|
|
| 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: |
23/08/2016 |
Data da última atualização: |
12/08/2020 |
Tipo da produção científica: |
Artigo em Periódico Indexado |
Autoria: |
CHAGAS, C. da S.; CARVALHO JUNIOR, W. de; BHERING, S. B.; CALDERANO FILHO, B. |
Afiliação: |
CESAR DA SILVA CHAGAS, CNPS; WALDIR DE CARVALHO JUNIOR, CNPS; SILVIO BARGE BHERING, CNPS; BRAZ CALDERANO FILHO, CNPS. |
Título: |
Spatial prediction of soil surface texture in a semiarid region using random forest and multiple linear regressions. |
Ano de publicação: |
2016 |
Fonte/Imprenta: |
Catena, v. 139, p. 232-240, Apr. 2016. |
Idioma: |
Inglês |
Conteúdo: |
Soil texture is an essential and extremely variable physical property that strongly influences many other soil properties that are highly relevant for agricultural production, e.g., fertility and water retention capacity. In plain areas, terrain properties derived from a digital elevation model are not effective for digital soil mapping, and the variation in the properties of such areas remains a challenge. In this regard, remote sensing can facilitate the mapping of soil properties. The purpose of this study was to evaluate the efficiency of using of data obtained fromthe ThematicMapper (TM) sensor of Landsat 5 for digital soil mapping in a semi-arid region, based on multiple linear regression (MLR) and a random forest model (RFM). To this end, 399 samples of the soil surface layer (0?20 cm)were used to predict the sand, silt and clay contents, using the bands 1, 2, 3, 4, 5 and 7, the Normalized Difference Vegetation Index (NDVI), the grain size index (GSI), and the relationships between bands 3 and 2, bands 3 and 7, and bands 5 and 7 (clay index) of the Landsat 5 TM sensor as covariates. Among these covariates, only band 1 (b1), the relationship between bands 5 and 7 (b5/b7) for sand, silt and clay, and band 4 (b4) for silt were not significantly correlated according to Pearson's correlation analysis. The validation of the models showed that the properties were best estimated using the RFM, which explained 63% and 56% of the spatial variability of sand and clay, respectively, whereas the MLR explained 30% of the spatial variation of silt. An analysis of the relevance of the variables predicted by the RFMshowed that the covariates b3/b7, b5, NDVI and b2 explained most of the variability of the considered properties. The RFM proved to be more advantageous than the MLR with respect to insensitivity to overfitting and the presence of noise in the data. In addition, the RFMproduced more realistic distribution maps of the soil properties than did the MLR, taking into account that the estimated values of the soil attributes were in the same range as the calibration data, while theMLR model estimates were out of the range of the calibration data. MenosSoil texture is an essential and extremely variable physical property that strongly influences many other soil properties that are highly relevant for agricultural production, e.g., fertility and water retention capacity. In plain areas, terrain properties derived from a digital elevation model are not effective for digital soil mapping, and the variation in the properties of such areas remains a challenge. In this regard, remote sensing can facilitate the mapping of soil properties. The purpose of this study was to evaluate the efficiency of using of data obtained fromthe ThematicMapper (TM) sensor of Landsat 5 for digital soil mapping in a semi-arid region, based on multiple linear regression (MLR) and a random forest model (RFM). To this end, 399 samples of the soil surface layer (0?20 cm)were used to predict the sand, silt and clay contents, using the bands 1, 2, 3, 4, 5 and 7, the Normalized Difference Vegetation Index (NDVI), the grain size index (GSI), and the relationships between bands 3 and 2, bands 3 and 7, and bands 5 and 7 (clay index) of the Landsat 5 TM sensor as covariates. Among these covariates, only band 1 (b1), the relationship between bands 5 and 7 (b5/b7) for sand, silt and clay, and band 4 (b4) for silt were not significantly correlated according to Pearson's correlation analysis. The validation of the models showed that the properties were best estimated using the RFM, which explained 63% and 56% of the spatial variability of sand and clay, respective... Mostrar Tudo |
Palavras-Chave: |
Composição granulométrica; Conjunto de dados Landsat; Mapeamento digital de solos; Pedometria; Tamanho do grão. |
Categoria do assunto: |
P Recursos Naturais, Ciências Ambientais e da Terra |
Marc: |
LEADER 02879naa a2200217 a 4500 001 2051511 005 2020-08-12 008 2016 bl uuuu u00u1 u #d 100 1 $aCHAGAS, C. da S. 245 $aSpatial prediction of soil surface texture in a semiarid region using random forest and multiple linear regressions.$h[electronic resource] 260 $c2016 520 $aSoil texture is an essential and extremely variable physical property that strongly influences many other soil properties that are highly relevant for agricultural production, e.g., fertility and water retention capacity. In plain areas, terrain properties derived from a digital elevation model are not effective for digital soil mapping, and the variation in the properties of such areas remains a challenge. In this regard, remote sensing can facilitate the mapping of soil properties. The purpose of this study was to evaluate the efficiency of using of data obtained fromthe ThematicMapper (TM) sensor of Landsat 5 for digital soil mapping in a semi-arid region, based on multiple linear regression (MLR) and a random forest model (RFM). To this end, 399 samples of the soil surface layer (0?20 cm)were used to predict the sand, silt and clay contents, using the bands 1, 2, 3, 4, 5 and 7, the Normalized Difference Vegetation Index (NDVI), the grain size index (GSI), and the relationships between bands 3 and 2, bands 3 and 7, and bands 5 and 7 (clay index) of the Landsat 5 TM sensor as covariates. Among these covariates, only band 1 (b1), the relationship between bands 5 and 7 (b5/b7) for sand, silt and clay, and band 4 (b4) for silt were not significantly correlated according to Pearson's correlation analysis. The validation of the models showed that the properties were best estimated using the RFM, which explained 63% and 56% of the spatial variability of sand and clay, respectively, whereas the MLR explained 30% of the spatial variation of silt. An analysis of the relevance of the variables predicted by the RFMshowed that the covariates b3/b7, b5, NDVI and b2 explained most of the variability of the considered properties. The RFM proved to be more advantageous than the MLR with respect to insensitivity to overfitting and the presence of noise in the data. In addition, the RFMproduced more realistic distribution maps of the soil properties than did the MLR, taking into account that the estimated values of the soil attributes were in the same range as the calibration data, while theMLR model estimates were out of the range of the calibration data. 653 $aComposição granulométrica 653 $aConjunto de dados Landsat 653 $aMapeamento digital de solos 653 $aPedometria 653 $aTamanho do grão 700 1 $aCARVALHO JUNIOR, W. de 700 1 $aBHERING, S. B. 700 1 $aCALDERANO FILHO, B. 773 $tCatena$gv. 139, p. 232-240, Apr. 2016.
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 Meio-Norte. |
Data corrente: |
09/08/2023 |
Data da última atualização: |
30/08/2023 |
Tipo da produção científica: |
Resumo em Anais de Congresso |
Autoria: |
SOARES, L. das D. do N.; CARVALHO, I. E. de; CARVALHO, S. P.; ARAUJO NETO, R. B. de; AZEVEDO, D. M. M. R.; CARVALHO, G. M. C. |
Afiliação: |
LARISSE DAS DORES DO NASCIMENTO SOARES, UNIVERSIDADE FEDERAL DO PIAUÍ; ISABELLA EMMILY DE CARVALHO, UNIVERSIDADE FEDERAL DO PIAUí; SUZANE PEREIRA CARVALHO, INSTITUTO FEDERAL DO PIAUÍ; RAIMUNDO BEZERRA DE ARAUJO NETO, CPAMN; DANIELLE MARIA MACHADO R AZEVEDO, CPAMN; GERALDO MAGELA CORTES CARVALHO, CPAMN. |
Título: |
Características do pelame em bovinos da raça Curraleiro Pé-Duro na região Meio-Norte do Brasil. |
Ano de publicação: |
2023 |
Fonte/Imprenta: |
In: JORNADA DE INICIAÇÃO CIENTÍFICA DA EMBRAPA MEIO-NORTE, 8., 2022, Teresina, PI. Anais... Teresina: Embrapa Meio-Norte, 2023. p. 24. (Embrapa Meio-Norte. Documentos, 291). |
Idioma: |
Português |
Conteúdo: |
No presente trabalho, foram estudadas as características do pelame de 219 animais adultos, entre machos, e fêmeas, da raça Curraleiro Pé-Duro (CPD), em cinco rebanhos na região de Campo Maior, PI. A coleta das amostras foi realizada em fevereiro de 2022. |
Palavras-Chave: |
Adaptabilidade; Bem-estar animal; Conforto térmico; Localmente adaptada. |
Categoria do assunto: |
X Pesquisa, Tecnologia e Engenharia |
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/doc/1155804/1/CaracteristicasPelameVIIIJornCientEmbrapaMeioNorteDoc291.2023-24.pdf
|
Marc: |
LEADER 01087nam a2200217 a 4500 001 2155804 005 2023-08-30 008 2023 bl uuuu u00u1 u #d 100 1 $aSOARES, L. das D. do N. 245 $aCaracterísticas do pelame em bovinos da raça Curraleiro Pé-Duro na região Meio-Norte do Brasil.$h[electronic resource] 260 $aIn: JORNADA DE INICIAÇÃO CIENTÍFICA DA EMBRAPA MEIO-NORTE, 8., 2022, Teresina, PI. Anais... Teresina: Embrapa Meio-Norte, 2023. p. 24. (Embrapa Meio-Norte. Documentos, 291).$c2023 520 $aNo presente trabalho, foram estudadas as características do pelame de 219 animais adultos, entre machos, e fêmeas, da raça Curraleiro Pé-Duro (CPD), em cinco rebanhos na região de Campo Maior, PI. A coleta das amostras foi realizada em fevereiro de 2022. 653 $aAdaptabilidade 653 $aBem-estar animal 653 $aConforto térmico 653 $aLocalmente adaptada 700 1 $aCARVALHO, I. E. de 700 1 $aCARVALHO, S. P. 700 1 $aARAUJO NETO, R. B. de 700 1 $aAZEVEDO, D. M. M. R. 700 1 $aCARVALHO, G. M. C.
Download
Esconder MarcMostrar Marc Completo |
Registro original: |
Embrapa Meio-Norte (CPAMN) |
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
Fechar
|
Nenhum registro encontrado para a expressão de busca informada. |
|
|