@Article{JaconGalvSilvSant:2021:ExHy,
author = "Jacon, Aline Daniele and Galv{\~a}o, L{\^e}nio Soares and Silva,
Ricardo Dal'Agnol da and Santos, Jo{\~a}o Roberto dos",
affiliation = "{Instituto Nacional de Pesquisas Espaciais (INPE)} and {Instituto
Nacional de Pesquisas Espaciais (INPE)} and {University of
Manchester} and {Instituto Nacional de Pesquisas Espaciais
(INPE)}",
title = "Aboveground biomass estimates over Brazilian savannas using
hyperspectral metrics and machine learning models: experiences
with Hyperion/EO-1",
journal = "Giscience and Remote Sensing",
year = "2021",
volume = "58",
number = "7",
pages = "1112--1129",
month = "Oct.",
keywords = "Hyperspectral remote sensing, aboveground biomass (AGB), savannas,
Cerrado, machine learning, Hyperion/EO-1.",
abstract = "We investigated the potential of hyperspectral remote sensing to
estimate aboveground biomass (AGB) over the Brazilian savannas
(Cerrado), the second-largest source of carbon emissions in
Brazil. For this purpose, a Hyperion/Earth Observing-1 (EO-1)
image was collected in the dry season at the Ecological Station of
{\'A}guas Emendadas (ESAE). In order to estimate the AGB, we
evaluated the performance of five machine learning models
(Classification and Regression Trees CART; Cubist CB, Partial
Least Squares Regression PLS; Random Forest RF; and Support Vector
Machine SVM) and four sets of metrics (reflectance, narrowband
vegetation indices VIs; absorption band parameters; and the
combination of these attributes). The lowest root mean square
error (RMSE) was obtained for RF using VIs (29%) and a combination
of metrics (28%). For VIs, RF differed from CUB, PLS and SVM at 5%
significance level. From cross-validation results, the RMSE was
26.36% for grasslands, 35.04% for open savannas, and 24.85% for
dense savannas. The RF model with VIs had the most stable
predictive performance across the models, as indicated by small
variations in RMSE from CART to SVM. The five most important
ranked VIs in the RF model were the Normalized Difference
Vegetation Index (NDVI), Pigment Specific Simple Ratio (PSSR),
Enhanced Vegetation Index (EVI), Red Edge Normalized Difference
Vegetation Index (RENDVI) and Structure Insensitive Pigment Index
(SIPI). Most of their relationships with AGB were non-linear. The
resultant AGB estimates showed consistent results with a
vegetation cover map of the ESAE. Areas of the ESAE with AGB lower
than 10 Mg.ha\−1 were coincident with the occurrence of
grassland physiognomies (savanna grasslands and shrub savannas),
while areas with AGB higher than 25 Mg.ha\−1 matched the
occurrence of dense savanna physiognomies (woodland savanna and
dense woodland savanna). Grassland areas showed larger values of
coefficient of variation (CV) than areas of dense savannas. These
first-hand results set a baseline of models and metrics for AGB
modeling of savannas during the future transition from current
sampling-type hyperspectral missions (< 10 km of swath) to
large-coverage hyperspectral satellites (> 100 km of swath).",
doi = "10.1080/15481603.2021.1969630",
url = "http://dx.doi.org/10.1080/15481603.2021.1969630",
issn = "1548-1603",
language = "en",
targetfile = "jacon_2021_aboveground.pdf",
urlaccessdate = "05 maio 2024"
}