全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

CART集成学习方法估算平原河网区不透水面覆盖度

DOI: 10.6046/gtzyyg.2013.04.28, PP. 174-179

Keywords: 不透水面,分类回归树,变精度粗糙集,TVDI,平原河网地区

Full-Text   Cite this paper   Add to My Lib

Abstract:

快速扩展的不透水面已成为影响高密度河网生态系统的主要因素。以平原河网城市的典型区域苏锡常地区为研究区,提出了一种基于分类与回归树(classificationandregressiontree,CART)集成学习的不透水面覆盖度(impervioussurfacepercentage,ISP)遥感估算方法,利用LandsatTM数据构建多源特征集,采用变精度粗糙集进行数据约简,以获取CART决策树的最佳属性变量,结果优于传统的单一CART方法,但得到的初始估算结果中ISP高值区低估现象较为严重,借助温度植被干旱指数(temperaturevegetationdrynessindex,TVDI)与ISP的相关性,寻找后处理规则对其进行改善。实验结果表明,经变精度粗糙集进行属性约简和TVDI后处理的CART集成学习方法估算精度明显提高,ISP估算值与ISP参考值之间的均方根误差为10.0%,决定系数为0.89,可用于平原河网地区ISP的估算。

References

[1]  王浩,吴炳方,李晓松,等.流域尺度的不透水面遥感提取[J].遥感学报,2011(2):388-400. Wan H,Wu B F,Li X S,et al.Extraction of impervious surface in Hai Basin using remote sensing[J].Journal of Remote Sensing,2011(2):388-400.
[2]  Herold N D,Koeln G,Cunnigham D.Mapping impervious surfaces and forest canopy using classification and regression tree (CART) analysis[C]//Droceedings of the 2003 ASPRS Annual Convention,Anchorage,AK.CD-ROM American Society for Photo grammetry and Remote Sensing,2003.
[3]  马雪梅,雷秀丽,李希峰,等.基于数据挖掘技术的流域不透水面及变化信息提取[J].测绘通报,2008(12):34-37. Ma X M,Li X l,Li X F,et al.Extracting valley impervious surfaces and it's change information based on the technology of data mining[J].Bulletin of Surveying and Mapping,2008(12):34-37.
[4]  廖明生,江利明,林珲,等.基于CART集成学习的城市不透水层百分比遥感估算[J].武汉大学学报:信息科学版,2007(12):1099-1102. Liao M S,Jiang L M,Lin H,et al.Estimating urban impervious surface percent using boosting as a refinement of CART analysis[J].Geomatics and Information Science of Wuhan University,2007(12):1099-1102.
[5]  Yang L,Huang C,Homer C G,et al.An approach for mapping large-area impervious surfaces:Synergistic use of Landsat-7 ETM+ and high spatial resolution imagery[J].Canadian Journal of Remote Sensing,2003,29(2):230-240.
[6]  Lu D,Weng Q.Spectral mixture analysis of the urban landscape in Indianapolis with Landsat ETM+ imagery[J].Photogrammetric Engineering and Remote Sensing,2004,70(9):1053-1062.
[7]  Ridd M K.Exploring a VIS (vegetation-impervious surface-soil) model for urban ecosystem analysis through remote sensing: Comparative anatomy for cities[J].International Journal of Remote Sensing,1995,16(12):2165-2185.
[8]  Ziarko W.Variable precision rough set model[J].Journal of Computer and System Sciences,1993,46(1):39-59.
[9]  王琳.基于不完备信息系统的VPRSM的规则获取方法研究[D].北京:中国石油大学,2009. Wan L.Research of rules extraction method based on VPRSM in incomplete information systems[D].Beijing:China University of Petroleum (EastChina),2009.
[10]  邵蔚.基于特征选择的水利空间要素识别研究[D].南京:河海大学,2011. Shao W.Water spatial element recognition research based on feature selection[D].Nanjing:Hohai university,2011.
[11]  常志玲,周庆敏.基于变精度粗糙集的决策树优化算法研究[J].计算机工程与设计,2006(17):3175-3177. Chang Z L,Zhou Q M.Method based on variable precision rough set to build decision tree[J].Computer Engineering and Design,2006(17):3175-3177.
[12]  赵越岭,王建辉,顾树生.基于变精度粗糙集阈值的选取[J].控制与决策,2007,22(1):78-80. Zhao Y L,Wang J H,Gu S S.Choiceof threshold value based on variable precision rough sets[J].Control and Decision,2007,22(1):78-80.
[13]  王文种,张友静.半干旱区旱情监测指数应用分析[J].地球信息科学,2008,10(2):273-278. Wang W,Zhang Y J.Drought monitoring index and its application in semiarid area[J].Geo-Information Science,2008,10(2):273-278.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133