|
|
![](/consulta/web/img/deny.png) | Acesso ao texto completo restrito à biblioteca da Embrapa Solos. Para informações adicionais entre em contato com cnps.biblioteca@embrapa.br. |
Registro Completo |
Biblioteca(s): |
Embrapa Solos. |
Data corrente: |
01/12/2017 |
Data da última atualização: |
10/11/2021 |
Tipo da produção científica: |
Artigo em Periódico Indexado |
Autoria: |
PINHEIRO, H. S. K.; OWENS, P. R.; ANJOS, L. H. C.; CARVALHO JUNIOR, W. de; CHAGAS, C. da S. |
Afiliação: |
H. S. K. PINHEIRO, UFRRJ; P. R. OWENS, USDA Dale Bumpers Small Farms Research Center; L. H. C. ANJOS, UFRRJ; WALDIR DE CARVALHO JUNIOR, CNPS; CESAR DA SILVA CHAGAS, CNPS. |
Título: |
Tree-based techniques to predict soil units. |
Ano de publicação: |
2017 |
Fonte/Imprenta: |
Soil Research, v. 55, n. 8, p. 788-798, 2017. |
DOI: |
https://doi.org/10.1071/SR16060 |
Idioma: |
Inglês |
Conteúdo: |
Quantitative soil-landscape models offer a method for conducting soil surveys that use statistical tools to predict natural patterns in the occurrence of particular map units across a landscape. The aim of the present study was to predict soil units in a watershed with wide variation in landscape conditions. The approach relied on a modelling of soil-forming factors in order to understand the variability of the landscape components in the region. Models were generated for landscape attributes related to pedogenesis, specifically elevation, slope, curvature, compound topographic index, Euclidean distance from stream networks, landforms map, clay minerals index, iron oxide index and normalised difference vegetation index, along with an existing geology map. The soil classification was adapted from the World Reference Base System for Soil Resources, and the predominant soil taxonomic orders observed were Ferrasols, Acrisols, Gleysols, Cambisols, Fluvisols and Regosols. The algorithms used to predict the soil units were based on decision tree (DT) and random forest (RF) methods. The criteria used to evaluate the models' performance were statistical indices, coherence between predicted units and the legacy map, as well as accuracy checks based on control samples. The best performing model was found to be the RF algorithm, with resulting statistical indices considered excellent (overall = 0.966, kappa = 0.962). The accuracy of the map as determined by control points was 67.89%, with a kappa value of 61.39%. MenosQuantitative soil-landscape models offer a method for conducting soil surveys that use statistical tools to predict natural patterns in the occurrence of particular map units across a landscape. The aim of the present study was to predict soil units in a watershed with wide variation in landscape conditions. The approach relied on a modelling of soil-forming factors in order to understand the variability of the landscape components in the region. Models were generated for landscape attributes related to pedogenesis, specifically elevation, slope, curvature, compound topographic index, Euclidean distance from stream networks, landforms map, clay minerals index, iron oxide index and normalised difference vegetation index, along with an existing geology map. The soil classification was adapted from the World Reference Base System for Soil Resources, and the predominant soil taxonomic orders observed were Ferrasols, Acrisols, Gleysols, Cambisols, Fluvisols and Regosols. The algorithms used to predict the soil units were based on decision tree (DT) and random forest (RF) methods. The criteria used to evaluate the models' performance were statistical indices, coherence between predicted units and the legacy map, as well as accuracy checks based on control samples. The best performing model was found to be the RF algorithm, with resulting statistical indices considered excellent (overall = 0.966, kappa = 0.962). The accuracy of the map as determined by control points was 67.89%, wi... Mostrar Tudo |
Palavras-Chave: |
Mapeamento digital do solo. |
Thesagro: |
Classificação do Solo; Pedologia. |
Categoria do assunto: |
P Recursos Naturais, Ciências Ambientais e da Terra |
Marc: |
LEADER 02162naa a2200217 a 4500 001 2081200 005 2021-11-10 008 2017 bl uuuu u00u1 u #d 024 7 $ahttps://doi.org/10.1071/SR16060$2DOI 100 1 $aPINHEIRO, H. S. K. 245 $aTree-based techniques to predict soil units.$h[electronic resource] 260 $c2017 520 $aQuantitative soil-landscape models offer a method for conducting soil surveys that use statistical tools to predict natural patterns in the occurrence of particular map units across a landscape. The aim of the present study was to predict soil units in a watershed with wide variation in landscape conditions. The approach relied on a modelling of soil-forming factors in order to understand the variability of the landscape components in the region. Models were generated for landscape attributes related to pedogenesis, specifically elevation, slope, curvature, compound topographic index, Euclidean distance from stream networks, landforms map, clay minerals index, iron oxide index and normalised difference vegetation index, along with an existing geology map. The soil classification was adapted from the World Reference Base System for Soil Resources, and the predominant soil taxonomic orders observed were Ferrasols, Acrisols, Gleysols, Cambisols, Fluvisols and Regosols. The algorithms used to predict the soil units were based on decision tree (DT) and random forest (RF) methods. The criteria used to evaluate the models' performance were statistical indices, coherence between predicted units and the legacy map, as well as accuracy checks based on control samples. The best performing model was found to be the RF algorithm, with resulting statistical indices considered excellent (overall = 0.966, kappa = 0.962). The accuracy of the map as determined by control points was 67.89%, with a kappa value of 61.39%. 650 $aClassificação do Solo 650 $aPedologia 653 $aMapeamento digital do solo 700 1 $aOWENS, P. R. 700 1 $aANJOS, L. H. C. 700 1 $aCARVALHO JUNIOR, W. de 700 1 $aCHAGAS, C. da S. 773 $tSoil Research$gv. 55, n. 8, p. 788-798, 2017.
Download
Esconder MarcMostrar Marc Completo |
Registro original: |
Embrapa Solos (CNPS) |
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
URL |
Voltar
|
|
Registro Completo
Biblioteca(s): |
Embrapa Arroz e Feijão. |
Data corrente: |
12/03/2009 |
Data da última atualização: |
12/03/2009 |
Tipo da produção científica: |
Resumo em Anais de Congresso |
Autoria: |
MADARI, B. E.; NOVOTNY, E. H.; MANGRICH, A. S.; MACHADO, P. L. O. de A.; CARVALHO, M. T. de M. |
Afiliação: |
Beáta Emöke Madari, CNPAF; Etelvino Henrique Novotny, CNPS; Antônio Sálvio Mangrich, Universidade Federal do Paraná; Pedro Luiz Oliveira de Almeida Machado, CNPAF; Márcia Thaís de Melo Carvalho, CNPAF. |
Título: |
Desenvolvimento de novas tecnologias para o seqüestro de carbono e consequente aumento da fertilidade dos solos tropicais. |
Ano de publicação: |
2008 |
Fonte/Imprenta: |
In: SIMPÓSIO SOBRE INOVAÇÃO E CRIATIVIDADE CIENTÍFICA NA EMBRAPA, 1., 2008, Brasília, DF. Comunicações selecionadas: resumos. Brasília, DF: Embrapa, 2008. |
Idioma: |
Português |
Conteúdo: |
O objetivo é a obtenção de informação para o desenvolvimento de novas práticas de manejo da fertilidade do solo ou material que tenha desempenho similar, como condicionador de solo ou adubo ?inteligente?, à matéria orgânica das TPIs, que sejam sustentáveis e adequados aos novos cenários da agricultura brasileira. |
Thesagro: |
Carbono; Fertilidade do Solo; Matéria Orgânica; Solo Tropical. |
Categoria do assunto: |
-- |
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/CNPAF-2009-09/28005/1/116_sequestrocarbono_beatamadari_cnpaf_0822_1909.pdf
|
Marc: |
LEADER 01078nam a2200205 a 4500 001 1216291 005 2009-03-12 008 2008 bl uuuu u00u1 u #d 100 1 $aMADARI, B. E. 245 $aDesenvolvimento de novas tecnologias para o seqüestro de carbono e consequente aumento da fertilidade dos solos tropicais. 260 $aIn: SIMPÓSIO SOBRE INOVAÇÃO E CRIATIVIDADE CIENTÍFICA NA EMBRAPA, 1., 2008, Brasília, DF. Comunicações selecionadas: resumos. Brasília, DF: Embrapa$c2008 520 $aO objetivo é a obtenção de informação para o desenvolvimento de novas práticas de manejo da fertilidade do solo ou material que tenha desempenho similar, como condicionador de solo ou adubo ?inteligente?, à matéria orgânica das TPIs, que sejam sustentáveis e adequados aos novos cenários da agricultura brasileira. 650 $aCarbono 650 $aFertilidade do Solo 650 $aMatéria Orgânica 650 $aSolo Tropical 700 1 $aNOVOTNY, E. H. 700 1 $aMANGRICH, A. S. 700 1 $aMACHADO, P. L. O. de A. 700 1 $aCARVALHO, M. T. de M.
Download
Esconder MarcMostrar Marc Completo |
Registro original: |
Embrapa Arroz e Feijão (CNPAF) |
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
Fechar
|
Nenhum registro encontrado para a expressão de busca informada. |
|
|