Improving discrimination of savanna tree species through a multiple-endmember spectral angle mapper approach: Canopy-level analysis

Moses Azong Cho, Pravesh Debba, Renaud Mathieu, Laven Naidoo, Jan Van Aardt, Gregory P. Asner

Research output: Contribution to journalArticle

91 Citations (Scopus)

Abstract

Differences in within-species phenology and structure are controlled by genetic variation, as well as topography, edaphic properties, and climatic variables across the landscape, and present important challenges to species differentiation with remote sensing. The objectives of this paper are as follows: 1) to evaluate the classification performance of a multiple-endmember spectral angle mapper (SAM) classification approach in discriminating ten common African savanna tree species and 2) to compare the results with the traditional SAM classifier based on a single endmember per species. The canopy spectral reflectance of the tree species ( Acacia nigrescens, Combretum apiculatum , Combretum imberbe, Dichrostachys cinerea, Euclea natalensis, Gymnosporia buxifolia, Lonchocarpus capassa, Pterocarpus rotundifolius, Sclerocarya birrea, and Terminalia sericea) was extracted from airborne hyperspectral imagery that was acquired using the Carnegie Airborne Observatory system over Kruger National Park, South Africa, in May 2008. This study highlights three important phenomena: 1) Intraspecies spectral variability affected the discrimination of savanna tree species with the SAM classifier; 2) the effect of intraspecies spectral variability was minimized by adopting the multiple-endmember approach, e.g., the multiple-endmember approach produced a higher overall accuracy (mean of 54.5% for 20 bootstrapped replicates) when compared to the traditional SAM (mean overall accuracy = 20.5%); and 3) targeted band selection improved the classification of savanna tree species (the mean overall percent accuracy is 57% for 20 bootstrapped replicates). Higher overall classification accuracies were observed for evergreen trees than for deciduous trees.

Original languageEnglish (US)
Article number5559438
Pages (from-to)4133-4142
Number of pages10
JournalIEEE Transactions on Geoscience and Remote Sensing
Volume48
Issue number11
DOIs
StatePublished - Nov 1 2010
Externally publishedYes

Fingerprint

savanna
canopy
Classifiers
Observatories
Topography
Remote sensing
airborne sensing
evergreen tree
canopy reflectance
deciduous tree
spectral reflectance
analysis
phenology
genetic variation
national park
observatory
topography
remote sensing

Keywords

  • Band selection
  • hyperspectral remote sensing
  • multiple-endmember approach
  • savanna tree species
  • spectral angle mapper (SAM)
  • spectral variability

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Earth and Planetary Sciences(all)

Cite this

Improving discrimination of savanna tree species through a multiple-endmember spectral angle mapper approach : Canopy-level analysis. / Cho, Moses Azong; Debba, Pravesh; Mathieu, Renaud; Naidoo, Laven; Van Aardt, Jan; Asner, Gregory P.

In: IEEE Transactions on Geoscience and Remote Sensing, Vol. 48, No. 11, 5559438, 01.11.2010, p. 4133-4142.

Research output: Contribution to journalArticle

@article{945ab40df5934187875525f223ead03a,
title = "Improving discrimination of savanna tree species through a multiple-endmember spectral angle mapper approach: Canopy-level analysis",
abstract = "Differences in within-species phenology and structure are controlled by genetic variation, as well as topography, edaphic properties, and climatic variables across the landscape, and present important challenges to species differentiation with remote sensing. The objectives of this paper are as follows: 1) to evaluate the classification performance of a multiple-endmember spectral angle mapper (SAM) classification approach in discriminating ten common African savanna tree species and 2) to compare the results with the traditional SAM classifier based on a single endmember per species. The canopy spectral reflectance of the tree species ( Acacia nigrescens, Combretum apiculatum , Combretum imberbe, Dichrostachys cinerea, Euclea natalensis, Gymnosporia buxifolia, Lonchocarpus capassa, Pterocarpus rotundifolius, Sclerocarya birrea, and Terminalia sericea) was extracted from airborne hyperspectral imagery that was acquired using the Carnegie Airborne Observatory system over Kruger National Park, South Africa, in May 2008. This study highlights three important phenomena: 1) Intraspecies spectral variability affected the discrimination of savanna tree species with the SAM classifier; 2) the effect of intraspecies spectral variability was minimized by adopting the multiple-endmember approach, e.g., the multiple-endmember approach produced a higher overall accuracy (mean of 54.5{\%} for 20 bootstrapped replicates) when compared to the traditional SAM (mean overall accuracy = 20.5{\%}); and 3) targeted band selection improved the classification of savanna tree species (the mean overall percent accuracy is 57{\%} for 20 bootstrapped replicates). Higher overall classification accuracies were observed for evergreen trees than for deciduous trees.",
keywords = "Band selection, hyperspectral remote sensing, multiple-endmember approach, savanna tree species, spectral angle mapper (SAM), spectral variability",
author = "Cho, {Moses Azong} and Pravesh Debba and Renaud Mathieu and Laven Naidoo and {Van Aardt}, Jan and Asner, {Gregory P.}",
year = "2010",
month = "11",
day = "1",
doi = "10.1109/TGRS.2010.2058579",
language = "English (US)",
volume = "48",
pages = "4133--4142",
journal = "IEEE Transactions on Geoscience and Remote Sensing",
issn = "0196-2892",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "11",

}

TY - JOUR

T1 - Improving discrimination of savanna tree species through a multiple-endmember spectral angle mapper approach

T2 - Canopy-level analysis

AU - Cho, Moses Azong

AU - Debba, Pravesh

AU - Mathieu, Renaud

AU - Naidoo, Laven

AU - Van Aardt, Jan

AU - Asner, Gregory P.

PY - 2010/11/1

Y1 - 2010/11/1

N2 - Differences in within-species phenology and structure are controlled by genetic variation, as well as topography, edaphic properties, and climatic variables across the landscape, and present important challenges to species differentiation with remote sensing. The objectives of this paper are as follows: 1) to evaluate the classification performance of a multiple-endmember spectral angle mapper (SAM) classification approach in discriminating ten common African savanna tree species and 2) to compare the results with the traditional SAM classifier based on a single endmember per species. The canopy spectral reflectance of the tree species ( Acacia nigrescens, Combretum apiculatum , Combretum imberbe, Dichrostachys cinerea, Euclea natalensis, Gymnosporia buxifolia, Lonchocarpus capassa, Pterocarpus rotundifolius, Sclerocarya birrea, and Terminalia sericea) was extracted from airborne hyperspectral imagery that was acquired using the Carnegie Airborne Observatory system over Kruger National Park, South Africa, in May 2008. This study highlights three important phenomena: 1) Intraspecies spectral variability affected the discrimination of savanna tree species with the SAM classifier; 2) the effect of intraspecies spectral variability was minimized by adopting the multiple-endmember approach, e.g., the multiple-endmember approach produced a higher overall accuracy (mean of 54.5% for 20 bootstrapped replicates) when compared to the traditional SAM (mean overall accuracy = 20.5%); and 3) targeted band selection improved the classification of savanna tree species (the mean overall percent accuracy is 57% for 20 bootstrapped replicates). Higher overall classification accuracies were observed for evergreen trees than for deciduous trees.

AB - Differences in within-species phenology and structure are controlled by genetic variation, as well as topography, edaphic properties, and climatic variables across the landscape, and present important challenges to species differentiation with remote sensing. The objectives of this paper are as follows: 1) to evaluate the classification performance of a multiple-endmember spectral angle mapper (SAM) classification approach in discriminating ten common African savanna tree species and 2) to compare the results with the traditional SAM classifier based on a single endmember per species. The canopy spectral reflectance of the tree species ( Acacia nigrescens, Combretum apiculatum , Combretum imberbe, Dichrostachys cinerea, Euclea natalensis, Gymnosporia buxifolia, Lonchocarpus capassa, Pterocarpus rotundifolius, Sclerocarya birrea, and Terminalia sericea) was extracted from airborne hyperspectral imagery that was acquired using the Carnegie Airborne Observatory system over Kruger National Park, South Africa, in May 2008. This study highlights three important phenomena: 1) Intraspecies spectral variability affected the discrimination of savanna tree species with the SAM classifier; 2) the effect of intraspecies spectral variability was minimized by adopting the multiple-endmember approach, e.g., the multiple-endmember approach produced a higher overall accuracy (mean of 54.5% for 20 bootstrapped replicates) when compared to the traditional SAM (mean overall accuracy = 20.5%); and 3) targeted band selection improved the classification of savanna tree species (the mean overall percent accuracy is 57% for 20 bootstrapped replicates). Higher overall classification accuracies were observed for evergreen trees than for deciduous trees.

KW - Band selection

KW - hyperspectral remote sensing

KW - multiple-endmember approach

KW - savanna tree species

KW - spectral angle mapper (SAM)

KW - spectral variability

UR - http://www.scopus.com/inward/record.url?scp=78049251348&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78049251348&partnerID=8YFLogxK

U2 - 10.1109/TGRS.2010.2058579

DO - 10.1109/TGRS.2010.2058579

M3 - Article

AN - SCOPUS:78049251348

VL - 48

SP - 4133

EP - 4142

JO - IEEE Transactions on Geoscience and Remote Sensing

JF - IEEE Transactions on Geoscience and Remote Sensing

SN - 0196-2892

IS - 11

M1 - 5559438

ER -