当前位置: 首页 > 文章 > 基于单时相MODIS数据的土地覆盖三种分类方法对比研究 干旱地区农业研究 2008,26 (3) 253-258
Position: Home > Articles > Comparison of the land cover classification methods based on single-temporal MODIS data Agricultural Research in the Arid Areas 2008,26 (3) 253-258

基于单时相MODIS数据的土地覆盖三种分类方法对比研究

作  者:
徐晓桃;韩涛;颉耀文
单  位:
中国气象局兰州干旱气象研究所甘肃省干旱气候变化与减灾重点实验室中国气象局干旱气候变化与减灾重点开放实验室;兰州大学西部环境教育部重点实验室
关键词:
MODIS;最大似然法;BP神经网络;决策树;See5.0;土地覆盖分类
摘  要:
以甘肃省为试验区,基于单时相MODIS数据,主要利用其可见光多波段光谱信息,分别使用最大似然法、BP神经网络算法以及基于See 5.0数据挖掘的决策树分类方法对土地覆盖进行了自动分类研究,结果验证表明:决策树分类性能最优,总分类精度达到82.13%,神经网络算法次之,总分类精度为77.60%,最大似然法最差,总分类精度为73.93%;加入boosting技术的See 5.0数据挖掘决策树方法能够快速地进行决策树的建立且能很好地提高较难识别地物类型的分类精度。
译  名:
Comparison of the land cover classification methods based on single-temporal MODIS data
作  者:
XU Xiao-tao1,HAN Tao2,XIE Yao-wen1(1.Key Laboratory of Western China's Environmental Systems(Ministry of Education),Lanzhou University,Lanzhou,Gansu 730000,China;2.Institute of Arid Meteorology,CMA,Lanzhou,Key Laboratory of Arid Climatic Changing and Reducing Disaster of Gansu GOV and CMA,Lanzhou,Gansu 730020,China)
关键词:
MODIS;maximum likelihood classifier;BP neural network;decision tree classifier;See 5.0;land cover classification
摘  要:
Based on single-temporal MODIS data of Gansu Province,mainly using its visible spectra,three classifiers-the maximum likelihood,BP neural network and decision tree based on data mining software of See 5.0 are used for land cover classification research.The validated result shows that the decision tree algorithm has the best performance of extraction,with an overall accuracy of 82.13%,followed by the BP network algorithm,and the maximum likelihood classifier has the worst performance.Data mining software of See 5.0 with boosting technique can build decision tree quickly and improve the precision of miscible classes.

相似文章

计量
文章访问数: 12
HTML全文浏览量: 0
PDF下载量: 0

所属期刊

推荐期刊