Decision trees for digital soil mapping on subtropical basaltic steeplands

Detalhes bibliográficos
Autor(a) principal: Giasson,Elvio
Data de Publicação: 2011
Outros Autores: Sarmento,Eliana Casco, Weber,Eliseu, Flores,Carlos Alberto, Hasenack,Heinrich
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Scientia Agrícola (Online)
Texto Completo: http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0103-90162011000200006
Resumo: When soil surveys are not available for land use planning activities, digital soil mapping techniques can be of assistance. Soil surveyors can process spatial information faster, to assist in the execution of traditional soil survey or predict the occurrence of soil classes across landscapes. Decision tree techniques were evaluated as tools for predicting the ocurrence of soil classes in basaltic steeplands in South Brazil. Several combinations of types of decicion tree algorithms and number of elements on terminal nodes of trees were compared using soil maps with both original and simplified legends. In general, decision tree analysis was useful for predicting occurrence of soil mapping units. Decision trees with fewer elements on terminal nodes yield higher accuracies, and legend simplification (aggregation) reduced the precision of predictions. Algorithm J48 had better performance than BF Tree, RepTree, Random Tree, and Simple Chart.
id USP-18_e3aa62620886a2d0c8fe82c281820054
oai_identifier_str oai:scielo:S0103-90162011000200006
network_acronym_str USP-18
network_name_str Scientia Agrícola (Online)
repository_id_str
spelling Decision trees for digital soil mapping on subtropical basaltic steeplandsGISsoil surveyterrain analysisWhen soil surveys are not available for land use planning activities, digital soil mapping techniques can be of assistance. Soil surveyors can process spatial information faster, to assist in the execution of traditional soil survey or predict the occurrence of soil classes across landscapes. Decision tree techniques were evaluated as tools for predicting the ocurrence of soil classes in basaltic steeplands in South Brazil. Several combinations of types of decicion tree algorithms and number of elements on terminal nodes of trees were compared using soil maps with both original and simplified legends. In general, decision tree analysis was useful for predicting occurrence of soil mapping units. Decision trees with fewer elements on terminal nodes yield higher accuracies, and legend simplification (aggregation) reduced the precision of predictions. Algorithm J48 had better performance than BF Tree, RepTree, Random Tree, and Simple Chart.Escola Superior de Agricultura "Luiz de Queiroz"2011-04-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S0103-90162011000200006Scientia Agricola v.68 n.2 2011reponame:Scientia Agrícola (Online)instname:Universidade de São Paulo (USP)instacron:USP10.1590/S0103-90162011000200006info:eu-repo/semantics/openAccessGiasson,ElvioSarmento,Eliana CascoWeber,EliseuFlores,Carlos AlbertoHasenack,Heinricheng2011-03-31T00:00:00Zoai:scielo:S0103-90162011000200006Revistahttp://revistas.usp.br/sa/indexPUBhttps://old.scielo.br/oai/scielo-oai.phpscientia@usp.br||alleoni@usp.br1678-992X0103-9016opendoar:2011-03-31T00:00Scientia Agrícola (Online) - Universidade de São Paulo (USP)false
dc.title.none.fl_str_mv Decision trees for digital soil mapping on subtropical basaltic steeplands
title Decision trees for digital soil mapping on subtropical basaltic steeplands
spellingShingle Decision trees for digital soil mapping on subtropical basaltic steeplands
Giasson,Elvio
GIS
soil survey
terrain analysis
title_short Decision trees for digital soil mapping on subtropical basaltic steeplands
title_full Decision trees for digital soil mapping on subtropical basaltic steeplands
title_fullStr Decision trees for digital soil mapping on subtropical basaltic steeplands
title_full_unstemmed Decision trees for digital soil mapping on subtropical basaltic steeplands
title_sort Decision trees for digital soil mapping on subtropical basaltic steeplands
author Giasson,Elvio
author_facet Giasson,Elvio
Sarmento,Eliana Casco
Weber,Eliseu
Flores,Carlos Alberto
Hasenack,Heinrich
author_role author
author2 Sarmento,Eliana Casco
Weber,Eliseu
Flores,Carlos Alberto
Hasenack,Heinrich
author2_role author
author
author
author
dc.contributor.author.fl_str_mv Giasson,Elvio
Sarmento,Eliana Casco
Weber,Eliseu
Flores,Carlos Alberto
Hasenack,Heinrich
dc.subject.por.fl_str_mv GIS
soil survey
terrain analysis
topic GIS
soil survey
terrain analysis
description When soil surveys are not available for land use planning activities, digital soil mapping techniques can be of assistance. Soil surveyors can process spatial information faster, to assist in the execution of traditional soil survey or predict the occurrence of soil classes across landscapes. Decision tree techniques were evaluated as tools for predicting the ocurrence of soil classes in basaltic steeplands in South Brazil. Several combinations of types of decicion tree algorithms and number of elements on terminal nodes of trees were compared using soil maps with both original and simplified legends. In general, decision tree analysis was useful for predicting occurrence of soil mapping units. Decision trees with fewer elements on terminal nodes yield higher accuracies, and legend simplification (aggregation) reduced the precision of predictions. Algorithm J48 had better performance than BF Tree, RepTree, Random Tree, and Simple Chart.
publishDate 2011
dc.date.none.fl_str_mv 2011-04-01
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0103-90162011000200006
url http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0103-90162011000200006
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 10.1590/S0103-90162011000200006
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv text/html
dc.publisher.none.fl_str_mv Escola Superior de Agricultura "Luiz de Queiroz"
publisher.none.fl_str_mv Escola Superior de Agricultura "Luiz de Queiroz"
dc.source.none.fl_str_mv Scientia Agricola v.68 n.2 2011
reponame:Scientia Agrícola (Online)
instname:Universidade de São Paulo (USP)
instacron:USP
instname_str Universidade de São Paulo (USP)
instacron_str USP
institution USP
reponame_str Scientia Agrícola (Online)
collection Scientia Agrícola (Online)
repository.name.fl_str_mv Scientia Agrícola (Online) - Universidade de São Paulo (USP)
repository.mail.fl_str_mv scientia@usp.br||alleoni@usp.br
_version_ 1748936462397603840

Registros relacionados