Application of spectral mixture analysis to Amazonian land-use and land-cover classification

Abundant vegetation species and associated complex forest stand structures in moist tropical regions often create difficulties in accurately classifying land-use and land-cover (LULC) features. This paper examines the value of spectral mixture analysis (SMA) using Landsat Thematic Mapper (TM) data for improving LULC classification accuracy in a moist tropical area in Rondônia, Brazil. Different routines, such as constrained and unconstrained least-squares solutions, different numbers of endmembers, and minimum noise fraction transformation, were examined while implementing the SMA approach. A maximum likelihood classifier was also used to classify fraction images into seven LULC classes: mature forest, intermediate secondary succession, initial secondary succession, pasture, agricultural land, water, and bare land. The results of this study indicate that reducing correlation between image bands and using four endmembers improve classification accuracy. The overall classification accuracy was 86.6% for the seven LULC classes using the best SMA processing routine, which represents very good results for such a complex environment. The overall classification accuracy using a maximum likelihood approach was 81.4%. Another finding is that use of constrained or unconstrained solutions for unmixing the atmospherically corrected or raw Landsat TM images does not have significant influence on LULC classification performances when image endmembers are used in a SMA approach.

[1]  M. Batistella,et al.  Linear mixture model applied to Amazonian vegetation classification , 2003 .

[2]  D. Roberts,et al.  Green vegetation, nonphotosynthetic vegetation, and soils in AVIRIS data , 1993 .

[3]  Didier Tanré,et al.  Second Simulation of the Satellite Signal in the Solar Spectrum, 6S: an overview , 1997, IEEE Trans. Geosci. Remote. Sens..

[4]  Fabio Maselli,et al.  Definition of Spatially Variable Spectral Endmembers by Locally Calibrated Multivariate Regression Analyses , 2001 .

[5]  P. Fisher.  The pixel: A snare and a delusion , 1997 .

[6]  P. Chavez.  Image-Based Atmospheric Corrections - Revisited and Improved , 1996 .

[7]  Gregory P. Asner,et al.  IKONOS imagery for the Large Scale Biosphere–Atmosphere Experiment in Amazonia (LBA) , 2003 .

[8]  Giles M. Foody,et al.  Status of land cover classification accuracy assessment , 2002 .

[9]  Dengsheng Lu,et al.  Classification of successional forest stages in the Brazilian Amazon basin , 2003 .

[10]  Nelson D. A. Mascarenhas,et al.  Use of synthetic bands derived from mixing models in the multispectral classification of remote sensing images , 1999 .

[11]  S. Tompkins,et al.  Optimization of endmembers for spectral mixture analysis , 1997 .

[12]  M. Batistella.  Landscape change and Land-use/Land-Cover Dynamics in Rondônia, Brazilian Amazon. , 2001 .

[13]  M. Batistella,et al.  COMPARISON OF LAND-COVER CLASSIFICATION METHODS IN THE BRAZILIAN AMAZON BASIN , 2004 .

[14]  P. C. Smits,et al.  QUALITY ASSESSMENT OF IMAGE CLASSIFICATION ALGORITHMS FOR LAND-COVER MAPPING , 1999 .

[15]  S. Ustin,et al.  Vegetation mapping on hardwood rangelands in California , 1996 .

[16]  F. J. García-Haro,et al.  Linear spectral mixture modelling to estimate vegetation amount from optical spectral data , 1996 .

[17]  Brian L. Markham,et al.  Thematic Mapper bandpass solar exoatmospheric irradiances , 1987 .

[18]  D. Roberts,et al.  Endmember selection for multiple endmember spectral mixture analysis using endmember average RMSE , 2003 .

[19]  Xiaojun Yang,et al.  Relative Radiometric Normalization Performance for Change Detection from Multi-Date Satellite Images , 2000 .

[20]  F. D. van der Meer,et al.  Iterative spectral unmixing (ISU) , 1999 .

[21]  J. Settle,et al.  Linear mixing and the estimation of ground cover proportions , 1993 .

[22]  Klaus I. Itten,et al.  A physically-based model to correct atmospheric and illumination effects in optical satellite data of rugged terrain , 1997, IEEE Trans. Geosci. Remote. Sens..

[23]  M. Cochrane.  Linear mixture model classification of burned forests in the Eastern Amazon , 1998 .

[24]  Russell G. Congalton,et al.  A review of assessing the accuracy of classifications of remotely sensed data , 1991 .

[25]  F. J. García-Haro,et al.  Extraction of Endmembers from Spectral Mixtures , 1999 .

[26]  A. Cracknell.  Review article Synergy in remote sensing-what's in a pixel? , 1998 .

[27]  Dr Robert Bryant,et al.  The mapping of hydrothermal alteration zones on the island of Lesvos, Greece using an integrated remote sensing dataset , 2002 .

[28]  Alan R. Gillespie,et al.  Vegetation in deserts. I - A regional measure of abundance from multispectral images. II - Environmental influences on regional abundance , 1990 .

[29]  D. Lu.  INTEGRATION OF VEGETATION INVENTORY DATA AND TIlEMATIC MAPPER IMAGE FOR AMAZONIAN SUCCESSIONAL AND MATURE FOREST CLASSIFICATION , 2022 .

[30]  S. M. Jong,et al.  Improving the results of spectral unmixing of Landsat thematic mapper imagery by enhancing the orthogonality of end-members , 2000 .

[31]  Y. E. Shimabukuro,et al.  Identification and mapping of the Amazon habitats using a mixing model , 1997 .

[32]  Brian Curtiss,et al.  A method for manual endmember selection and spectral unmixing , 1996 .

[33]  C. Small.  Estimation of urban vegetation abundance by spectral mixture analysis , 2001 .

[34]  Dengsheng Lu,et al.  Assessment of atmospheric correction methods for Landsat TM data applicable to Amazon basin LBA research , 2002 .

[35]  Emilio F. Moran,et al.  Settlement Design, Forest Fragmentation, and Landscape Change in Rondonia, Amazonia , 2003 .

[36]  R. Congalton.  A Quantitative Method to Test for Consistency and Correctness in Photointerpretation , 1983 .

[37]  Solos das "Glebas 01, 02, 03 e 06" do Município de Machadinho D´Oeste-RO. , 1999 .

[38]  Margaret E. Gardner,et al.  Mapping Chaparral in the Santa Monica Mountains Using Multiple Endmember Spectral Mixture Models , 1998 .

[39]  L.L.F. Janssen,et al.  Accuracy assessment of satellite derived land - cover data : a review , 1994 .

[40]  C. Woodcock,et al.  Classification and Change Detection Using Landsat TM Data: When and How to Correct Atmospheric Effects? , 2001 .

[41]  Emilio F. Moran,et al.  Developing the Amazon. , 1981 .

[42]  D. Lobell,et al.  Quantifying vegetation change in semiarid environments: precision and accuracy of spectral mixture analysis and the normalized difference vegetation index. , 2000 .

[43]  Eduardo S Brondízio,et al.  Land Reform and Land-Use Changes in the Lower Amazon: Implications for Agricultural Intensification , 2003 .

[44]  John B. Adams,et al.  Classification of multispectral images based on fractions of endmembers: Application to land-cover change in the Brazilian Amazon , 1995 .

[45]  Alan R. Gillespie,et al.  Structural stage in Pacific Northwest forests estimated using simple mixing models of multispectral images , 2002 .

[46]  J. C. Taylor,et al.  Sensitivity of mixture modelling to end‐member selection , 2003 .