|
|
Registro Completo |
Biblioteca(s): |
Embrapa Solos. |
Data corrente: |
20/08/2020 |
Data da última atualização: |
21/08/2020 |
Tipo da produção científica: |
Artigo em Periódico Indexado |
Autoria: |
CARVALHO JUNIOR, W. de; PEREIRA, N. R.; FERNANDES FILHO, E. I.; CALDERANO FILHO, B.; PINHEIRO, H. S. K.; CHAGAS, C. da S.; BHERING, S. B.; PEREIRA, V. R.; LAWALL, S. |
Afiliação: |
WALDIR DE CARVALHO JUNIOR, CNPS; NILSON RENDEIRO PEREIRA, CNPS; ELPIDIO INACIO FERNANDES FILHO, UFV; BRAZ CALDERANO FILHO, CNPS; HELENA SARAIVA KOENOW PINHEIRO, UFRRJ; CESAR DA SILVA CHAGAS, CNPS; SILVIO BARGE BHERING, CNPS; VINICIUS RENDEIRO PEREIRA, UFRRJ; SARA LAWALL, UFRRJ. |
Título: |
Sample design effects on soil unit prediction with machine: randomness, uncertainty, and majority map. |
Ano de publicação: |
2020 |
Fonte/Imprenta: |
Revista Brasileira de Ciência do Solo, v. 44, e0190120, 2020. |
DOI: |
https://doi.org/10.36783/18069657rbcs2019 |
Idioma: |
Inglês |
Conteúdo: |
Notwithstanding the importance of soil surveys, advances in digital soil mapping have mainly focused on mapping soil attributes or properties rather than developing digital maps of soil units or soil classes. The purpose of this research was to develop digital soil unit maps based on primary soil data collection in areas without previously collected soil information. The covariate variability, the random effect across the data subset and the map outputs were the focuses of this study. We used five datasets with four models (Random Forest - RF, Gradient Boosted Machine - GBM, C5.0, and multinomial log-linear model - MLR). The covariates were grouped into five datasets, where four were grouped by Region Of Interest per Class (ROIC) and one was not grouped by ROIC. To evaluate the random effect to split the dataset, we ran each model 50 times and observed the overall accuracy (OA) and kappa index, and uncertainty, majority and variety maps. The OA of Dataset01 to 04 was lower than to Dataset05 accuracy. However, map outputs of RF and GBM for Dataset01 and Dataset05 had the same majority prediction. It seems that RF and GBM produce consistent results in map outputs according to this methodology and pedologist expertise. To evaluate the uncertainty and the consistency of soil unit prediction, we used the majority maps process. Random Forest, similar to GBM, presented the best results. The increase in the number of covariates was not a guarantee of improvement in the OA or in the quality of the map output. Geographic position and distance raster did not improve the map output according to expert evaluation. Because the variance between the ROICs, when the training and validation datasets were split based on it, the subsets are quite different in relation to the covariates, and this is the reason for the worse results of this model, comparing with the Dataset05. On the other hand, when considering one complete dataset not based on ROICs, the variance of training and validation subsets is lower and produced more accurate parameters of quality. MenosNotwithstanding the importance of soil surveys, advances in digital soil mapping have mainly focused on mapping soil attributes or properties rather than developing digital maps of soil units or soil classes. The purpose of this research was to develop digital soil unit maps based on primary soil data collection in areas without previously collected soil information. The covariate variability, the random effect across the data subset and the map outputs were the focuses of this study. We used five datasets with four models (Random Forest - RF, Gradient Boosted Machine - GBM, C5.0, and multinomial log-linear model - MLR). The covariates were grouped into five datasets, where four were grouped by Region Of Interest per Class (ROIC) and one was not grouped by ROIC. To evaluate the random effect to split the dataset, we ran each model 50 times and observed the overall accuracy (OA) and kappa index, and uncertainty, majority and variety maps. The OA of Dataset01 to 04 was lower than to Dataset05 accuracy. However, map outputs of RF and GBM for Dataset01 and Dataset05 had the same majority prediction. It seems that RF and GBM produce consistent results in map outputs according to this methodology and pedologist expertise. To evaluate the uncertainty and the consistency of soil unit prediction, we used the majority maps process. Random Forest, similar to GBM, presented the best results. The increase in the number of covariates was not a guarantee of improvement in the OA or in the ... Mostrar Tudo |
Palavras-Chave: |
Hillslope areas; Mapeamento digital de solos; Random forest; Tree learners models. |
Thesagro: |
Mapa; Solo. |
Thesaurus Nal: |
Soil map. |
Categoria do assunto: |
P Recursos Naturais, Ciências Ambientais e da Terra |
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/item/215441/1/Sample-design-effects-on-soil-unit-prediction-with-machine-2020.pdf
|
Marc: |
LEADER 03027naa a2200313 a 4500 001 2124458 005 2020-08-21 008 2020 bl uuuu u00u1 u #d 024 7 $ahttps://doi.org/10.36783/18069657rbcs2019$2DOI 100 1 $aCARVALHO JUNIOR, W. de 245 $aSample design effects on soil unit prediction with machine$brandomness, uncertainty, and majority map.$h[electronic resource] 260 $c2020 520 $aNotwithstanding the importance of soil surveys, advances in digital soil mapping have mainly focused on mapping soil attributes or properties rather than developing digital maps of soil units or soil classes. The purpose of this research was to develop digital soil unit maps based on primary soil data collection in areas without previously collected soil information. The covariate variability, the random effect across the data subset and the map outputs were the focuses of this study. We used five datasets with four models (Random Forest - RF, Gradient Boosted Machine - GBM, C5.0, and multinomial log-linear model - MLR). The covariates were grouped into five datasets, where four were grouped by Region Of Interest per Class (ROIC) and one was not grouped by ROIC. To evaluate the random effect to split the dataset, we ran each model 50 times and observed the overall accuracy (OA) and kappa index, and uncertainty, majority and variety maps. The OA of Dataset01 to 04 was lower than to Dataset05 accuracy. However, map outputs of RF and GBM for Dataset01 and Dataset05 had the same majority prediction. It seems that RF and GBM produce consistent results in map outputs according to this methodology and pedologist expertise. To evaluate the uncertainty and the consistency of soil unit prediction, we used the majority maps process. Random Forest, similar to GBM, presented the best results. The increase in the number of covariates was not a guarantee of improvement in the OA or in the quality of the map output. Geographic position and distance raster did not improve the map output according to expert evaluation. Because the variance between the ROICs, when the training and validation datasets were split based on it, the subsets are quite different in relation to the covariates, and this is the reason for the worse results of this model, comparing with the Dataset05. On the other hand, when considering one complete dataset not based on ROICs, the variance of training and validation subsets is lower and produced more accurate parameters of quality. 650 $aSoil map 650 $aMapa 650 $aSolo 653 $aHillslope areas 653 $aMapeamento digital de solos 653 $aRandom forest 653 $aTree learners models 700 1 $aPEREIRA, N. R. 700 1 $aFERNANDES FILHO, E. I. 700 1 $aCALDERANO FILHO, B. 700 1 $aPINHEIRO, H. S. K. 700 1 $aCHAGAS, C. da S. 700 1 $aBHERING, S. B. 700 1 $aPEREIRA, V. R. 700 1 $aLAWALL, S. 773 $tRevista Brasileira de Ciência do Solo$gv. 44, e0190120, 2020.
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 Agroindústria de Alimentos; Embrapa Algodão. |
Data corrente: |
05/01/2001 |
Data da última atualização: |
24/05/2012 |
Autoria: |
ARRIEL, N. H. C.; VIEIRA, D. J.; ANDRADE, F. P. de; BOUTY, F. de A. C.; COUTINHO, J. L. B.; AMIM, S. M. F.; ANTONIASSI, R.; FIRMINO, P. de T.; GUEDES, A. R.; ALENCAR, A. R. de; BIDO, L. |
Título: |
Melhoramento genetico do gergelim para o nordeste. |
Ano de publicação: |
1999 |
Fonte/Imprenta: |
Campina Grande: EMBRAPA-CNPA, 1999. |
Páginas: |
10p. |
Série: |
(EMBRAPA. CNPA. Comunicado Tecnico, 106) |
Idioma: |
Português |
Conteúdo: |
Através dos trabalhos de difusão e transferência das tecnologias geradas e adaptadas pela Embrapa Algodão, como o uso de cultivar e espaçamento recomendado pela pesquisa, os produtores têm obtido melhores rendimentos, passando de 300 a 500/ha para 600 a 800 kg/ha, havendo casos em que chegou-se a produzir em condições de sequeiro 1200 kg/ha, de acordo com informacões da Área de Transferência de Tecnologia do Centro. Descrição das cultivares de gergelim desenvolvidas pela Embrapa Algodão. |
Palavras-Chave: |
Adaptabilidade; Adaptability; Brasil; Genetic breeding; Genetic variability; Melhoramento genetico; Nordeste; Northeast; Sesame; Variabilidade genetica. |
Thesagro: |
Gergelim; Melhoramento Genético Vegetal; Sesamum Indicum; Variedade. |
Thesaurus NAL: |
Brazil; breeding; varieties. |
Categoria do assunto: |
-- |
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/item/59993/1/COMTEC106.pdf
|
Marc: |
LEADER 01700nam a2200457 a 4500 001 1271614 005 2012-05-24 008 1999 bl uuuu u0uu1 u #d 100 1 $aARRIEL, N. H. C. 245 $aMelhoramento genetico do gergelim para o nordeste. 260 $aCampina Grande: EMBRAPA-CNPA$c1999 300 $a10p. 490 $a(EMBRAPA. CNPA. Comunicado Tecnico, 106) 520 $aAtravés dos trabalhos de difusão e transferência das tecnologias geradas e adaptadas pela Embrapa Algodão, como o uso de cultivar e espaçamento recomendado pela pesquisa, os produtores têm obtido melhores rendimentos, passando de 300 a 500/ha para 600 a 800 kg/ha, havendo casos em que chegou-se a produzir em condições de sequeiro 1200 kg/ha, de acordo com informacões da Área de Transferência de Tecnologia do Centro. Descrição das cultivares de gergelim desenvolvidas pela Embrapa Algodão. 650 $aBrazil 650 $abreeding 650 $avarieties 650 $aGergelim 650 $aMelhoramento Genético Vegetal 650 $aSesamum Indicum 650 $aVariedade 653 $aAdaptabilidade 653 $aAdaptability 653 $aBrasil 653 $aGenetic breeding 653 $aGenetic variability 653 $aMelhoramento genetico 653 $aNordeste 653 $aNortheast 653 $aSesame 653 $aVariabilidade genetica 700 1 $aVIEIRA, D. J. 700 1 $aANDRADE, F. P. de 700 1 $aBOUTY, F. de A. C. 700 1 $aCOUTINHO, J. L. B. 700 1 $aAMIM, S. M. F. 700 1 $aANTONIASSI, R. 700 1 $aFIRMINO, P. de T. 700 1 $aGUEDES, A. R. 700 1 $aALENCAR, A. R. de 700 1 $aBIDO, L.
Download
Esconder MarcMostrar Marc Completo |
Registro original: |
Embrapa Algodão (CNPA) |
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
Fechar
|
Expressão de busca inválida. Verifique!!! |
|
|