@InProceedings{SilvaFonsMell:2015:ReBaMa,
author = "Silva, Alexsandro C{\^a}ndido de Oliveira and Fonseca, Leila
Maria Garcia and Mello, Marcio Pupin",
affiliation = "{Instituto Nacional de Pesquisas Espaciais (INPE)} and {Instituto
Nacional de Pesquisas Espaciais (INPE)}",
title = "Redes Bayesianas no mapeamento de culturas de ver{\~a}o no Estado
do Paran{\'a}",
booktitle = "Anais...",
year = "2015",
editor = "Gherardi, Douglas Francisco Marcolino and Arag{\~a}o, Luiz
Eduardo Oliveira e Cruz de",
pages = "2379--2386",
organization = "Simp{\'o}sio Brasileiro de Sensoriamento Remoto, 17. (SBSR)",
publisher = "Instituto Nacional de Pesquisas Espaciais (INPE)",
address = "S{\~a}o Jos{\'e} dos Campos",
abstract = "In Brazil, the methodologies employed to obtain official
agricultural statistics are subjective, and take a long time to be
realized. Remote sensing technologies, combined with artificial
intelligence, allow quick and accurate outcomes, which may help
these methodologies to be more efficient. This paper aims at
proposing the use of BayNeRD (Bayesian Network for Raster Data)
algorithm to map summer crops areas (soybean and maize) in
Paran{\'a} State Brazil. BayNeRD is a computer-aided Bayesian
Network method that is able to incorporate experts knowledge to
handle with raster data. The main outcome of BayNeRD is a
probability image, wherein each pixel contains the probability of
occurrence of target under study. Based on observations of a
vegetation index, terrain slope, soil aptitude and other
variables, BayNeRD was able to map soybean and maize plantations
in Paran{\'a} State with 82% of sensitivity and 85% of
specificity. Moreover, the probability image showed strong
adherence to the reference data used for accuracy assessment and
to the literature, denoting BayNeRDs potential to be applicable
for agricultural inference through remote sensoring and ancillary
data.",
conference-location = "Jo{\~a}o Pessoa",
conference-year = "25-29 abr. 2015",
isbn = "978-85-17-0076-8",
label = "480",
language = "pt",
organisation = "Instituto Nacional de Pesquisas Espaciais (INPE)",
ibi = "8JMKD3MGP6W34M/3JM49U6",
url = "http://urlib.net/ibi/8JMKD3MGP6W34M/3JM49U6",
targetfile = "p0480.pdf",
type = "Geoprocessamento e aplica{\c{c}}{\~o}es",
urlaccessdate = "03 jun. 2024"
}