Spatial Disaggregation of Multi-Component Soil Map Units Using Legacy Data and a Tree-Based Algorithm in Southern Brazil
Autor(a) principal: | |
---|---|
Data de Publicação: | 2018 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Revista Brasileira de Ciência do Solo (Online) |
Texto Completo: | http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0100-06832018000100303 |
Resumo: | ABSTRACT Soil surveys often contain multi-component map units comprising two or more soil classes, whose spatial distribution within the map unit is not represented. Digital Soil Mapping tools supported by information from soil surveys make it possible to predict where these classes are located. The aim of this study was to develop a methodology to increase the detail of conventional soil maps by means of spatial disaggregation of multi-component map units and to predict the spatial location of the derived soil classes. Three digital maps of terrain variables - slope, landforms, and topographic wetness index - were correlated with the soil map and 72 georeferenced profiles from the Porto Alegre soil survey. Explicit rules that expressed regional soil-landscape relationships were formulated based on the resulting combinations. These rules were used to select typical areas of occurrence of each soil class and to train a decision tree model to predict the occurrence of individualized soil classes. Validation of the soil map predictions was conducted by comparison with available soil profiles. The soil map produced showed high agreement (80.5 % accuracy) with the soil classes observed in the soil profiles; Ultisols and Lithic Udorthents were predicted with greater accuracy. The soil variables selected in this study were suitable to represent the soil-landscape relationships, suggesting potential use in future studies. This approach developed a more detailed soil map relevant to current demands for soil information and has potential to be replicated in other areas in which data availability is similar. |
id |
SBCS-1_e8b3760f63532716f591c68f13a2e431 |
---|---|
oai_identifier_str |
oai:scielo:S0100-06832018000100303 |
network_acronym_str |
SBCS-1 |
network_name_str |
Revista Brasileira de Ciência do Solo (Online) |
repository_id_str |
|
spelling |
Spatial Disaggregation of Multi-Component Soil Map Units Using Legacy Data and a Tree-Based Algorithm in Southern Brazildigital soil mappingsoil-landscape relationshipsdecision treesABSTRACT Soil surveys often contain multi-component map units comprising two or more soil classes, whose spatial distribution within the map unit is not represented. Digital Soil Mapping tools supported by information from soil surveys make it possible to predict where these classes are located. The aim of this study was to develop a methodology to increase the detail of conventional soil maps by means of spatial disaggregation of multi-component map units and to predict the spatial location of the derived soil classes. Three digital maps of terrain variables - slope, landforms, and topographic wetness index - were correlated with the soil map and 72 georeferenced profiles from the Porto Alegre soil survey. Explicit rules that expressed regional soil-landscape relationships were formulated based on the resulting combinations. These rules were used to select typical areas of occurrence of each soil class and to train a decision tree model to predict the occurrence of individualized soil classes. Validation of the soil map predictions was conducted by comparison with available soil profiles. The soil map produced showed high agreement (80.5 % accuracy) with the soil classes observed in the soil profiles; Ultisols and Lithic Udorthents were predicted with greater accuracy. The soil variables selected in this study were suitable to represent the soil-landscape relationships, suggesting potential use in future studies. This approach developed a more detailed soil map relevant to current demands for soil information and has potential to be replicated in other areas in which data availability is similar.Sociedade Brasileira de Ciência do Solo2018-01-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S0100-06832018000100303Revista Brasileira de Ciência do Solo v.42 2018reponame:Revista Brasileira de Ciência do Solo (Online)instname:Sociedade Brasileira de Ciência do Solo (SBCS)instacron:SBCS10.1590/18069657rbcs20170193info:eu-repo/semantics/openAccessMachado,Israel RosaGiasson,ElvioCampos,Alcinei RibeiroCosta,José Janderson FerreiraSilva,Elisângela Benedet daBonfatti,Benito Robertoeng2018-03-06T00:00:00Zoai:scielo:S0100-06832018000100303Revistahttp://www.scielo.br/scielo.php?script=sci_serial&pid=0100-0683&lng=es&nrm=isohttps://old.scielo.br/oai/scielo-oai.php||sbcs@ufv.br1806-96570100-0683opendoar:2018-03-06T00:00Revista Brasileira de Ciência do Solo (Online) - Sociedade Brasileira de Ciência do Solo (SBCS)false |
dc.title.none.fl_str_mv |
Spatial Disaggregation of Multi-Component Soil Map Units Using Legacy Data and a Tree-Based Algorithm in Southern Brazil |
title |
Spatial Disaggregation of Multi-Component Soil Map Units Using Legacy Data and a Tree-Based Algorithm in Southern Brazil |
spellingShingle |
Spatial Disaggregation of Multi-Component Soil Map Units Using Legacy Data and a Tree-Based Algorithm in Southern Brazil Machado,Israel Rosa digital soil mapping soil-landscape relationships decision trees |
title_short |
Spatial Disaggregation of Multi-Component Soil Map Units Using Legacy Data and a Tree-Based Algorithm in Southern Brazil |
title_full |
Spatial Disaggregation of Multi-Component Soil Map Units Using Legacy Data and a Tree-Based Algorithm in Southern Brazil |
title_fullStr |
Spatial Disaggregation of Multi-Component Soil Map Units Using Legacy Data and a Tree-Based Algorithm in Southern Brazil |
title_full_unstemmed |
Spatial Disaggregation of Multi-Component Soil Map Units Using Legacy Data and a Tree-Based Algorithm in Southern Brazil |
title_sort |
Spatial Disaggregation of Multi-Component Soil Map Units Using Legacy Data and a Tree-Based Algorithm in Southern Brazil |
author |
Machado,Israel Rosa |
author_facet |
Machado,Israel Rosa Giasson,Elvio Campos,Alcinei Ribeiro Costa,José Janderson Ferreira Silva,Elisângela Benedet da Bonfatti,Benito Roberto |
author_role |
author |
author2 |
Giasson,Elvio Campos,Alcinei Ribeiro Costa,José Janderson Ferreira Silva,Elisângela Benedet da Bonfatti,Benito Roberto |
author2_role |
author author author author author |
dc.contributor.author.fl_str_mv |
Machado,Israel Rosa Giasson,Elvio Campos,Alcinei Ribeiro Costa,José Janderson Ferreira Silva,Elisângela Benedet da Bonfatti,Benito Roberto |
dc.subject.por.fl_str_mv |
digital soil mapping soil-landscape relationships decision trees |
topic |
digital soil mapping soil-landscape relationships decision trees |
description |
ABSTRACT Soil surveys often contain multi-component map units comprising two or more soil classes, whose spatial distribution within the map unit is not represented. Digital Soil Mapping tools supported by information from soil surveys make it possible to predict where these classes are located. The aim of this study was to develop a methodology to increase the detail of conventional soil maps by means of spatial disaggregation of multi-component map units and to predict the spatial location of the derived soil classes. Three digital maps of terrain variables - slope, landforms, and topographic wetness index - were correlated with the soil map and 72 georeferenced profiles from the Porto Alegre soil survey. Explicit rules that expressed regional soil-landscape relationships were formulated based on the resulting combinations. These rules were used to select typical areas of occurrence of each soil class and to train a decision tree model to predict the occurrence of individualized soil classes. Validation of the soil map predictions was conducted by comparison with available soil profiles. The soil map produced showed high agreement (80.5 % accuracy) with the soil classes observed in the soil profiles; Ultisols and Lithic Udorthents were predicted with greater accuracy. The soil variables selected in this study were suitable to represent the soil-landscape relationships, suggesting potential use in future studies. This approach developed a more detailed soil map relevant to current demands for soil information and has potential to be replicated in other areas in which data availability is similar. |
publishDate |
2018 |
dc.date.none.fl_str_mv |
2018-01-01 |
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=S0100-06832018000100303 |
url |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0100-06832018000100303 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.1590/18069657rbcs20170193 |
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 |
Sociedade Brasileira de Ciência do Solo |
publisher.none.fl_str_mv |
Sociedade Brasileira de Ciência do Solo |
dc.source.none.fl_str_mv |
Revista Brasileira de Ciência do Solo v.42 2018 reponame:Revista Brasileira de Ciência do Solo (Online) instname:Sociedade Brasileira de Ciência do Solo (SBCS) instacron:SBCS |
instname_str |
Sociedade Brasileira de Ciência do Solo (SBCS) |
instacron_str |
SBCS |
institution |
SBCS |
reponame_str |
Revista Brasileira de Ciência do Solo (Online) |
collection |
Revista Brasileira de Ciência do Solo (Online) |
repository.name.fl_str_mv |
Revista Brasileira de Ciência do Solo (Online) - Sociedade Brasileira de Ciência do Solo (SBCS) |
repository.mail.fl_str_mv |
||sbcs@ufv.br |
_version_ |
1752126521730924544 |