Operational tree species mapping in a diverse tropical forest with airborne imaging spectroscopy

Claire A. Baldeck, Gregory P. Asner, Robin E. Martin, Christopher B. Anderson, David E. Knapp, James R. Kellner, S. Joseph Wright

Research output: Contribution to journalArticle

53 Citations (Scopus)

Abstract

Remote identification and mapping of canopy tree species can contribute valuable information towards our understanding of ecosystem biodiversity and function over large spatial scales. However, the extreme challenges posed by highly diverse, closed-canopy tropical forests have prevented automated remote species mapping of non-flowering tree crowns in these ecosystems. We set out to identify individuals of three focal canopy tree species amongst a diverse background of tree and liana species on Barro Colorado Island, Panama, using airborne imaging spectroscopy data. First, we compared two leading singleclass classification methods - binary support vector machine (SVM) and biased SVM - for their performance in identifying pixels of a single focal species. From this comparison we determined that biased SVM was more precise and created a multi-species classification model by combining the three biased SVM models. This model was applied to the imagery to identify pixels belonging to the three focal species and the prediction results were then processed to create a map of focal species crown objects. Crown-level cross-validation of the training data indicated that the multi-species classification model had pixel-level producer's accuracies of 94-97% for the three focal species, and field validation of the predicted crown objects indicated that these had user's accuracies of 94-100%. Our results demonstrate the ability of high spatial and spectral resolution remote sensing to accurately detect non-flowering crowns of focal species within a diverse tropical forest. We attribute the success of our model to recent classification and mapping techniques adapted to species detection in diverse closed-canopy forests, which can pave the way for remote species mapping in a wider variety of ecosystems.

Original languageEnglish (US)
Article numbere0118403
JournalPloS one
Volume10
Issue number7
DOIs
StatePublished - Jul 8 2015
Externally publishedYes

Fingerprint

Crowns
tropical forests
tree crown
spectroscopy
Spectrum Analysis
image analysis
Spectroscopy
Support vector machines
Imaging techniques
Ecosystems
taxonomy
Ecosystem
Pixels
canopy
ecosystems
Panama
Biodiversity
Imagery (Psychotherapy)
Spectral resolution
forest canopy

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Operational tree species mapping in a diverse tropical forest with airborne imaging spectroscopy. / Baldeck, Claire A.; Asner, Gregory P.; Martin, Robin E.; Anderson, Christopher B.; Knapp, David E.; Kellner, James R.; Wright, S. Joseph.

In: PloS one, Vol. 10, No. 7, e0118403, 08.07.2015.

Research output: Contribution to journalArticle

Baldeck, Claire A. ; Asner, Gregory P. ; Martin, Robin E. ; Anderson, Christopher B. ; Knapp, David E. ; Kellner, James R. ; Wright, S. Joseph. / Operational tree species mapping in a diverse tropical forest with airborne imaging spectroscopy. In: PloS one. 2015 ; Vol. 10, No. 7.
@article{1f4b6cb48c014f20ae7990c94e9b0d92,
title = "Operational tree species mapping in a diverse tropical forest with airborne imaging spectroscopy",
abstract = "Remote identification and mapping of canopy tree species can contribute valuable information towards our understanding of ecosystem biodiversity and function over large spatial scales. However, the extreme challenges posed by highly diverse, closed-canopy tropical forests have prevented automated remote species mapping of non-flowering tree crowns in these ecosystems. We set out to identify individuals of three focal canopy tree species amongst a diverse background of tree and liana species on Barro Colorado Island, Panama, using airborne imaging spectroscopy data. First, we compared two leading singleclass classification methods - binary support vector machine (SVM) and biased SVM - for their performance in identifying pixels of a single focal species. From this comparison we determined that biased SVM was more precise and created a multi-species classification model by combining the three biased SVM models. This model was applied to the imagery to identify pixels belonging to the three focal species and the prediction results were then processed to create a map of focal species crown objects. Crown-level cross-validation of the training data indicated that the multi-species classification model had pixel-level producer's accuracies of 94-97{\%} for the three focal species, and field validation of the predicted crown objects indicated that these had user's accuracies of 94-100{\%}. Our results demonstrate the ability of high spatial and spectral resolution remote sensing to accurately detect non-flowering crowns of focal species within a diverse tropical forest. We attribute the success of our model to recent classification and mapping techniques adapted to species detection in diverse closed-canopy forests, which can pave the way for remote species mapping in a wider variety of ecosystems.",
author = "Baldeck, {Claire A.} and Asner, {Gregory P.} and Martin, {Robin E.} and Anderson, {Christopher B.} and Knapp, {David E.} and Kellner, {James R.} and Wright, {S. Joseph}",
year = "2015",
month = "7",
day = "8",
doi = "10.1371/journal.pone.0118403",
language = "English (US)",
volume = "10",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "7",

}

TY - JOUR

T1 - Operational tree species mapping in a diverse tropical forest with airborne imaging spectroscopy

AU - Baldeck, Claire A.

AU - Asner, Gregory P.

AU - Martin, Robin E.

AU - Anderson, Christopher B.

AU - Knapp, David E.

AU - Kellner, James R.

AU - Wright, S. Joseph

PY - 2015/7/8

Y1 - 2015/7/8

N2 - Remote identification and mapping of canopy tree species can contribute valuable information towards our understanding of ecosystem biodiversity and function over large spatial scales. However, the extreme challenges posed by highly diverse, closed-canopy tropical forests have prevented automated remote species mapping of non-flowering tree crowns in these ecosystems. We set out to identify individuals of three focal canopy tree species amongst a diverse background of tree and liana species on Barro Colorado Island, Panama, using airborne imaging spectroscopy data. First, we compared two leading singleclass classification methods - binary support vector machine (SVM) and biased SVM - for their performance in identifying pixels of a single focal species. From this comparison we determined that biased SVM was more precise and created a multi-species classification model by combining the three biased SVM models. This model was applied to the imagery to identify pixels belonging to the three focal species and the prediction results were then processed to create a map of focal species crown objects. Crown-level cross-validation of the training data indicated that the multi-species classification model had pixel-level producer's accuracies of 94-97% for the three focal species, and field validation of the predicted crown objects indicated that these had user's accuracies of 94-100%. Our results demonstrate the ability of high spatial and spectral resolution remote sensing to accurately detect non-flowering crowns of focal species within a diverse tropical forest. We attribute the success of our model to recent classification and mapping techniques adapted to species detection in diverse closed-canopy forests, which can pave the way for remote species mapping in a wider variety of ecosystems.

AB - Remote identification and mapping of canopy tree species can contribute valuable information towards our understanding of ecosystem biodiversity and function over large spatial scales. However, the extreme challenges posed by highly diverse, closed-canopy tropical forests have prevented automated remote species mapping of non-flowering tree crowns in these ecosystems. We set out to identify individuals of three focal canopy tree species amongst a diverse background of tree and liana species on Barro Colorado Island, Panama, using airborne imaging spectroscopy data. First, we compared two leading singleclass classification methods - binary support vector machine (SVM) and biased SVM - for their performance in identifying pixels of a single focal species. From this comparison we determined that biased SVM was more precise and created a multi-species classification model by combining the three biased SVM models. This model was applied to the imagery to identify pixels belonging to the three focal species and the prediction results were then processed to create a map of focal species crown objects. Crown-level cross-validation of the training data indicated that the multi-species classification model had pixel-level producer's accuracies of 94-97% for the three focal species, and field validation of the predicted crown objects indicated that these had user's accuracies of 94-100%. Our results demonstrate the ability of high spatial and spectral resolution remote sensing to accurately detect non-flowering crowns of focal species within a diverse tropical forest. We attribute the success of our model to recent classification and mapping techniques adapted to species detection in diverse closed-canopy forests, which can pave the way for remote species mapping in a wider variety of ecosystems.

UR - http://www.scopus.com/inward/record.url?scp=84941308996&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84941308996&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0118403

DO - 10.1371/journal.pone.0118403

M3 - Article

C2 - 26153693

AN - SCOPUS:84941308996

VL - 10

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 7

M1 - e0118403

ER -