@Article{SouzaSLGAFSSVDS:2019:SuVeAp,
author = "Souza, Guilherme Silverio Aquino de and Soares, Vicente Paulo and
Leite, Helio Garcia and Gleriani, Jos{\'e} Marinaldo and Amaral,
Cibele Hummel do and Ferraz, Ant{\^o}nio Santana and Silveira,
Marcus Vinicius de Freitas and Santos, Jo{\~a}o Fl{\'a}vio Costa
dos and Velloso, Sidney Geraldo Silveira and Domingues, Getulio
Fonseca and Silva, Simone",
affiliation = "{Universidade Federal de Vi{\c{c}}osa (UFV)} and {Universidade
Federal de Vi{\c{c}}osa (UFV)} and {Universidade Federal de
Vi{\c{c}}osa (UFV)} and {Universidade Federal de Vi{\c{c}}osa
(UFV)} and {Universidade Federal de Vi{\c{c}}osa (UFV)} and
{Universidade Federal de Vi{\c{c}}osa (UFV)} and {Instituto
Nacional de Pesquisas Espaciais (INPE)} and {Universidade Federal
de Vi{\c{c}}osa (UFV)} and {Instituto Brasileiro de Geografia e
Estat{\'{\i}}stica (IBGE)} and {Universidade Federal de
Vi{\c{c}}osa (UFV)} and {Universidade Federal de Vi{\c{c}}osa
(UFV)}",
title = "Multi-sensor prediction of Eucalyptus stand volume: a support
vector approach",
journal = "ISPRS Journal of Photogrammetry and Remote Sensing",
year = "2019",
volume = "156",
pages = "135--146",
month = "Oct.",
keywords = "ALOS AVNIR-2, ALOS PALSAR, Machine learning, Monte Carlo
cross-validation, Sampling intensity, L-band, Synthetic aperture
radar.",
abstract = "Stem volume is a key attribute of Eucalyptus forest plantations
upon which decision-making is based at diverse levels of planning.
Quantifying volume through remote sensing can support a proper
management of forests. Because of limitations on spaceborne
optical and synthetic aperture radar sensors, this study
integrated both types of datasets assembled using support vector
regression (SVR) to retrieve the stand volume of Eucalyptus
plantations. We assessed different combinations of sensors and a
minimum number of plots to develop an SVR model. Finally, the best
SVR performance was compared with other analytical methods already
tested and in the literature: multilinear regression, artificial
neural networks (ANN), and random forest (RF). Here, we introduce
a test for comparative analysis of the performance of different
methods. We found that SVR accurately predicted stem volume of
Brazilian fast-growing Eucalyptus forest plantations. Gaussian
radial basis was the most suitable kernel function. Integrating
the optical and L-band backscatter data increased the predictive
accuracy compared to a single sensor model. Combining NIR-band
data from ALOS AVNIR-2 and backscatter of L-band horizontal
emitted and vertical received (HV) electric fields from ALOS
PALSAR produced the most accurate SVR model (with an R2 of 0.926
and root mean square error of 11.007 m3 /ha). The number of field
plots sufficient for model development with non-redundant
explanatory variables was 77. Under this condition, SVR performed
similarly to ANN and outperformed the multiple linear regression
and random forest methods.",
doi = "10.1016/j.isprsjprs.2019.08.002",
url = "http://dx.doi.org/10.1016/j.isprsjprs.2019.08.002",
issn = "0924-2716",
language = "en",
targetfile = "souza_multi.pdf",
urlaccessdate = "27 abr. 2024"
}