Adv Search

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

Integrating TM and Ancillary Geographical Data with Classification Trees for Land Cover Classification of Marsh Area

NA Xiaodong,  ZHANG Shuqing,  ZHANG Huaiqing,  LI Xiaofeng,  YU Huan,  LIU Chunyue

downloadPDF
文章导航 > Chinese Geographical Science  > 2009 >  19(2): 177-185
NA Xiaodong, ZHANG Shuqing, ZHANG Huaiqing, LI Xiaofeng, YU Huan, LIU Chunyue. Integrating TM and Ancillary Geographical Data with Classification Trees for Land Cover Classification of Marsh Area[J]. 中国地理科学, 2009, 19(2): 177-185. doi: 10.1007/s11769-009-0177-y
引用本文: NA Xiaodong, ZHANG Shuqing, ZHANG Huaiqing, LI Xiaofeng, YU Huan, LIU Chunyue. Integrating TM and Ancillary Geographical Data with Classification Trees for Land Cover Classification of Marsh Area[J]. 中国地理科学, 2009, 19(2): 177-185. doi: 10.1007/s11769-009-0177-y
shu
NA Xiaodong, ZHANG Shuqing, ZHANG Huaiqing, LI Xiaofeng, YU Huan, LIU Chunyue. Integrating TM and Ancillary Geographical Data with Classification Trees for Land Cover Classification of Marsh Area[J]. Chinese Geographical Science, 2009, 19(2): 177-185. doi: 10.1007/s11769-009-0177-y
Citation: NA Xiaodong, ZHANG Shuqing, ZHANG Huaiqing, LI Xiaofeng, YU Huan, LIU Chunyue. Integrating TM and Ancillary Geographical Data with Classification Trees for Land Cover Classification of Marsh Area[J]. Chinese Geographical Science, 2009, 19(2): 177-185. doi: 10.1007/s11769-009-0177-y
shu

Integrating TM and Ancillary Geographical Data with Classification Trees for Land Cover Classification of Marsh Area

doi: 10.1007/s11769-009-0177-y
  • 1.

    Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, Changchun 130012, China;

  • 2.

    Graduate University of the Chinese Academy of Sciences, Beijing 100049, China;

  • 3.

    Institute of Resources Information, Chinese Academy of Forestry, Beijing 100091, China

基金项目: Under the auspices of National Natural Science Foundation of China (No. 40871188); National Key Technologies R&D Program of China (No. 2006BAD23B03)
详细信息
    通讯作者:

    ZHANG Shuqing.E-mail:shqzhang@263.net

Integrating TM and Ancillary Geographical Data with Classification Trees for Land Cover Classification of Marsh Area

  • 1.

    Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, Changchun 130012, China;

  • 2.

    Graduate University of the Chinese Academy of Sciences, Beijing 100049, China;

  • 3.

    Institute of Resources Information, Chinese Academy of Forestry, Beijing 100091, China

Funds: Under the auspices of National Natural Science Foundation of China (No. 40871188); National Key Technologies R&D Program of China (No. 2006BAD23B03)

  • 摘要: The main objective of this research is to determine the capacity of land cover classification combining spectral and textural features of Landsat TM imagery with ancillary geographical data in wetlands of the Sanjiang Plain, Heilongjiang Province, China. Semi-variograms and Z-test value were calculated to assess the separability of grey-level co-occurrence texture measures to maximize the difference between land cover types. The degree of spatial autocorrelation showed that window sizes of 3×3 pixels and 11×11 pixels were most appropriate for Landsat TM image texture calculations. The texture analysis showed that co-occurrence entropy, dissimilarity, and variance texture measures, derived from the Landsat TM spectrum bands and vegetation indices provided the most significant statistical differentiation between land cover types. Subsequently, a Classification and Regression Tree (CART) algorithm was applied to three different combinations of predictors: 1) TM imagery alone (TM-only); 2) TM imagery plus image texture (TM+TXT model); and 3) all predictors including TM imagery, image texture and additional ancillary GIS information (TM+TXT+GIS model). Compared with traditional Maximum Likelihood Classification (MLC) supervised classification, three classification trees predictive models reduced the overall error rate significantly. Image texture measures and ancillary geographical variables depressed the speckle noise effectively and reduced classification error rate of marsh obviously. For classification trees model making use of all available predictors, omission error rate was 12.90% and commission error rate was 10.99% for marsh. The developed method is portable, relatively easy to implement and should be applicable in other settings and over larger extents.
    Abstract: The main objective of this research is to determine the capacity of land cover classification combining spectral and textural features of Landsat TM imagery with ancillary geographical data in wetlands of the Sanjiang Plain, Heilongjiang Province, China. Semi-variograms and Z-test value were calculated to assess the separability of grey-level co-occurrence texture measures to maximize the difference between land cover types. The degree of spatial autocorrelation showed that window sizes of 3×3 pixels and 11×11 pixels were most appropriate for Landsat TM image texture calculations. The texture analysis showed that co-occurrence entropy, dissimilarity, and variance texture measures, derived from the Landsat TM spectrum bands and vegetation indices provided the most significant statistical differentiation between land cover types. Subsequently, a Classification and Regression Tree (CART) algorithm was applied to three different combinations of predictors: 1) TM imagery alone (TM-only); 2) TM imagery plus image texture (TM+TXT model); and 3) all predictors including TM imagery, image texture and additional ancillary GIS information (TM+TXT+GIS model). Compared with traditional Maximum Likelihood Classification (MLC) supervised classification, three classification trees predictive models reduced the overall error rate significantly. Image texture measures and ancillary geographical variables depressed the speckle noise effectively and reduced classification error rate of marsh obviously. For classification trees model making use of all available predictors, omission error rate was 12.90% and commission error rate was 10.99% for marsh. The developed method is portable, relatively easy to implement and should be applicable in other settings and over larger extents.
  • [1] Bolstad P V,Lillesand T M,1992.Rule-based classification models:flexible integration of satellite imagery and thematic spatial data.Photogrammetric Engineering and Remote Sensing,58(7):965-971.
    [2] Breiman L,Friedman J H,Olshen R A et al.,1984.Classification and Regression Trees.Boca Raton,FL:Chapman & Hall.
    [3] Chavez P S,1988.An improved dark-object substraction technique for atmospheric scattering correction of multispectral data.Remote Sensing of Environment,24(3):459-479.DOI: 10.1016/0034-4257(88)90019-3.
    [4] Clark L A,Pregibon D,1992.Tree-based models.In:Chambers et al.(eds.).Statistical Models.Pacific Grove,CA:Wadsworth & Brooks/Cole,377-419.
    [5] Congalton R G,Green K,1999.Assessing the Accuracy of Remotely Sensed Data:Principles and Practices.Boca Raton,FL:CRC Press.
    [6] Ernst C L,Hoffer R M,1979.Digital processing of remotely sensed data for mapping wetland communities.West Lafayette:Laboratory for Applications of Remote Sensing,Purdue University.
    [7] Franklin S,Wulder M,Lavigne M,1996.Automated derivation of geographic windows for use in remote sensing digital image analysis.Computers and Geosciences,22(6):665-673.DOI: 10.1016/0098-3004(96)00009-X.
    [8] Hansen M,Dubayah R,Defries R,1996.Classification trees:An alternative to traditional land cover classifiers.International Journal of Remote Sensing,17(5):1075-1081.DOI: 10.1080/01431169608949069.
    [9] Hinson J M,German C D,Pulich W J,1994.Accuracy assessment and validation of classified satellite imagery of Texas coastal wetlands.Marine Technology Society Journal,28(2):4-9.
    [10] Huete A,Didan K,Miura T et al.,2002.Overview of the radiometric and biophysical performance of the MODIS vegetation indices.Remote Sensing of Environment,83(1-2):195-213.DOI: 10.1016/S0034-4257(02)00096-2.
    [11] Jensen J R,Hodgson M,Christensen E et al.,1986.Remote sensing of inland wetlands:A multi-spectral approach.Photogrammetric Engineering and Remote Sensing,52(1):87-100.
    [12] Johansen K,Phinn S,2006a.Mapping structural parameters and species composition of riparian Vegetation using IKONOS and Landsat ETM+ data in Australian tropical Savannahs.Photogrammetric Engineering and Remote Sensing,72(1):71-80.
    [13] Johansen K,Phinn S,2006b.Linking riparian vegetation spatial structure in Australian tropical savannas to ecosystem health indicators:Semivariogram analysis of high spatial resolution satellite imagery.Canadian Journal of Remote Sensing,32(3):228-243.
    [14] Joy S M,Reich R M,Reynolds R T,2003.A non-parametric supervised classification of vegetation types on the Kaibab National Forest using decision trees.International Journal of Remote Sensing,24(9):1835-1852.DOI: 10.1080/01431160210154948.
    [15] Laine A,Heikkinen K,Heikldnen M et al.,2002.Integrated management and monitoring of boreal river basins:An application to the Finnish River Siuruanjoki.Large Rivers,13(3-4):387-399.
    [16] Lillesand T M,Kiefer R W,Chipman J W,2004.Remote Sensing and Image Interpretation.5th edition.New York,USA:Wiley.
    [17] Liu Xingtu,1995.Wetland and its rational utilization and conservation in the Sanjiang Plain.In:Chen Yiyu (ed.).Study of Wetlands in China.Changchun:Jilin Science and Technology Press,108-117.(in Chinese).
    [18] Miller J,Franklin J,2002.Modeling the distribution of four vegeration alliances using generalized linear models and classification trees with spatial dependence.Ecological Modelling,157(2-3):227-247.DOI: 10.1016/S0304-3800(02)00196-5.
    [19] Mitsch W J,Gusselink J O,1993.Wetlands.3rd edition.New York,USA:Van Nostrand Reinhold.
    [20] Ozesmi S L,Bauer M E,2002.Satellite remote sensing of wetlands.Wetlands Ecology and Management,10(5):381-402.DOI: 10.1023/A:1020908432489.
    [21] Pal M,2005.Random forest classifier for remote sensing classification.International Journal of Remote Sensing,26(1):217-222.DOI: 10.1080/01431160412331269698.
    [22] Sader S A,Ahl D,Liou W S,1995.Accuracy of Landsat TM and GIS rule-based methods for forest wetland classification in Maine.Remote Sensing of Environment,53(3):133-144.DOI: 10.1016/0034-4257(95)00085-F.
    [23] Sesnie S E,Gessler P E,Finegan Bet al.,2008.Integrating Landsat TM and SRTM-DEM derived variables with decision trees for habitat classification and change detection in complex neotropical environments.Remote Sensing of Environment,112(5):2145-2159.DOI: 10.1016/j.rse.2007.08.025.
    [24] Shalaby A,Tateishi R,2007.Remote sensing and GIS for mapping and monitoring land cover and land use changes in the Northwestern coastal zone of Egypt.Applied Geography,27(1):28-41.DOI: 10.1016/j.apgeog.2006.09.004.
    [25] Stehman S V,1999.Estimating the Kappa coefficient and its variance under stratified random sampling.Photogrammetric Engineering and Remote Sensing,62(4):401-407.
    [26] Stehman S V,Wickham J D,Smith J H et al.,2003.Thematic accuracy of the 1992 National Land-Cover Data for the eastern United States:Statistical methodology and regional results.Remote Sensing of Environment,86(3-4):500-516.DOI: 10.1016/S0034-4257(03)00128-7.
    [27] Stow D,Hope A,Boynton W et al.,1998.Satellite-derived vegetation index and cover type maps for estimating carbon dioxide flux for arctic tundra regions.Geomorphology,21(3-4):313-327.DOI: 10.1016/S0169-555X(97)00071-8.
    [28] Wright C,Gallant A,2007.Improved wetland remote sensing in Yellowstone National Park using classification trees to cony bine TM imagery and ancillary geographical data.Remote Sensing of Environment,107(4):582-605.DOI: 10.1016/j.rse.2006.10.019.
    [29] Zar J H,1984.Biostatistical Analysis,2nd Edition.Englewood Cliffs:Prentice-Hall.
    [30] Zhang S Q,Na X D,Kong B et al.,2009.Identifying wetland change in China's Sanjiang Plain using remote sensing.Wetlands,29(1):302-313.
    [31] Zhang S Q,Zhang J Y,Li F et al.,2006.Vector analysis theory on landscape pattern (VATLP).Ecological Modelling,193(3-4):492-502.DOI: 10.1016/j.ecolmodel.2005.08.022.
    [32] Zhang Yangzhen,1988.The genesis,properties and classification of marsh soil in Sanjiang Plain.In:Huang Xichon (ed.).Marsh Research in China.Beijing:Science Press,135-143.(in Chinese).
  • [1] Xinshuang WANG, Jiancheng CAO, Jiange LIU, Xiangwu LI, Lu WANG, Feihang ZUO, Mu BAI.  Improving the Interpretability and Reliability of Regional Land Cover Classification by U-Net Using Remote Sensing Data . Chinese Geographical Science, 2022, 32(6): 979-994. doi: 10.1007/s11769-022-1315-z
    [2] ZENG Hongwei, WU Bingfang, WANG Shuai, MUSAKWA Walter, TIAN Fuyou, MASHIMBYE Zama Eric, POONA Nitesh, SYNDEY Mavengahama.  A Synthesizing Land-cover Classification Method Based on Google Earth Engine: A Case Study in Nzhelele and Levhuvu Catchments, South Africa . Chinese Geographical Science, 2020, 30(3): 397-409. doi: 10.1007/s11769-020-1119-y
    [3] LI Xianju, CHEN Gang, LIU Jingyi, CHEN Weitao, CHENG Xinwen, LIAO Yiwei.  Effects of RapidEye Imagery's Red-edge Band and Vegetation Indices on Land Cover Classification in an Arid Region . Chinese Geographical Science, 2017, 27(5): 827-835. doi: 10.1007/s11769-017-0894-6
    [4] LIU Tingxiang, ZHANG Shuwen, XU Xinliang, BU Kun, NING Jia, CHANG Liping.  High Resolution Land Cover Datasets Integration and Application Based on Landsat and GlobCover Data from 1975 to 2010 in Siberia . Chinese Geographical Science, 2016, 26(4): 429-438. doi: 10.1007/s11769-016-0819-9
    [5] ZHANG Jifei, DENG Wei, LIU Shaoquan.  Geographical Space Development Zone Classification:An Essential Guide for Transformation of Mountain Resource Cities . Chinese Geographical Science, 2015, 25(3): 361-374. doi: 10.1007/s11769-015-0755-0
    [6] Naci YASTIKLI, Umut G SEFERCIK, Fatih ESIRTGEN.  Quantitative Assessment of Remotely Sensed Global Surface Models Using Various Land Classes Produced from Landsat Data in Istanbul . Chinese Geographical Science, 2014, 0(3): 307-316. doi: 10.1007/s11769-014-0681-6
    [7] ZHANG Shengwei, LEI Yuping, WANG Liping, et al..  Crop Classification Using MODIS NDVI Data Denoised by Wavelet: A Case Study in Hebei Plain, China . Chinese Geographical Science, 2011, 21(3): 322-333.
    [8] DU Peijun, YUAN Linshan, XIA Junshi, et al..  Fusion and Classification of Beijing-1 Small Satellite Remote Sensing Image for Land Cover Monitoring in Mining Area . Chinese Geographical Science, 2011, 21(6): 656-665.
    [9] GAO Junqin, OUYANG Hua, LEI Guangchun et al..  Temperature and Soil Moisture Interactively Affect Soil Carbon Mineralization in Zoige Alpine Wetlands . Chinese Geographical Science, 2011, 21(1): 27-35.
    [10] LI Huapeng, ZHANG Shuqing, SUN Yan, GAO Jing.  Land Cover Classification with Multi-source Data Using Evidential Reasoning Approach . Chinese Geographical Science, 2011, 21(3): 312-321.
    [11] JIN Huijun, SUN Guangyou, YU Shaopeng, JIN Rui, HE Ruixia.  Symbiosis of Marshes and Permafrost in Da and Xiao Hinggan Mountains in Northeastern China . Chinese Geographical Science, 2008, 18(1): 62-69. doi: 10.1007/s11769-008-0062-0
    [12] WANG Deyu, FENG Xuezhi, MA Ronghua, KANG Guoding.  A Method for Retrieving Water-leaving Radiance from Landsat TM Image in Taihu Lake, East China . Chinese Geographical Science, 2007, 17(4): 364-369. doi: 10.1007/s11769-007-0364-7
    [13] SHAO Jing'an, GE Xiaofeng, WEI Chaofu, XIE Deti.  Classification and Gradation of Cultivated Land Quality in Bishan County of Chongqing, China . Chinese Geographical Science, 2007, 17(1): 82-91. doi: 10.1007/s11769-007-0082-1
    [14] QI Yueming, TAN Haiqiao, LIANG Xing.  Geomorphologic Study of Anhui Section of Changjiang River Using Landsat TM Image . Chinese Geographical Science, 2007, 17(3): 250-256. doi: 10.1007/s11769-007-0250-3
    [15] ZHOU Xing-dong, DU Pei-jun, GUO Da-zhi.  STUDY ON THE SUBSIDING LAND EXTRACTION FROM LANDSAT TM IMAGE SUPPORTED BY GIS AND DOMAIN KNOWLEDGE . Chinese Geographical Science, 2003, 13(1): 30-33.
    [16] WANG Yi-yong, YANG Yong-xing.  EFFECTS OF AGRICULTURE RECLAMATION ON THE HYDROLOGIC CHARACTERISTICS IN THE SAN JIANG PLAIN, CHINA . Chinese Geographical Science, 2001, 11(2): 163-167.
    [17] 赵文经, 赵焕宸.  ESTIMATION OF VEGETATIVE SURFACE ALBEDO IN THE KUSHIRO MIRE WITH LANDSAT TM DATA ──A New Approach to Atmospheric and Spectral Corrections . Chinese Geographical Science, 1997, 7(3): 278-288.
    [18] 闫敏华, 马学慧, 吕宪国.  CO2 CONCENTRATION AND FLUX NEAR GROUND IN MARSH OF THE SANJIANG PLAIN OF NORTHEAST CHINA . Chinese Geographical Science, 1997, 7(1): 79-87.
    [19] 陈刚起, 吕宪国.  A STUDY ON MARSH EVAPOTRANSPIRATION IN THE SANJIANG PLAIN . Chinese Geographical Science, 1994, 4(2): 159-167.
    [20] 刘兴土.  RADIATION BALANCE AND MICROCLIMATIC FEATURES OF MARSH IN THE SANJIANG PLAIN . Chinese Geographical Science, 1991, 1(4): 347-358.
  • 加载中
WeChat 点击查看大图
计量
  • 文章访问数:  1350
  • HTML全文浏览量:  14
  • PDF下载量:  928
  • 被引次数: 0
出版历程
  • 收稿日期:  2008-08-18
  • 修回日期:  2009-01-10
  • 刊出日期:  2009-06-20

Integrating TM and Ancillary Geographical Data with Classification Trees for Land Cover Classification of Marsh Area

doi: 10.1007/s11769-009-0177-y
  • 1. Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, Changchun 130012, China;
  • 2. Graduate University of the Chinese Academy of Sciences, Beijing 100049, China;
  • 3. Institute of Resources Information, Chinese Academy of Forestry, Beijing 100091, China
    • 基金项目:  Under the auspices of National Natural Science Foundation of China (No. 40871188); National Key Technologies R&D Program of China (No. 2006BAD23B03)
    通讯作者: ZHANG Shuqing.E-mail:shqzhang@263.net
  • 收稿日期: 2008-08-18
  • 修回日期: 2009-01-10
  • 刊出日期: 2009-06-20

摘要: The main objective of this research is to determine the capacity of land cover classification combining spectral and textural features of Landsat TM imagery with ancillary geographical data in wetlands of the Sanjiang Plain, Heilongjiang Province, China. Semi-variograms and Z-test value were calculated to assess the separability of grey-level co-occurrence texture measures to maximize the difference between land cover types. The degree of spatial autocorrelation showed that window sizes of 3×3 pixels and 11×11 pixels were most appropriate for Landsat TM image texture calculations. The texture analysis showed that co-occurrence entropy, dissimilarity, and variance texture measures, derived from the Landsat TM spectrum bands and vegetation indices provided the most significant statistical differentiation between land cover types. Subsequently, a Classification and Regression Tree (CART) algorithm was applied to three different combinations of predictors: 1) TM imagery alone (TM-only); 2) TM imagery plus image texture (TM+TXT model); and 3) all predictors including TM imagery, image texture and additional ancillary GIS information (TM+TXT+GIS model). Compared with traditional Maximum Likelihood Classification (MLC) supervised classification, three classification trees predictive models reduced the overall error rate significantly. Image texture measures and ancillary geographical variables depressed the speckle noise effectively and reduced classification error rate of marsh obviously. For classification trees model making use of all available predictors, omission error rate was 12.90% and commission error rate was 10.99% for marsh. The developed method is portable, relatively easy to implement and should be applicable in other settings and over larger extents.

English Abstract

NA Xiaodong, ZHANG Shuqing, ZHANG Huaiqing, LI Xiaofeng, YU Huan, LIU Chunyue. Integrating TM and Ancillary Geographical Data with Classification Trees for Land Cover Classification of Marsh Area[J]. 中国地理科学, 2009, 19(2): 177-185. doi: 10.1007/s11769-009-0177-y
引用本文: NA Xiaodong, ZHANG Shuqing, ZHANG Huaiqing, LI Xiaofeng, YU Huan, LIU Chunyue. Integrating TM and Ancillary Geographical Data with Classification Trees for Land Cover Classification of Marsh Area[J]. 中国地理科学, 2009, 19(2): 177-185. doi: 10.1007/s11769-009-0177-y
shu
NA Xiaodong, ZHANG Shuqing, ZHANG Huaiqing, LI Xiaofeng, YU Huan, LIU Chunyue. Integrating TM and Ancillary Geographical Data with Classification Trees for Land Cover Classification of Marsh Area[J]. Chinese Geographical Science, 2009, 19(2): 177-185. doi: 10.1007/s11769-009-0177-y
Citation: NA Xiaodong, ZHANG Shuqing, ZHANG Huaiqing, LI Xiaofeng, YU Huan, LIU Chunyue. Integrating TM and Ancillary Geographical Data with Classification Trees for Land Cover Classification of Marsh Area[J]. Chinese Geographical Science, 2009, 19(2): 177-185. doi: 10.1007/s11769-009-0177-y
shu

    全文HTML

参考文献 (32)

目录

    /

    返回文章
    返回

    Copyright © Editorial office of Chinese Geographical Science

    Tel: +86-0431-85542219   Email: egeoscien@neigae.ac.cn