Please wait a minute...
img

官方微信

遥感技术与应用  2009, Vol. 24 Issue (5): 648-653    DOI: 10.11873/j.issn.1004-0323.2009.5.648
技术研究与图像处理     
基于C5.0决策树算法的西北干旱区土地覆盖分类研究——以甘肃省武威市为例
齐红超,祁 元,徐 瑱
中国科学院寒区旱区环境与工程研究所,甘肃 兰州
The Study of the Northwest Arid Zone Land-Cover Classification Based on C5.0 Decision Tree Algorithm at Wuwei City,Gansu Province
 QI Hong-chao,QI Yuan,XU Zhen
730000Cold and Arid Regions Environmental and Engineering Research Institute,Chinese Academy ofSciences,Lanzhou 730000,China
 全文: PDF(1018 KB)  
摘要:

西北干旱区面积广阔,由于土地利用类型多样,成因复杂,对环境变化敏感、变化过程快、幅度大、景观差异明显等特点,在影像上表现出的“同物异谱”现象明显 |利用常规目视解译、监督非监督分类、人工参与的决策树分类等方法在效率或精度等方面各有其缺陷。采用机器学习C5.0决策树算法,综合利用地物波谱、NDVI、TC、纹理等信息,根据样本数据自动挖掘分类规则并对整个研究区进行地物分类。机器学习的决策树可以挖掘出更多的分类规则,C5.0算法对采样数据的分布没有要求,可以处理离散和连续数据,生成的规则易于理解,分类精度高,可以满足西北干旱区大面积的土地利用/覆被变化制图的需要。

关键词: C5.0算法 西北干旱区 土地覆被 See5.0 NLCD    
Abstract:

In the broadly northwest arid regions,frequently,same object has different spectral characters because of the special characteristics of land cover change such as complex causes of formation,sensitivity to environment change,rapid and violent change and obvious differences in landscape.The conventional methods of classification including visual interpretation,supervised classification,unsupervised classification,and artificial decision tree classification have disadvantages in the efficiency or the accuracy.In this paper,machine learning algorithm based on C5.0 decision tree was used to classify the entire study area automatically according to the sample data mining classification rules.Spectral features,NDVI,TC,texture and other informations were involved in the algorithm.More classification rules could be mined by machine learning decision tree.C5.0 algorithm handling with both continuous and discrete data is independent of the distribution of sampling sites,The classification rules mined by this algorithm were interpretable.Other superiority of this algorithm included the fast speed of training and higher accuracy than many other classifiers.Thus,it is able to be used in the mapping of land use/cover change in a large scale in northwest arid regions.

 

Key words: C5.0 algorithm    The northwest arid region    Land cover    See5.0    NLCD
收稿日期: 2009-05-27 出版日期: 2010-08-24
基金资助:

国家自然科学基金面上项目(40501069)资助。

作者简介: 齐红超(1983-),男,硕士研究生,研究方向为GIS与RS在资源与环境中的应用。E-mail:qihongchao@hotmail.com。
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
齐红超
祁 元
徐 瑱

引用本文:

齐红超, 祁 元, 徐 瑱. 基于C5.0决策树算法的西北干旱区土地覆盖分类研究——以甘肃省武威市为例[J]. 遥感技术与应用, 2009, 24(5): 648-653.

QI Hong-Chao, QI Yuan, XU Tian. The Study of the Northwest Arid Zone Land-Cover Classification Based on C5.0 Decision Tree Algorithm at Wuwei City,Gansu Province. Remote Sensing Technology and Application, 2009, 24(5): 648-653.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2009.5.648        http://www.rsta.ac.cn/CN/Y2009/V24/I5/648

[1] Li Xiubin.A Review of the International Researches on Land Use /Land Cover Change[J].Acta Geographica Sinica,1996,51(6):553-557.[李秀彬.全球环境变化研究的核心领域——土地利用/土地覆被变化的国际研究动向[J].地理学报,1996,51(6):553-557.]


[2] Xie Yaowen,Chen Fahu.The Land Use / Land Cover Change in Arid Region and the Global Environment Change[J].Areal Research and Development,2002,21(2):21-26.[颉耀文,陈发虎.干旱区土地利用/土地覆盖变化与全球环境变化[J].地域研究与开发,2002,21(2):21-26.]


[3] Cilhar J.Land-cover Mapping of Large Areas from Satellites:Status and Research Priorities[J].International Journal of Remote Sensing,2000,21:1093-1114.


[4] Aspinall R.A Land-cover Data Infrastructure for Measurement,Modeling,and Analysis of Land-cover Change Dynamics[J].Photogrammetric Engineering and Remote Sensing,2002,68(10):1101-1105.


[5] Muchoney D,Williamson J.A Gaussian Adaptive Resonance Theory Neural Network Classification Algorithm Applied to Supervised Land-cover Mapping Using Multi-temporal Vegetation Index Data[J].IEEE Transactions on Geoscience and Remote Sensing,2001,39(9):1969-1977.


[6] Rogan J.Mapping Land-cover Modifications over Large Areas[J].A Comparison of Machine Learning Algorithms Remote Sensing of Environment,2008,112:2272-2283.〖HJ2.125mm〗


[7] Homer C,Huang C Q,Yang L M,et al.Development of a 2001 National Land-cover Database for the United States[J].Photogrammetric Engineering & Remote Sensing,2004,70(7):829-840.


[8] Crist E P,Cicone R C.A Physically-based Transformation of Thematic Mapper Data——the TM Tasseled Cap[J].IEEE Trans.on Geosciences and Remote Sensing,1984,22:256-263.


[9] Cohen W B,Spies T A,Fiorella M.Estimating the Age and Structure of Forests in a Multi-ownership Landscape of Northwest Oregon,U.S.A.[J].International Journal of Remote Sensing,1995,16:721-746.


[10] Huang C Q,Wylie B.Derivation of a Tasseled Cap Transformation Based on Landsat7 At-Satellite Reflectance[S].USGS EROS Data Center White Paper.


[11] Haralick R M.Statistical and Structural Approaches to Texture[J].IEEE Proceedings,1979,67(5):786-804.


[12] Chen Liang,Zhang Youjing,Chen Bo.High Spatial Resolution Remote Sensing Image Classification Based on Decision Tree Classification Combined with Multi-scale Texture[J].Geography and Geo-Information Science,2007,23(4):18-21.[陈亮,张友静,陈波.2007年7月结合多尺度纹理的高分辨率遥感影像决策树分类[J].地理与地理信息科学,2007,23(4):18-21.]


[13] Quinian J R.C4.5.Programs for Machine Learning[M].San Mateo,CA:Morgan Kaufmann,1993.


[14] Wen Xingping,Hu Guangdao,Yang Xiaofeng.Extracting Information from ETM+ Image Using C5.0 Decision Tree Algorithm[J].Geography and Geo-Information Science,2007,23(6):26-29.[温兴平,胡光道,杨晓峰.基于C5.0决策树分类算法的ETM+影像信息提取[J].地理与地理信息科学,2007,23(6):26-29.]


[15] Zhao Ping,Fu Yunfei.Cart-based Land use /cover Classification of Remote Sensing Images[J].Journal of Remote Sensing,2005,9(6):708-716.[赵萍,傅云飞.基于分类回归树分析的遥感影像土地利用/覆被分类研究[J].遥感学报,2005,9(6):708-716.]


[16] Vogelmann J E,Sohl T,Howard S M.Regional Characterization of Land Cover Using Multiple Sources of Data[J].Photogrammetric of Engineering and Remote Sensing,1998,64:45-57.


[17] Zhang Feng,Wang Qiao.Development of Extraction for High-Resolution Land-cover Information in the United States[J].Remote Sensing Technology and Application,2006,21(6):593-600.[张峰,王桥.美国高分辨率土地覆盖信息提取技术研究进展[J].遥感技术与应用,2006,21(6):593-600].

[1] 胡云锋,商令杰,张千力,王召海. 基于GEE平台的1990年以来北京市土地变化格局及驱动机制分析[J]. 遥感技术与应用, 2018, 33(4): 573-583.
[2] 苏阳,祁元,王建华,徐菲楠,张金龙. 基于航空高光谱影像的额济纳绿洲土地覆被提取[J]. 遥感技术与应用, 2018, 33(2): 202-211.
[3] 陈栋栋,赵军. 我国西北干旱区湖泊变化时空特征[J]. 遥感技术与应用, 2017, 32(6): 1114-1125.
[4] 仇江啸, 王效科. 基于高分辨率遥感影像的面向对象城市土地覆被分类比较研究[J]. 遥感技术与应用, 2010, 25(5): 653-661.
[5] 李娟,赵军. 基于DEM的西北干旱区典型地貌类型坡度提取分析[J]. 遥感技术与应用, 2008, 23(2): 214-218.
[6] 陈 玲, 王根绪, 王惠林. 基于Landsat TM 数据的若尔盖县LUCC 时空特征研究[J]. 遥感技术与应用, 2006, 21(4): 277-283.
[7] 张宝雷, 宋孟强, 周万村. GIS 支持下三峡库区主要地类自动分类方法研究[J]. 遥感技术与应用, 2006, 21(1): 71-76.