@InProceedings{SilvaMellFons:2015:InArCo,
author = "Silva, Alexsandro C{\^a}ndido de Oliveira and Mello, Marcio Pupin
and Fonseca, Leila Maria Garcia",
affiliation = "{Instituto Nacional de Pesquisas Espaciais (INPE)} and {} and
{Instituto Nacional de Pesquisas Espaciais (INPE)}",
title = "Intelig{\^e}ncia Artificial como ferramenta para direcionar a
expans{\~a}o sustent{\'a}vel da cana-de-a{\c{c}}{\'u}car no
Estado de S{\~a}o Paulo",
booktitle = "Anais...",
year = "2015",
editor = "Gherardi, Douglas Francisco Marcolino and Arag{\~a}o, Luiz
Eduardo Oliveira e Cruz de",
pages = "3423--3430",
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 = "Predictive models have been used to understand several phenomena
in the field of Earth sciences. Bayesian networks have become
increasingly popular due to its potential to model such phenomena
and, through graphical representation, state the relationship
among variables with probabilistic models associated. This paper
presents an improved algorithm of Bayesian networks, implemented
in R software, able of handling raster data for remote sensing
applications: e-BayNeRD (enhanced Bayesian Network for Raster
Data). A case study was used to describe the main changes and test
the enhanced version of the algorithm. Based on observed values
for terrain slope, soil and fertility, edaphoclimatic aptitude and
the Agri-environmental zoning, suitable areas for sustainable
expansion of sugarcane in S{\~a}o Paulo State were mapped.",
conference-location = "Jo{\~a}o Pessoa",
conference-year = "25-29 abr. 2015",
isbn = "978-85-17-0076-8",
label = "677",
language = "pt",
organisation = "Instituto Nacional de Pesquisas Espaciais (INPE)",
ibi = "8JMKD3MGP6W34M/3JM4BM2",
url = "http://urlib.net/ibi/8JMKD3MGP6W34M/3JM4BM2",
targetfile = "p0677.pdf",
type = "Geoprocessamento e aplica{\c{c}}{\~o}es",
urlaccessdate = "27 abr. 2024"
}