Integrating TM and ancillary geographical data with classification trees for land cover classification of marsh area

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]  C. Wright,et al.  Improved wetland remote sensing in Yellowstone National Park using classification trees to combine TM imagery and ancillary environmental data , 2007 .

[2]  I. Vasiliniuc.  Book review of „Remote Sensing and Image Interpretation”, 5th edition (Lillesand M. Thomas, Kiefer W. Ralph, Chipman W. Jonathan) , 2007 .

[3]  S. Phinn,et al.  Mapping structural parameters and species composition of riparian vegetation using IKONOS and landsat ETM+ data in australian tropical savannahs , 2006 .

[4]  Mahesh Pal,et al.  Random forest classifier for remote sensing classification , 2005 .

[5]  R. Tateishi,et al.  Remote sensing and GIS for mapping and monitoring land cover and land-use changes in the Northwestern coastal zone of Egypt , 2007 .

[6]  J. Wickham,et al.  Thematic accuracy of the 1992 National Land-Cover Data for the eastern United States: Statistical methodology and regional results , 2003 .

[7]  Michael E. Hodgson,et al.  Remote sensing inland wetlands: a multispectral approach , 1985 .

[8]  Stacy L. Ozesmi,et al.  Satellite remote sensing of wetlands , 2002, Wetlands Ecology and Management.

[9]  A. Huete,et al.  Overview of the radiometric and biophysical performance of the MODIS vegetation indices , 2002 .

[10]  B. Bhatta.  Remote Sensing and GIS , 2008 .

[11]  Shuqing Zhang,et al.  Vector analysis theory on landscape pattern (VATLP) , 2006 .

[12]  Arun D Kulkarni,et al.  Digital Processing of Remotely Sensed Data , 1986 .

[13]  S. Stehman.  Estimating the Kappa Coefficient and its Variance under Stratified Random Sampling , 1996 .

[14]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[15]  Xiaofeng Li,et al.  Identifying wetland change in China’s Sanjiang Plain using remote sensing , 2009, Wetlands.

[16]  Jennifer A. Miller,et al.  Modeling the distribution of four vegetation alliances using generalized linear models and classification trees with spatial dependence , 2002 .

[17]  Digital processing of remotely sensed data for mapping wetland communities. , 1980 .

[18]  P. Chavez.  An improved dark-object subtraction technique for atmospheric scattering correction of multispectral data , 1988 .

[19]  Stuart R. Phinn,et al.  Satellite-derived vegetation index and cover type maps for estimating carbon dioxide flux for arctic tundra regions , 1998 .

[20]  T. M. Lillesand,et al.  Rule-based classification models: flexible integration of satellite imagery and thematic spatial data , 1992 .

[21]  Michael A. Wulder,et al.  Automated derivation of geographic window sizes for use in remote sensing digital image texture analysis , 1996 .

[22]  Hinson Jm,et al.  Accuracy assessment and validation of classified satellite imagery of Texas coastal wetlands , 1994 .

[23]  R. DeFries,et al.  Classification trees: an alternative to traditional land cover classifiers , 1996 .

[24]  Paul E. Gessler,et al.  Integrating Landsat TM and SRTM-DEM derived variables with decision trees for habitat classification and change detection in complex neotropical environments , 2008 .

[25]  S. Sader,et al.  Accuracy of landsat-TM and GIS rule-based methods for forest wetland classification in Maine , 1995 .

[26]  Russell G. Congalton,et al.  Assessing the accuracy of remotely sensed data : principles and practices , 1998 .

[27]  A. Laine,et al.  Integrated management and monitoring of boreal river basins: an application to the Finnish River Siuruanjoki. , 2002 .

[28]  R. Reynolds,et al.  A non-parametric, supervised classification of vegetation types on the Kaibab National Forest using decision trees , 2003 .

[29]  Daryl Pregibon,et al.  Tree-based models , 1992 .

[30]  Stuart R. Phinn,et al.  Linking riparian vegetation spatial structure in Australian tropical savannas to ecosystem health indicators: semi-variogram analysis of high spatial resolution satellite imagery , 2006 .

[31]  T. M. Lillesand,et al.  Remote Sensing and Image Interpretation , 1980 .

[32]  D. B. Morrison,et al.  Fifth Annual Symposium, Machine Processing of Remotely Sensed Data : Purdue University, Laboratory for Applications of Remote Sensing, West Lafayette, Indiana ... June 27-29, 1979 , 1979 .