@InProceedings{SantosJoMoPaSoSi:2023:GoEaEn,
author = "Santos, Marcelo Henrique de Oliveira and Johann, Jerry Adriani and
Moura, Valdir and Paludo, Alex and Souza, Ranieli dos Anjos de and
Silveira, Jo{\~a}o Felipe Cesar",
affiliation = "{Universidade Estadual do Oeste do Paran{\'a} (UNIOESTE)} and
{Universidade Estadual do Oeste do Paran{\'a} (UNIOESTE)} and
{Instituto Federal de Rond{\^o}nia (IFRO)} and {Universidade
Estadual do Oeste do Paran{\'a} (UNIOESTE)} and {Instituto
Federal de Rond{\^o}nia (IFRO)} and {Universidade Estadual do
Oeste do Paran{\'a} (UNIOESTE)}",
title = "Google Earth Engine no mapemento de {\'a}reas de pastagem e
culturas anuais em Rond{\^o}nia",
booktitle = "Anais...",
year = "2023",
editor = "Gherardi, Douglas Francisco Marcolino and Arag{\~a}o, Luiz
Eduardo Oliveira e Cruz de and Sanches, Ieda DelArco",
pages = "e155984",
organization = "Simp{\'o}sio Brasileiro de Sensoriamento Remoto, 20. (SBSR)",
publisher = "Instituto Nacional de Pesquisas Espaciais (INPE)",
address = "S{\~a}o Jos{\'e} dos Campos",
keywords = "{\'{\i}}ndices de vegeta{\c{c}}{\~a}o, agricultura,
pecu{\'a}ria, processamento em nuvem, vegetation indices,
agriculture, livestock, cloud processing, orbital images.imagens
orbitais.",
abstract = "Este estudo teve como objetivo realizar o mapeamento de {\'a}reas
com culturas anuais (ver{\~a}o e inverno) e pastagens no estado
de Rond{\^o}nia, utilizando imagens de sat{\'e}lite e aplicando
t{\'e}cnicas de sensoriamento remoto e de aprendizagem de
m{\'a}quina. Para a realiza{\c{c}}{\~a}o dos mapeamentos se
utilizaram as composi{\c{c}}{\~o}es RGB (8,11,4) para o Sentinel
2 e RGB (5,6,4) para o Landsat 8 e {\'{\i}}ndices de
vegeta{\c{c}}{\~a}o (NDVI, EVI e SAVI) de forma conjunta com no
algoritmo classificador Naive Bayes. A classifica{\c{c}}{\~a}o
foi realizada utilizando a platafor ABSTRACT: This study aimed to
map areas with annual crops (summer and winter) and pastures in
Rond{\^o}nia state, using satellite images and applying remote
sensing and machine learning techniques. To carry out the
mappings, the RGB (8,11,4) compositions Sentinel 2 and RGB (5,6,4)
Landsat 8 and vegetation indices (NDVI, EVI and SAVI) were user
together with the Naive Bayes classifier algorithm. The
classification was performed using the Google Earth Engine
platform. With the classification, the areas with summer, winter
and pasture crops were quantified, by Rond{\^o}nia microregion,
for 2020/2021 harvest. As a result, 384 thousand ha were mapped
with summer crops, 219 thousand ha with winter crops and 7.73
million ha with pasture.",
conference-location = "Florian{\'o}polis",
conference-year = "02-05 abril 2023",
isbn = "978-65-89159-04-9",
language = "pt",
organisation = "Instituto Nacional de Pesquisas Espaciais (INPE)",
ibi = "8JMKD3MGP6W34M/492GAEH",
url = "http://urlib.net/ibi/8JMKD3MGP6W34M/492GAEH",
targetfile = "155984.pdf",
type = "Produ{\c{c}}{\~a}o e previs{\~a}o agr{\'{\i}}cola",
urlaccessdate = "09 maio 2024"
}