints on land resource utilization. Remote sensing data were of great practical significance to accurately and automatically extract salinized soil information in order to monitor soil salinization. This research investigated soil salinization in Group 150 of Shihezi, Xinjiang Province. ETM data in August 2010 and July 2005 were used to extract normalized difference vegetation index (NDVI) and the first principal component (PC1). They were specified as the major characteristic variables for information extraction of nonsalinized soil and salinized soils respectively. Subsequently, modified normalized difference water index (MNDWI), TM1 and TM7 were cited as supplementary characteristic variables, which were used to determine the threshold value of each characteristic variable by combining the field study with remote sensing information of typical soil sample and comparative analysis with K-T transformation. The RS images was classified using the decision tree. The results implied that it was feasible and reached high accuracy on automaticly extracting arid salinized soil information basd on the decision tree.
中文关键词	干旱区 ; 遥感 ; 土壤盐碱化 ; 决策树 ; K-T变化
英文关键词	Arid area Remote sensing Soil salinization Decision tree classification K-T transformation
语种	中文
国家	中国
收录类别	CSCD
WOS类目	AUTOMATION CONTROL SYSTEMS
WOS研究方向	Automation & Control Systems
CSCD记录号	CSCD:5207135
来源机构	石河子大学
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/231844
作者单位	石河子大学水利建筑工程学院, 石河子, 新疆 832000, 中国
推荐引用方式 GB/T 7714	姜亮亮,刘海隆,安小艳,等. 基于决策树的干旱区盐碱化土壤信息提取方法研究[J]. 石河子大学,2014,45(4):801-808.
APA	姜亮亮,刘海隆,安小艳,&任艳群.(2014).基于决策树的干旱区盐碱化土壤信息提取方法研究.土壤通报,45(4),801-808.
MLA	姜亮亮,et al."基于决策树的干旱区盐碱化土壤信息提取方法研究".土壤通报 45.4(2014):801-808.