|
|
Registros recuperados : 4 | |
1. | | PEREIRA, V. R.; VICTORIA, D. de C.; OLIVEIRA, A. F. de; CUADRA, S. V.; MONTEIRO, J. E. B. de A.; NAKAI, A. M.; MACIEL, R. J. S. Avaliação do impacto das mudanças climáticas no risco climático da soja a partir dos cenários do CMIP6. In: CONGRESSO BRASILEIRO DE AGROMETEOROLOGIA, 22., 2023, Natal. A agrometeorologia e a agropecuária: adaptação às mudanças climáticas: anais. Natal: Sociedade Brasileira de Agrometeorologia, 2023. p. 2535-2545. CBAGRO 2023. Biblioteca(s): Embrapa Agricultura Digital. |
| |
2. | | SILVA, M. T. da; SILVA, S. D. dos A. e; EICHOLZ, E. D.; MORSELLI, T. B. G. A.; OLIVEIRA, R. J. P. de; ANTUNES, W. R.; PEREIRA, V. R.; CAMPOS, A. D. S. de. Biossólido como adubação orgânica no crescimento inicial de mamona. In: CONGRESSO BRASILEIRO DE MAMONA, 6.; SIMPÓSIO INTERNACIONAL DE OLEAGINOSAS ENERGÉTICAS, 3., 2014, Fortaleza. Energia e segurança alimentar na agricultura familiar: anais. Campina Grande, PB: Embrapa Algodão, 2014. p. 49 Biblioteca(s): Embrapa Clima Temperado. |
| |
3. | | PEREIRA, N. R.; CARVALHO JUNIOR, W. de; FERNANDES FILHO, E. I.; CALDERANO FILHO, B.; BHERING, S. B.; CHAGAS, C. da S.; DART, R. de O.; AGLIO, M. L. D.; LAWALL, S.; PINHEIRO, H. S. K.; PEREIRA, V. R. Levantamento semidetalhado dos solos da microbacia do Córrego do Bonfim, município de Petrópolis, Região Serrana do estado do Rio de Janeiro. Rio de Janeiro: Embrapa Solos, 2021. E-book: il. color. (Embrapa Solos. Boletim de pesquisa e desenvolvimento, 273). Acompanha 1 mapa, color. Escala 1:10.000. Biblioteca(s): Embrapa Solos. |
| |
4. | | 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. Sample design effects on soil unit prediction with machine: randomness, uncertainty, and majority map. Revista Brasileira de Ciência do Solo, v. 44, e0190120, 2020. Biblioteca(s): Embrapa Solos. |
| |
Registros recuperados : 4 | |
|
|
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 |
Circulação/Nível: |
A - 2 |
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 |
Fechar
|
Nenhum registro encontrado para a expressão de busca informada. |
|
|