2009
DOI: 10.1590/s0100-204x2009001200021
|View full text |Cite
|
Sign up to set email alerts
|

Mineração de dados para inferência de relações solo-paisagem em mapeamentos digitais de solo

Abstract: Resumo -O objetivo deste trabalho foi desenvolver uma metodologia para mapeamento digital de solos na escala 1:100.000 com a aplicação de técnicas de mineração de dados a descritores de relevo e a dados de mapas geológico e pedológico preexistentes. Foi criada uma base de dados digitais a partir de cartas topográfi cas e temáticas, que permitiu elaboração do modelo digital de elevação (MDE) da folha Dois Córregos, SP (escala 1:50.000). A partir do MDE, foram calculados os parâmetros geomorfométricos declividad… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
8
1
11

Year Published

2012
2012
2021
2021

Publication Types

Select...
8

Relationship

2
6

Authors

Journals

citations
Cited by 19 publications
(20 citation statements)
references
References 15 publications
(21 reference statements)
0
8
1
11
Order By: Relevance
“…In approximately 60 % of the points (pixels) on the landscape, the same class existing on the original map was attributed by the models to the predictive maps (Table 1). This value is greater than the values found in the literature of 43 % (Crivelenti et al, 2009), 38.6 % (Coelho & Giasson, 2010 and 51.8 % (Giasson et al, 2011). In spite of a greater prediction quality obtained in this study in relation to the studies found in the literature, it may be observed that with the displacement of 100 m, the class ACha2 was not predicted.…”
Section: Resultscontrasting
confidence: 88%
See 1 more Smart Citation
“…In approximately 60 % of the points (pixels) on the landscape, the same class existing on the original map was attributed by the models to the predictive maps (Table 1). This value is greater than the values found in the literature of 43 % (Crivelenti et al, 2009), 38.6 % (Coelho & Giasson, 2010 and 51.8 % (Giasson et al, 2011). In spite of a greater prediction quality obtained in this study in relation to the studies found in the literature, it may be observed that with the displacement of 100 m, the class ACha2 was not predicted.…”
Section: Resultscontrasting
confidence: 88%
“…According to Qi & Zhu (2003), the basic idea of formalization of the soil-landscape relationships contained in choropleth soil maps consists of recovering pedological knowledge contained in the map by application of data mining techniques. The information of the soil polygons on choropleth maps has proven to be applicable to DSM (Crivelenti et al, 2009;Giasson et al, 2011;ten Caten et al, 2011a).…”
Section: Introductionmentioning
confidence: 99%
“…In order to have this correction in the individual wood volume, it used the form factor equal to 0.4 (OLIVEIRA et al, 2009). The Huber's formula, adapted and described by Péllico Netto (2004), is obtained by the product of the sectional area (taken by half of the section) and sectional length determined by equation 1.…”
Section: Collection and Determination Of Dendrometric And Soil Attribmentioning
confidence: 99%
“…Among the computational techniques used to interfere in the development of eucalyptus, due to heterogeneity found in the soil, data mining techniques aim to find patterns in large amount of data to infer a dependent variable from a set of features associated with this variable (CRIVELENTI et al, 2009).…”
Section: Introductionmentioning
confidence: 99%
“…As cartas topográficas 1:50.000 do Instituto Brasileiro de Geografia e Estatística (IBGE) e disponíveis em formato raster (http://www.ibge.gov.br/home/ geociencias/cartografia/default.shtm) foram vetorizadas no programa ArcGIS, obtendo-se os planos de informação (PIs): malha viária, composto de ferrovias, caminhos, estradas de terra, estradas pavimentadas e rodovias; hidrografia, composto de rios e lagos/represas; hipsometria, que compreende curvas de nível e pontos cotados; e manchas urbanas, digitalizadas em polígonos. O mapa temático de geologia (polígonos e linhas) na escala 1:500.000 (IPT, 1981b) e as cartas pedológicas das quadrículas de Brotas (Almeida et al, 1981) e Piracicaba (Oliveira & Prado, 1989) Crivelenti et al (2009), selecionaram-se variáveis morfométricas para a composição do banco de dados: curvatura em perfil, curvatura em planta, distância diagonal e declividade. Os protocolos de treinamento foram completados com a seleção das variáveis: altitude, direção de fluxo e índice topográfico combinado (Moore et al, 1993;Irvin et al, 1997;Carvalho Júnior et al, 2003;Borges et al, 2005;Chagas, 2006;Valladares & Hot, 2006).…”
Section: Methodsunclassified