Land‐cover classification in the Andes of southern Ecuador using Landsat ETM+ data as a basis for SVAT modelling

A land‐cover classification is needed to deduce surface boundary conditions for a soil–vegetation–atmosphere transfer (SVAT) scheme that is operated by a geoecological research unit working in the Andes of southern Ecuador. Landsat Enhanced Thematic Mapper Plus (ETM+) data are used to classify distinct vegetation types in the tropical mountain forest. Besides a hard classification, a soft classification technique is applied. Dempster–Shafer evidence theory is used to analyse the quality of the spectral training sites and a modified linear spectral unmixing technique is selected to produce abundancies of the spectral endmembers. The hard classification provides very good results, with a Kappa value of 0.86. The Dempster–Shafer ambiguity underlines the good quality of the training sites and the probability guided spectral unmixing is chosen for the determination of plant functional types for the land model. A similar model run with a spatial distribution of land cover from both the hard and the soft classification processes clearly points to more realistic model results by using the land surface based on the probability guided spectral unmixing technique.

[1]  A. Paulsch,et al.  Development and Application of a Classification System for Undisturbed and Disturbed Tropical Montane Forests Based on Vegetation Structure , 2002 .

[2]  Wilhelm Barthlott,et al.  Global Centers of Vascular Plant Diversity , 2005 .

[3]  E. Jordan,et al.  Estimation by photogrammetry of the glacier recession on the Cotopaxi Volcano (Ecuador) between 1956 and 1997 / Estimation par photogrammétrie de la récession glaciaire sur le Volcan Cotopaxi (Equateur) entre 1956 et 1997 , 2005 .

[4]  Peter F. Fisher,et al.  Comparing the consistency of expert land cover knowledge , 2005 .

[5]  N. Brummitt,et al.  Biodiversity: Where's Hot and Where's Not , 2003 .

[6]  Jeffrey D. Colby,et al.  Land cover classification using Landsat TM imagery in the tropical highlands : the influence of anisotropic reflectance , 1998 .

[7]  D. Peddle,et al.  Spectral mixture analysis of agricultural crops: Endmember validation and biophysical estimation in potato plots , 2005 .

[8]  Martha C. Anderson,et al.  A Multiscale Remote Sensing Model for Disaggregating Regional Fluxes to Micrometeorological Scales , 2004 .

[9]  M. Richter,et al.  Seasonality of weather and tree phenology in a tropical evergreen mountain rain forest , 2006, International journal of biometeorology.

[10]  Qihao Weng,et al.  A survey of image classification methods and techniques for improving classification performance , 2007 .

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

[12]  Erwin Beck,et al.  Analysis of undisturbed and disturbed tropical mountain forest ecosystems in Southern Ecuador , 2001 .

[13]  David Riaño,et al.  Assessment of different topographic corrections in Landsat-TM data for mapping vegetation types (2003) , 2003, IEEE Trans. Geosci. Remote. Sens..

[14]  Peter F. Fisher,et al.  Integrating land-cover data with different ontologies: identifying change from inconsistency , 2004, Int. J. Geogr. Inf. Sci..

[15]  J. Dymond,et al.  Correcting satellite imagery for the variance of reflectance and illumination with topography , 2003 .

[16]  Honglei Zhu,et al.  Linear spectral unmixing assisted by probability guided and minimum residual exhaustive search for subpixel classification , 2005 .

[17]  Keith W. Oleson,et al.  Landscapes as patches of plant functional types: An integrating concept for climate and ecosystem models , 2002 .

[18]  Christian Töttrup,et al.  Improving tropical forest mapping using multi-date Landsat TM data and pre-classification image smoothing , 2004 .

[19]  H. Kürschner,et al.  Ecosociological studies in Ecuadorian bryophyte communities. II. Syntaxonomy of the submontane and montane epiphytic vegetation of S Ecuador , 2004 .

[20]  M. Zervakis,et al.  Exemplifying the theory of evidence in remote sensing image classification , 2001 .

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

[22]  J. Eastman,et al.  Bayesian Soft Classification for Sub-Pixel Analysis: A Critical Evaluation , 2002 .

[23]  J. Bendix,et al.  Die Niederschlagsjahreszeiten in Ecuador und ihre klimadynamische Interpretation , 1992 .

[24]  Kati J. Salovaara,et al.  Classification of Amazonian primary rain forest vegetation using Landsat ETM+ satellite imagery , 2005 .

[25]  M. Richter.  Using epiphytes and soil temperatures for eco-climatic interpretations in southern Ecuador , 2003 .

[26]  Giles M. Foody,et al.  Separability of tropical rain-forest types in the Tambopata-Candamo Reserved Zone, Peru , 1994 .

[27]  R. Mccoy,et al.  Mapping Desert Shrub Rangeland Using Spectral Unmixing and Modeling Spectral Mixtures with TM Data , 1997 .

[28]  W. Cohen,et al.  Mapping montane tropical forest successional stage and land use with multi-date Landsat imagery , 2000 .

[29]  K. Fiedler,et al.  Beta diversity of geometrid moths (Lepidoptera: Geometridae) in an Andean montane rainforest , 2003 .

[30]  Conghe Song,et al.  Spectral mixture analysis for subpixel vegetation fractions in the urban environment: How to incorporate endmember variability? , 2005 .

[31]  E. Beck,et al.  THE BRACKEN FERN (PTERIDIUM ARACHNOIDEUM (KAULF.) MAXON) DILEMMA IN THE ANDES OF SOUTHERN ECUADOR , 2003 .

[32]  José A. Malpica,et al.  Dempster-Shafer Theory in geographic information systems: A survey , 2007, Expert Syst. Appl..

[33]  Jörg Bendix,et al.  Cloud detection in the Tropics--a suitable tool for climate-ecological studies in the high mountains of Ecuador , 2004 .

[34]  R. Hill.  Image segmentation for humid tropical forest classification in Landsat TM data , 1999 .

[35]  R. Congalton,et al.  Accuracy assessment: a user's perspective , 1986 .

[36]  J. Bendix,et al.  Cloud occurrence and cloud properties in Ecuador , 2006 .

[37]  R. Dickinson,et al.  The Common Land Model , 2003 .