Sample design effects on soil unit prediction with machine: randomness, uncertainty, and majority map (Registro n. 330489)
[ somente texto ]
| 000 -LÍDER | |
|---|---|
| fixed length control field | 03399nab a2200325 i 4500 |
| 003 - CÓDIGO MARC DA AGÊNCIA CATALOGADORA | |
| Campo de controle | BR-BrBNA |
| 005 - DATA E HORA DA ÚLTIMA ATUALIZAÇÃO | |
| Campo de controle | 20250318142533.0 |
| 008 - CAMPO DE TAMANHO FIXO | |
| fixed length control field | 250318b2020 bl.ar|pooa||| 00| 0 eng | |
| 040 ## - FONTE DA CATALOGAÇÃO | |
| Agência catalogadora | BR-BrBNA |
| Idioma da catalogação | eng |
| 072 ## - CATEGORIA AGRIS | |
| Código AGRIS | P31 |
| 100 ## - ENTRADA PRINCIPAL - NOME PESSOAL | |
| Nome pessoal | Carvalho Junior, Waldir de |
| 100 ## - ENTRADA PRINCIPAL - NOME PESSOAL | |
| Nome pessoal | Pereira, Nilson Rendeiro |
| 100 ## - ENTRADA PRINCIPAL - NOME PESSOAL | |
| Nome pessoal | Fernandes Filho, Elpidio Inacio |
| 100 ## - ENTRADA PRINCIPAL - NOME PESSOAL | |
| Nome pessoal | Calderano Filho, Braz |
| 100 ## - ENTRADA PRINCIPAL - NOME PESSOAL | |
| Nome pessoal | Pinheiro, Helena Saraiva Koenow |
| 100 ## - ENTRADA PRINCIPAL - NOME PESSOAL | |
| Nome pessoal | Chagas, Cesar da Silva |
| 100 ## - ENTRADA PRINCIPAL - NOME PESSOAL | |
| Nome pessoal | Bhering, Silvio Barge |
| 100 ## - ENTRADA PRINCIPAL - NOME PESSOAL | |
| Nome pessoal | Pereira, Vinicius Rendeiro |
| 100 ## - ENTRADA PRINCIPAL - NOME PESSOAL | |
| Nome pessoal | Lawall, Sara |
| 245 ## - TÍTULO PRINCIPAL | |
| Título principal | Sample design effects on soil unit prediction with machine: randomness, uncertainty, and majority map |
| 500 ## - NOTA GERAL | |
| Nota geral | Publicação on-line; 37 ref.; 8 illus; 4 tables; Sumaries (En) |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Koha item type | Analítica |
| 520 ## - NOTA DE RESUMO | |
| Nota de conteúdo | <br/><br/>ABSTRACT: 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.<br/><br/>Keywords: tree learners models, hillslope areas, random forest. |
| 650 ## - ASSUNTO - THESAGRO | |
| Cabeçalho tópico ou nome geográfico | RECONHECIMENTO DO SOLO |
| 650 ## - ASSUNTO - THESAGRO | |
| Cabeçalho tópico ou nome geográfico | ANÁLISE DO SOLO |
| 650 ## - ASSUNTO - THESAGRO | |
| Cabeçalho tópico ou nome geográfico | MAPA DIGITAL |
| 773 0# - ENTRADA ANALÍTICA | |
| Host Biblionumber | 808 |
| Registro do item | 345421 |
| Imprenta | Viçosa-MG Sociedade Brasileira de Ciência do Solo 1977 |
| Outro identificador | 2024-5955 |
| Título | Revista Brasileira de Ciência do Solo (Brazil) |
| ISSN | 0100-0683 |
| Colação | v. 44 p. 1-21; (2020) |
| Número de controle de registro | BR2024004904 |
| 856 ## - ACESSO E ENDEREÇO ELETRÔNICO | |
| Identificador uniforme de recurso - URI | https://www.scielo.br/j/rbcs/a/TcxtYSFhcdNrrcLkBQJgwYL/?format=pdf&lang=en |
Nenhum exemplar disponível.
BINAGRI