@Article{FéretMJBBHCOPSBCNPPSGL:2019:PoLiPh,
author = "F{\'e}ret, J. B. and Maire, G. le and Jay, S. and Berveiller, D.
and Bendoula, R. and Hmimina, G. and Cheraiet, A. and Oliveira, J.
C. and Ponzoni, Fl{\'a}vio Jorge and Solanki, T. and Boissieu, F.
de and Chave, J. and Nouvellon, Y. and Porcar-Castell, A. and
Proisy, C. and Soudani, K. and Gastellu-Etchegorry, J. P. and
Lef{\'e}vre-Fonollosa, M. J.",
affiliation = "{Universit{\'e} Montpellier} and CIRAD, UMR ECO\&SOL and {Aix
Marseille Univ} and {University of Paris-Sud} and {Universit{\'e}
Montpellier} and {University of Paris-Sud} and {University of
Paris-Sud} and {Universidade Estadual de Campinas (UNICAMP0} and
{Instituto Nacional de Pesquisas Espaciais (INPE)} and {University
of Helsinki} and {Universit{\'e} Montpellier} and
{Universit{\'e} Paul Sabatier} and CIRAD, UMR ECO\&SOL and
{University of Helsinki} and {Univ. Montpellier} and {University
of Paris-Sud} and {Centre d'Etudes Spatiales de la Biosph{\`e}re}
and CNES",
title = "Estimating leaf mass per area and equivalent water thickness based
on leaf optical properties: Potential and limitations of physical
modeling and machine learning",
journal = "Remote Sensing of Environment",
year = "2019",
volume = "231",
pages = "e110959",
month = "Sept.",
keywords = "Biophysical properties, Leaf spectroscopy, EWT, LMA, Radiative
transfer model, Support vector machine, Vegetation.",
abstract = "Leaf mass per area (LMA) and leaf equivalent water thickness (EWT)
are key leaf functional traits providing information for many
applications including ecosystem functioning modeling and fire
risk management. In this paper, we investigate two common
conclusions generally made for LMA and EWT estimation based on
leaf optical properties in the near-infrared (NIR) and shortwave
infrared (SWIR) domains: (1) physically-based approaches estimate
EWT accurately and LMA poorly, while (2) statistically-based and
machine learning (ML) methods provide accurate estimates of both
LMA and EWT. Using six experimental datasets including broadleaf
species samples of >150 species collected over tropical, temperate
and boreal ecosystems, we compared the performances of a
physically-based method (PROSPECT model inversion) and a ML
algorithm (support vector machine regression, SVM) to infer EWT
and LMA based on leaf reflectance and transmittance. We assessed
several merit functions to invert PROSPECT based on iterative
optimization and investigated the spectral domain to be used for
optimal estimation of LMA and EWT. We also tested several
strategies to select the training samples used by the SVM, in
order to investigate the generalization ability of the derived
regression models. We evidenced that using spectral information
from 1700 to 2400 nm leads to strong improvement in the estimation
of EWT and LMA when performing a PROSPECT inversion, decreasing
the LMA and EWT estimation errors by 55% and 33%, respectively.
The comparison of various sampling strategies for the training set
used with SVM suggests that regression models show limited
generalization ability, particularly when the regression model is
applied on data fully independent from the training set. Finally,
our results demonstrate that, when using an appropriate spectral
domain, the PROSPECT inversion outperforms SVM trained with
experimental data for the estimation of EWT and LMA. Thus we
recommend that estimation of LMA and EWT based on leaf optical
properties should be physically-based using inversion of
reflectance and transmittance measurements on the 1700 to 2400 nm
spectral range.",
doi = "10.1016/j.rse.2018.11.002",
url = "http://dx.doi.org/10.1016/j.rse.2018.11.002",
issn = "0034-4257",
language = "en",
targetfile = "feret_estimating.pdf",
urlaccessdate = "28 abr. 2024"
}