Mapping Soil Cation Exchange Capacity in a Semiarid Region through Predictive Models and Covariates from Remote Sensing Data

Detalhes bibliográficos
Autor(a) principal: Chagas,César da Silva
Data de Publicação: 2018
Outros Autores: Carvalho Júnior,Waldir de, Pinheiro,Helena Saraiva Koenow, Xavier,Pedro Armentano Mudado, Bhering,Silvio Barge, Pereira,Nilson Rendeiro, Calderano Filho,Braz
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=S0100-06832018000100311
Resumo: ABSTRACT: Planning sustainable use of land resources requires reliable information about spatial distribution of soil physical and chemical properties related to environmental processes and ecosystemic functions. In this context, cation exchange capacity (CEC) is a fundamental soil quality indicator; however, it takes money and time to obtain this data. Although many studies have been conducted to spatially quantify soil properties on various scales and in different environments, not much is known about interactions between soil properties and environmental covariates in the Brazilian semiarid region. The goal of this study was to evaluate the efficiency of random forest and cokriging models applied to predict CEC in the Brazilian semiarid region. The covariates used to predict CEC consist of images from Landsat 5 TM and a legacy soil map (scale 1:10,000). The sample set comprises 499 samples from the topsoil layer (0.00-0.20 m), where 375 samples were used in training processes and 124 as validation samples. The cokriging model (R2 = 0.57 and RMSE = 7.22 cmolc kg-1) performed better in predicting CEC than the random forest model (R2 = 0.47 and RMSE = 7.89 cmolc kg-1). The approach used showed potential for estimating CEC content in the Brazilian semiarid region by using covariates obtained from orbital remote sensing and the legacy soil map.
id SBCS-1_a7bbe623b76729f12b36612ec687c715
oai_identifier_str oai:scielo:S0100-06832018000100311
network_acronym_str SBCS-1
network_name_str Revista Brasileira de Ciência do Solo (Online)
repository_id_str
spelling Mapping Soil Cation Exchange Capacity in a Semiarid Region through Predictive Models and Covariates from Remote Sensing Datadata mininggeostatisticsLandsat 5legacy datasoil surveyABSTRACT: Planning sustainable use of land resources requires reliable information about spatial distribution of soil physical and chemical properties related to environmental processes and ecosystemic functions. In this context, cation exchange capacity (CEC) is a fundamental soil quality indicator; however, it takes money and time to obtain this data. Although many studies have been conducted to spatially quantify soil properties on various scales and in different environments, not much is known about interactions between soil properties and environmental covariates in the Brazilian semiarid region. The goal of this study was to evaluate the efficiency of random forest and cokriging models applied to predict CEC in the Brazilian semiarid region. The covariates used to predict CEC consist of images from Landsat 5 TM and a legacy soil map (scale 1:10,000). The sample set comprises 499 samples from the topsoil layer (0.00-0.20 m), where 375 samples were used in training processes and 124 as validation samples. The cokriging model (R2 = 0.57 and RMSE = 7.22 cmolc kg-1) performed better in predicting CEC than the random forest model (R2 = 0.47 and RMSE = 7.89 cmolc kg-1). The approach used showed potential for estimating CEC content in the Brazilian semiarid region by using covariates obtained from orbital remote sensing and the legacy soil map.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=S0100-06832018000100311Revista Brasileira de Ciência do Solo v.42 2018reponame:Revista Brasileira de Ciência do Solo (Online)instname:Sociedade Brasileira de Ciência do Solo (SBCS)instacron:SBCS10.1590/18069657rbcs20170183info:eu-repo/semantics/openAccessChagas,César da SilvaCarvalho Júnior,Waldir dePinheiro,Helena Saraiva KoenowXavier,Pedro Armentano MudadoBhering,Silvio BargePereira,Nilson RendeiroCalderano Filho,Brazeng2018-10-16T00:00:00Zoai:scielo:S0100-06832018000100311Revistahttp://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:2018-10-16T00:00Revista Brasileira de Ciência do Solo (Online) - Sociedade Brasileira de Ciência do Solo (SBCS)false
dc.title.none.fl_str_mv Mapping Soil Cation Exchange Capacity in a Semiarid Region through Predictive Models and Covariates from Remote Sensing Data
title Mapping Soil Cation Exchange Capacity in a Semiarid Region through Predictive Models and Covariates from Remote Sensing Data
spellingShingle Mapping Soil Cation Exchange Capacity in a Semiarid Region through Predictive Models and Covariates from Remote Sensing Data
Chagas,César da Silva
data mining
geostatistics
Landsat 5
legacy data
soil survey
title_short Mapping Soil Cation Exchange Capacity in a Semiarid Region through Predictive Models and Covariates from Remote Sensing Data
title_full Mapping Soil Cation Exchange Capacity in a Semiarid Region through Predictive Models and Covariates from Remote Sensing Data
title_fullStr Mapping Soil Cation Exchange Capacity in a Semiarid Region through Predictive Models and Covariates from Remote Sensing Data
title_full_unstemmed Mapping Soil Cation Exchange Capacity in a Semiarid Region through Predictive Models and Covariates from Remote Sensing Data
title_sort Mapping Soil Cation Exchange Capacity in a Semiarid Region through Predictive Models and Covariates from Remote Sensing Data
author Chagas,César da Silva
author_facet Chagas,César da Silva
Carvalho Júnior,Waldir de
Pinheiro,Helena Saraiva Koenow
Xavier,Pedro Armentano Mudado
Bhering,Silvio Barge
Pereira,Nilson Rendeiro
Calderano Filho,Braz
author_role author
author2 Carvalho Júnior,Waldir de
Pinheiro,Helena Saraiva Koenow
Xavier,Pedro Armentano Mudado
Bhering,Silvio Barge
Pereira,Nilson Rendeiro
Calderano Filho,Braz
author2_role author
author
author
author
author
author
dc.contributor.author.fl_str_mv Chagas,César da Silva
Carvalho Júnior,Waldir de
Pinheiro,Helena Saraiva Koenow
Xavier,Pedro Armentano Mudado
Bhering,Silvio Barge
Pereira,Nilson Rendeiro
Calderano Filho,Braz
dc.subject.por.fl_str_mv data mining
geostatistics
Landsat 5
legacy data
soil survey
topic data mining
geostatistics
Landsat 5
legacy data
soil survey
description ABSTRACT: Planning sustainable use of land resources requires reliable information about spatial distribution of soil physical and chemical properties related to environmental processes and ecosystemic functions. In this context, cation exchange capacity (CEC) is a fundamental soil quality indicator; however, it takes money and time to obtain this data. Although many studies have been conducted to spatially quantify soil properties on various scales and in different environments, not much is known about interactions between soil properties and environmental covariates in the Brazilian semiarid region. The goal of this study was to evaluate the efficiency of random forest and cokriging models applied to predict CEC in the Brazilian semiarid region. The covariates used to predict CEC consist of images from Landsat 5 TM and a legacy soil map (scale 1:10,000). The sample set comprises 499 samples from the topsoil layer (0.00-0.20 m), where 375 samples were used in training processes and 124 as validation samples. The cokriging model (R2 = 0.57 and RMSE = 7.22 cmolc kg-1) performed better in predicting CEC than the random forest model (R2 = 0.47 and RMSE = 7.89 cmolc kg-1). The approach used showed potential for estimating CEC content in the Brazilian semiarid region by using covariates obtained from orbital remote sensing and the legacy soil map.
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=S0100-06832018000100311
url http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0100-06832018000100311
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 10.1590/18069657rbcs20170183
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_ 1752126521746653184