Data mining to infer soil-landscape relationships in digital soil mapping
Autor(a) principal: | |
---|---|
Data de Publicação: | 2010 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Pesquisa Agropecuária Brasileira (Online) |
Texto Completo: | https://seer.sct.embrapa.br/index.php/pab/article/view/2215 |
Resumo: | The objective of this work was to develop a methodology for digital soil mapping at a 1:100,000 scale by applying data mining techniques to preexisting relief descriptors and data from pedological and geological maps. A digital database was created from topographic and thematic maps, and allowed the generation of a digital elevation model (DEM) of the Dois Córregos (SP, Brazil) sheet (1:50,000 scale). The slope gradient, slope profile, contour profile, basin contributing area, and diagonal distance to drainage geomorphometric parameters were extracted from the DEM. The matrix which associated this georeferred data was analyzed by means of decision trees within the Weka machine-learning environment, and a model for soil mapping unit prediction was generated. The overall model accuracy increased from 54 to 61% when soil classes with no chances of being predicted were excluded. The association of data mining techniques with geographical information systems produced digital soil maps feasible to be used in studies requiring less detail than those made with the original reference soil maps. |
id |
EMBRAPA-4_aa3bd89d34a3c55c6b97fa268a342f32 |
---|---|
oai_identifier_str |
oai:ojs.seer.sct.embrapa.br:article/2215 |
network_acronym_str |
EMBRAPA-4 |
network_name_str |
Pesquisa Agropecuária Brasileira (Online) |
repository_id_str |
|
spelling |
Data mining to infer soil-landscape relationships in digital soil mappingMineração de dados para inferência de relações solo-paisagem em mapeamentos digitais de solodecision trees; soil survey; geomorphometric parameters; geographic information systemárvores de decisão; levantamento pedológico; parâmetros geomorfométricos; sistemas de informação geográficaThe objective of this work was to develop a methodology for digital soil mapping at a 1:100,000 scale by applying data mining techniques to preexisting relief descriptors and data from pedological and geological maps. A digital database was created from topographic and thematic maps, and allowed the generation of a digital elevation model (DEM) of the Dois Córregos (SP, Brazil) sheet (1:50,000 scale). The slope gradient, slope profile, contour profile, basin contributing area, and diagonal distance to drainage geomorphometric parameters were extracted from the DEM. The matrix which associated this georeferred data was analyzed by means of decision trees within the Weka machine-learning environment, and a model for soil mapping unit prediction was generated. The overall model accuracy increased from 54 to 61% when soil classes with no chances of being predicted were excluded. The association of data mining techniques with geographical information systems produced digital soil maps feasible to be used in studies requiring less detail than those made with the original reference soil maps.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 topográficas 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 declividade, curvaturas em planta e perfil, área de contribuição e distância diagonal de drenagem. A matriz que associou esses dados georreferenciados foi analisada por meio de árvores de decisão, no ambiente de aprendizado de máquina Weka, o que gerou um modelo de predição de unidades de mapeamento de solos. A acurácia geral do modelo aumentou de 54 para 61% com a eliminação das classes com probabilidade nula de ocorrência. A associação da mineração de dados com sistemas de informações geográficas permite a elaboração de mapas digitais passíveis de uso em estudos que requeiram menor detalhamento que aqueles realizados com o mapa original.Pesquisa Agropecuaria BrasileiraPesquisa Agropecuária BrasileiraCrivelenti, Rafael CastroCoelho, Ricardo MarquesAdami, Samuel FernandoOliveira, Stanley Robson de Medeiros2010-12-22info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://seer.sct.embrapa.br/index.php/pab/article/view/2215Pesquisa Agropecuaria Brasileira; v.44, n.12, dez. 2009; 1707-1715Pesquisa Agropecuária Brasileira; v.44, n.12, dez. 2009; 1707-17151678-39210100-104xreponame:Pesquisa Agropecuária Brasileira (Online)instname:Empresa Brasileira de Pesquisa Agropecuária (Embrapa)instacron:EMBRAPAporhttps://seer.sct.embrapa.br/index.php/pab/article/view/2215/5920https://seer.sct.embrapa.br/index.php/pab/article/downloadSuppFile/2215/1607https://seer.sct.embrapa.br/index.php/pab/article/downloadSuppFile/2215/1627info:eu-repo/semantics/openAccess2012-06-17T11:54:28Zoai:ojs.seer.sct.embrapa.br:article/2215Revistahttp://seer.sct.embrapa.br/index.php/pabPRIhttps://old.scielo.br/oai/scielo-oai.phppab@sct.embrapa.br || sct.pab@embrapa.br1678-39210100-204Xopendoar:2012-06-17T11:54:28Pesquisa Agropecuária Brasileira (Online) - Empresa Brasileira de Pesquisa Agropecuária (Embrapa)false |
dc.title.none.fl_str_mv |
Data mining to infer soil-landscape relationships in digital soil mapping Mineração de dados para inferência de relações solo-paisagem em mapeamentos digitais de solo |
title |
Data mining to infer soil-landscape relationships in digital soil mapping |
spellingShingle |
Data mining to infer soil-landscape relationships in digital soil mapping Crivelenti, Rafael Castro decision trees; soil survey; geomorphometric parameters; geographic information system árvores de decisão; levantamento pedológico; parâmetros geomorfométricos; sistemas de informação geográfica |
title_short |
Data mining to infer soil-landscape relationships in digital soil mapping |
title_full |
Data mining to infer soil-landscape relationships in digital soil mapping |
title_fullStr |
Data mining to infer soil-landscape relationships in digital soil mapping |
title_full_unstemmed |
Data mining to infer soil-landscape relationships in digital soil mapping |
title_sort |
Data mining to infer soil-landscape relationships in digital soil mapping |
author |
Crivelenti, Rafael Castro |
author_facet |
Crivelenti, Rafael Castro Coelho, Ricardo Marques Adami, Samuel Fernando Oliveira, Stanley Robson de Medeiros |
author_role |
author |
author2 |
Coelho, Ricardo Marques Adami, Samuel Fernando Oliveira, Stanley Robson de Medeiros |
author2_role |
author author author |
dc.contributor.none.fl_str_mv |
|
dc.contributor.author.fl_str_mv |
Crivelenti, Rafael Castro Coelho, Ricardo Marques Adami, Samuel Fernando Oliveira, Stanley Robson de Medeiros |
dc.subject.por.fl_str_mv |
decision trees; soil survey; geomorphometric parameters; geographic information system árvores de decisão; levantamento pedológico; parâmetros geomorfométricos; sistemas de informação geográfica |
topic |
decision trees; soil survey; geomorphometric parameters; geographic information system árvores de decisão; levantamento pedológico; parâmetros geomorfométricos; sistemas de informação geográfica |
description |
The objective of this work was to develop a methodology for digital soil mapping at a 1:100,000 scale by applying data mining techniques to preexisting relief descriptors and data from pedological and geological maps. A digital database was created from topographic and thematic maps, and allowed the generation of a digital elevation model (DEM) of the Dois Córregos (SP, Brazil) sheet (1:50,000 scale). The slope gradient, slope profile, contour profile, basin contributing area, and diagonal distance to drainage geomorphometric parameters were extracted from the DEM. The matrix which associated this georeferred data was analyzed by means of decision trees within the Weka machine-learning environment, and a model for soil mapping unit prediction was generated. The overall model accuracy increased from 54 to 61% when soil classes with no chances of being predicted were excluded. The association of data mining techniques with geographical information systems produced digital soil maps feasible to be used in studies requiring less detail than those made with the original reference soil maps. |
publishDate |
2010 |
dc.date.none.fl_str_mv |
2010-12-22 |
dc.type.none.fl_str_mv |
|
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://seer.sct.embrapa.br/index.php/pab/article/view/2215 |
url |
https://seer.sct.embrapa.br/index.php/pab/article/view/2215 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
https://seer.sct.embrapa.br/index.php/pab/article/view/2215/5920 https://seer.sct.embrapa.br/index.php/pab/article/downloadSuppFile/2215/1607 https://seer.sct.embrapa.br/index.php/pab/article/downloadSuppFile/2215/1627 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Pesquisa Agropecuaria Brasileira Pesquisa Agropecuária Brasileira |
publisher.none.fl_str_mv |
Pesquisa Agropecuaria Brasileira Pesquisa Agropecuária Brasileira |
dc.source.none.fl_str_mv |
Pesquisa Agropecuaria Brasileira; v.44, n.12, dez. 2009; 1707-1715 Pesquisa Agropecuária Brasileira; v.44, n.12, dez. 2009; 1707-1715 1678-3921 0100-104x reponame:Pesquisa Agropecuária Brasileira (Online) instname:Empresa Brasileira de Pesquisa Agropecuária (Embrapa) instacron:EMBRAPA |
instname_str |
Empresa Brasileira de Pesquisa Agropecuária (Embrapa) |
instacron_str |
EMBRAPA |
institution |
EMBRAPA |
reponame_str |
Pesquisa Agropecuária Brasileira (Online) |
collection |
Pesquisa Agropecuária Brasileira (Online) |
repository.name.fl_str_mv |
Pesquisa Agropecuária Brasileira (Online) - Empresa Brasileira de Pesquisa Agropecuária (Embrapa) |
repository.mail.fl_str_mv |
pab@sct.embrapa.br || sct.pab@embrapa.br |
_version_ |
1793416698046447616 |