@Article{DinizGamReiOliMar:2023:PlBrUs,
author = "Diniz, Juliana Maria Ferreira de Souza and Gama, F{\'a}bio Furlan
and Reis, Aliny Aparecida dos and Oliveira, Cleber Gonzales de and
Marques, Eduardo Resende Girardi",
affiliation = "{Instituto Nacional de Pesquisas Espaciais (INPE)} and {Instituto
Nacional de Pesquisas Espaciais (INPE)} and {Universidade Estadual
de Campinas (UNICAMP)} and {VISIONA Tecnologia Espacial} and
{KLABIN S.A.}",
title = "Estimating stem volume of Eucalyptus sp. and Pinus sp. plantations
in Brazil, using Sentinel-1B and ALOS-2/PALSAR-2 data",
journal = "Journal of Applied Remote Sensing",
year = "2023",
volume = "17",
number = "1",
pages = "e014513",
month = "Jan.",
keywords = "machine learning, multifrequency, polarimetry, synthetic aperture
radar.",
abstract = "Multifrequency synthetic aperture radar (SAR) data have been
applied to discriminate subtle differences in the vegetation and
to better characterize its structural properties, since each SAR
frequency will interact with the different sections of the
vegetation canopy. In this study, our main objective was to
evaluate the use of multifrequency Sentinel-1 and ALOS-2/PALSAR-2
data for stem volume estimations in Eucalyptus sp. and Pinus sp.
plantations using three different machine learning algorithms:
random forest (RF), support vector regression (SVR), and extreme
gradient boosting (XGB). Different experiments were carried out
using combinations of predictor variables derived from both SAR
sensors: backscattering, polarimetric decompositions, and
interferometry data, and field data considering specific models
for Eucalyptus sp. and Pinus sp. and a generic model comprising
all forest plantations data. The machine learning models using
predictor variables derived from SAR data achieved moderately high
accuracy to predict stem volume, mainly when SAR data were used in
combination with stand age (Experiment iv). In the best prediction
scenario (Experiment iv), the RF, SVR, and XGB models were able to
explain 81.7%, 68.5%, and 81.8% [coefficient of variation (R2)
values] of stem volume variability considering the generic models,
respectively. Our results pointed out that the RF algorithm showed
the best performance in predicting stem volume with significant
good results and easier implementation in comparison with the
other two algorithms (SVR and XGB).",
doi = "10.1117/1.JRS.17.014513",
url = "http://dx.doi.org/10.1117/1.JRS.17.014513",
issn = "1931-3195",
language = "en",
targetfile = "014513_1.pdf",
urlaccessdate = "20 maio 2024"
}