@Article{BolfePSSBVSV:2023:MaLeAp,
author = "Bolfe, {\'E}dson Luis and Parreiras, Taya Cristo and Silva, Lucas
Augusto Pereira da and Sano, Edson Eyji and Bettiol, Giovana
Maranh{\~a}o and Victoria, Daniel de Castro and Sanches, Ieda
Del'Arco and Vicente, Luiz Eduardo",
affiliation = "{Embrapa Agricultura Digital} and {Universidade Estadual de
Campinas (UNICAMP)} and {Universidade Federal de Uberl{\^a}ndia
(UFU)} and {Embrapa Cerrados} and {Embrapa Cerrados} and {Embrapa
Agricultura Digital} and {Instituto Nacional de Pesquisas
Espaciais (INPE)} and {Embrapa Meio Ambiente}",
title = "Mapping Agricultural Intensification in the Brazilian Savanna: A
Machine Learning Approach Using Harmonized Data from Landsat
Sentinel-2",
journal = "ISPRS International Journal of Geo-Information",
year = "2023",
volume = "12",
number = "7",
pages = "e263",
month = "July",
keywords = "agriculture, artificial intelligence, Cerrado, HLS, multisensor,
remote sensing.",
abstract = "Agricultural intensification practices have been adopted in the
Brazilian savanna (Cerrado), mainly in the transition between
Cerrado and the Amazon Forest, to increase productivity while
reducing pressure for new land clearing. Due to the growing demand
for more sustainable practices, more accurate information on
geospatial monitoring is required. Remote sensing products and
artificial intelligence models for pixel-by-pixel classification
have great potential. Therefore, we developed a methodological
framework with spectral indices (Normalized Difference Vegetation
Index (NDVI), Normalized Difference Water Index (NDWI), and
Soil-Adjusted Vegetation Index (SAVI)) derived from the Harmonized
Landsat Sentinel-2 (HLS) and machine learning algorithms (Random
Forest (RF), Artificial Neural Networks (ANNs), and Extreme
Gradient Boosting (XGBoost)) to map agricultural intensification
considering three hierarchical levels, i.e., temporary crops
(level 1), the number of crop cycles (level 2), and the crop types
from the second season in double-crop systems (level 3) in the
20212022 crop growing season in the municipality of Sorriso, Mato
Grosso State, Brazil. All models were statistically similar, with
an overall accuracy between 85 and 99%. The NDVI was the most
suitable index for discriminating cultures at all hierarchical
levels. The RF-NDVI combination mapped best at level 1, while at
levels 2 and 3, the best model was XGBoost-NDVI. Our results
indicate the great potential of combining HLS data and machine
learning to provide accurate geospatial information for
decision-makers in monitoring agricultural intensification, with
an aim toward the sustainable development of agriculture.",
doi = "10.3390/ijgi12070263",
url = "http://dx.doi.org/10.3390/ijgi12070263",
issn = "2220-9964",
label = "self-archiving-INPE-MCTIC-GOV-BR",
language = "en",
targetfile = "ijgi-12-00263.pdf",
urlaccessdate = "16 jun. 2024"
}