Spectroscopic classification of tropical forest species using radiative transfer modeling

Jean Baptiste Féret, Gregory P. Asner

Research output: Contribution to journalArticle

42 Citations (Scopus)

Abstract

Leaf spectroscopy may be useful for tropical species discrimination, but few studies have provided an understanding of the spectral separability of species or how leaf spectroscopy scales to the canopy level relevant to mapping. Here we report on a study to classify humid tropical forest canopy species using field-measured leaf optical properties with leaf and canopy radiative transfer models. The experimental dataset included 188 canopy species collected in humid tropical forests of Hawaii. The leaf optical model PROSPECT-5 was used to simulate the leaf spectra of each species, which was used to train a classifier based on Linear Discriminant Analysis, and a canopy radiative transfer model 4SAIL2 to scale leaf measurements to the canopy level. The relationship linking classification accuracy at the leaf level to biodiversity showed an asymptotic trend reaching a maximum error of 47% when applied to the entire 188 species experimental dataset, and 56% when a simulated dataset showing amplified within-species spectral variability was used, suggesting uniqueness of the spectral signature for a significant proportion of species under study. The maximum error in canopy-level species classification was higher than leaf-level classification: 55% when canopy structure was held constant, and 64% with varying and unknown canopy structure. However, when classifying fewer species at a time, errors dropped considerably; for example, 20 species can be classified to 82-88% accuracy. These results highlight the potential of imaging spectroscopy to provide species discrimination in high-diversity, humid tropical forests.

Original languageEnglish (US)
Pages (from-to)2415-2422
Number of pages8
JournalRemote Sensing of Environment
Volume115
Issue number9
DOIs
StatePublished - Sep 15 2011
Externally publishedYes

Fingerprint

Radiative transfer
tropical forests
tropical forest
radiative transfer
Spectroscopy
canopy
modeling
leaves
Biodiversity
Discriminant analysis
forest canopy
spectroscopy
Classifiers
Optical properties
Imaging techniques
optical properties
Hawaii
discriminant analysis
image analysis
optical property

Keywords

  • 4SAIL2
  • Humid tropical forest
  • Hyperspectral data
  • Leaf spectroscopy
  • Linear discriminant analysis
  • Model inversion
  • PROSPECT
  • Species discrimination
  • Spectranomics

ASJC Scopus subject areas

  • Soil Science
  • Geology
  • Computers in Earth Sciences

Cite this

Spectroscopic classification of tropical forest species using radiative transfer modeling. / Féret, Jean Baptiste; Asner, Gregory P.

In: Remote Sensing of Environment, Vol. 115, No. 9, 15.09.2011, p. 2415-2422.

Research output: Contribution to journalArticle

@article{88bf38cad3b74c2b8c42c32953944c82,
title = "Spectroscopic classification of tropical forest species using radiative transfer modeling",
abstract = "Leaf spectroscopy may be useful for tropical species discrimination, but few studies have provided an understanding of the spectral separability of species or how leaf spectroscopy scales to the canopy level relevant to mapping. Here we report on a study to classify humid tropical forest canopy species using field-measured leaf optical properties with leaf and canopy radiative transfer models. The experimental dataset included 188 canopy species collected in humid tropical forests of Hawaii. The leaf optical model PROSPECT-5 was used to simulate the leaf spectra of each species, which was used to train a classifier based on Linear Discriminant Analysis, and a canopy radiative transfer model 4SAIL2 to scale leaf measurements to the canopy level. The relationship linking classification accuracy at the leaf level to biodiversity showed an asymptotic trend reaching a maximum error of 47{\%} when applied to the entire 188 species experimental dataset, and 56{\%} when a simulated dataset showing amplified within-species spectral variability was used, suggesting uniqueness of the spectral signature for a significant proportion of species under study. The maximum error in canopy-level species classification was higher than leaf-level classification: 55{\%} when canopy structure was held constant, and 64{\%} with varying and unknown canopy structure. However, when classifying fewer species at a time, errors dropped considerably; for example, 20 species can be classified to 82-88{\%} accuracy. These results highlight the potential of imaging spectroscopy to provide species discrimination in high-diversity, humid tropical forests.",
keywords = "4SAIL2, Humid tropical forest, Hyperspectral data, Leaf spectroscopy, Linear discriminant analysis, Model inversion, PROSPECT, Species discrimination, Spectranomics",
author = "F{\'e}ret, {Jean Baptiste} and Asner, {Gregory P.}",
year = "2011",
month = "9",
day = "15",
doi = "10.1016/j.rse.2011.05.004",
language = "English (US)",
volume = "115",
pages = "2415--2422",
journal = "Remote Sensing of Environment",
issn = "0034-4257",
publisher = "Elsevier Inc.",
number = "9",

}

TY - JOUR

T1 - Spectroscopic classification of tropical forest species using radiative transfer modeling

AU - Féret, Jean Baptiste

AU - Asner, Gregory P.

PY - 2011/9/15

Y1 - 2011/9/15

N2 - Leaf spectroscopy may be useful for tropical species discrimination, but few studies have provided an understanding of the spectral separability of species or how leaf spectroscopy scales to the canopy level relevant to mapping. Here we report on a study to classify humid tropical forest canopy species using field-measured leaf optical properties with leaf and canopy radiative transfer models. The experimental dataset included 188 canopy species collected in humid tropical forests of Hawaii. The leaf optical model PROSPECT-5 was used to simulate the leaf spectra of each species, which was used to train a classifier based on Linear Discriminant Analysis, and a canopy radiative transfer model 4SAIL2 to scale leaf measurements to the canopy level. The relationship linking classification accuracy at the leaf level to biodiversity showed an asymptotic trend reaching a maximum error of 47% when applied to the entire 188 species experimental dataset, and 56% when a simulated dataset showing amplified within-species spectral variability was used, suggesting uniqueness of the spectral signature for a significant proportion of species under study. The maximum error in canopy-level species classification was higher than leaf-level classification: 55% when canopy structure was held constant, and 64% with varying and unknown canopy structure. However, when classifying fewer species at a time, errors dropped considerably; for example, 20 species can be classified to 82-88% accuracy. These results highlight the potential of imaging spectroscopy to provide species discrimination in high-diversity, humid tropical forests.

AB - Leaf spectroscopy may be useful for tropical species discrimination, but few studies have provided an understanding of the spectral separability of species or how leaf spectroscopy scales to the canopy level relevant to mapping. Here we report on a study to classify humid tropical forest canopy species using field-measured leaf optical properties with leaf and canopy radiative transfer models. The experimental dataset included 188 canopy species collected in humid tropical forests of Hawaii. The leaf optical model PROSPECT-5 was used to simulate the leaf spectra of each species, which was used to train a classifier based on Linear Discriminant Analysis, and a canopy radiative transfer model 4SAIL2 to scale leaf measurements to the canopy level. The relationship linking classification accuracy at the leaf level to biodiversity showed an asymptotic trend reaching a maximum error of 47% when applied to the entire 188 species experimental dataset, and 56% when a simulated dataset showing amplified within-species spectral variability was used, suggesting uniqueness of the spectral signature for a significant proportion of species under study. The maximum error in canopy-level species classification was higher than leaf-level classification: 55% when canopy structure was held constant, and 64% with varying and unknown canopy structure. However, when classifying fewer species at a time, errors dropped considerably; for example, 20 species can be classified to 82-88% accuracy. These results highlight the potential of imaging spectroscopy to provide species discrimination in high-diversity, humid tropical forests.

KW - 4SAIL2

KW - Humid tropical forest

KW - Hyperspectral data

KW - Leaf spectroscopy

KW - Linear discriminant analysis

KW - Model inversion

KW - PROSPECT

KW - Species discrimination

KW - Spectranomics

UR - http://www.scopus.com/inward/record.url?scp=79958743653&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79958743653&partnerID=8YFLogxK

U2 - 10.1016/j.rse.2011.05.004

DO - 10.1016/j.rse.2011.05.004

M3 - Article

AN - SCOPUS:79958743653

VL - 115

SP - 2415

EP - 2422

JO - Remote Sensing of Environment

JF - Remote Sensing of Environment

SN - 0034-4257

IS - 9

ER -