|
|
|
|
|
| Meier,Martin; Souza,Eliana de; Francelino,Marcio Rocha; Fernandes Filho,Elpídio Inácio; Schaefer,Carlos Ernesto Gonçalves Reynaud. |
| ABSTRACT: Increasingly, applications of machine learning techniques for digital soil mapping (DSM) are being used for different soil mapping purposes. Considering the variety of models available, it is important to know their performance in relation to soil data and environmental variables involved in soil mapping. This paper investigated the performance of eight machine learning algorithms for soil mapping in a tropical mountainous area of an official rural settlement in the Zona da Mata region in Brazil. Morphometric maps generated from a digital elevation model, together with Landsat-8 satellite imagery, and climatic maps, were among the set of covariates to be selected by the Recursive Feature Elimination algorithm to predict soil types using machine... |
| Tipo: Info:eu-repo/semantics/article |
Palavras-chave: Soil classification; Machine learning; Pedometrics; Land use planning; Agrarian reform. |
| Ano: 2018 |
URL: http://www.scielo.br/scielo.php?script=sci_arttext&pid=S0100-06832018000100313 |
| |
|
|
| Cunha,Alexson de Mello; Lani,João Luiz; Santos,Gerson Rodrigues dos; Fernandes Filho,Elpídio Inácio; Trindade,Filipe Silveira; Souza,Eliana de. |
| O objetivo deste trabalho foi avaliar a cokrigagem ordinária, com dados de altitude e distância do mar, em comparação à krigagem ordinária, na espacialização da precipitação pluvial dos períodos anual, seco e úmido, no Estado do Espírito Santo. Os dados de altitude e distância do mar foram obtidos de pontos de amostragem em grades regulares e irregulares. Foram utilizados dados de 108 postos pluviométricos. A avaliação dos métodos e das variáveis foi realizada com base na validação cruzada, tendo-se considerado os erros dos valores preditos e o ajuste dos modelos de regressão linear para valores observados e preditos. A grade regular para amostragem das covariáveis apresentou melhor acurácia de predição em comparação à grade irregular. A cokrigagem... |
| Tipo: Info:eu-repo/semantics/article |
Palavras-chave: Distribuição da precipitação; Geoestatística; Linha de costa; Predição espacial. |
| Ano: 2013 |
URL: http://www.scielo.br/scielo.php?script=sci_arttext&pid=S0100-204X2013000900001 |
| |
|
|
| Jeune,Wesly; Francelino,Márcio Rocha; Souza,Eliana de; Fernandes Filho,Elpídio Inácio; Rocha,Genelício Crusoé. |
| ABSTRACT Digital soil mapping (DSM) has been increasingly used to provide quick and accurate spatial information to support decision-makers in agricultural and environmental planning programs. In this study, we used a DSM approach to map soils in western Haiti and compare the performance of the Multinomial Logistic Regression (MLR) with Random Forest (RF) to classify the soils. The study area of 4,300 km2 is mostly composed of diverse limestone rocks, alluvial deposits, and, to a lesser extent, basalt. A soil survey was conducted whereby soils were described and classified at 258 sites. Soil samples were collected and subjected to physical and chemical analyses. Recursive Feature Elimination (RFE) was used to select the most important covariates from... |
| Tipo: Info:eu-repo/semantics/article |
Palavras-chave: Auxiliary data; Digital soil mapping; Soil survey; Data-mining. |
| Ano: 2018 |
URL: http://www.scielo.br/scielo.php?script=sci_arttext&pid=S0100-06832018000100306 |
| |
|
|
| Souza,Eliana de; Fernandes Filho,Elpídio Inácio; Schaefer,Carlos Ernesto Gonçalves Reynaud; Batjes,Niels H.; Santos,Gerson Rodrigues dos; Pontes,Lucas Machado. |
| ABSTRACT Soil bulk density (ρb) data are needed for a wide range of environmental studies. However, ρb is rarely reported in soil surveys. An alternative to obtain ρb for data-scarce regions, such as the Rio Doce basin in southeastern Brazil, is indirect estimation from less costly covariates using pedotransfer functions (PTF). This study primarily aims to develop region-specific PTFs for ρb using multiple linear regressions (MLR) and random forests (RF). Secondly, it assessed the accuracy of PTFs for data grouped into soil horizons and soil classes. For that purpose, we compared the performance of PTFs compiled from the literature with those developed here. Two groups of data were evaluated as covariates: 1) readily available soil properties and 2) maps... |
| Tipo: Info:eu-repo/semantics/article |
Palavras-chave: Multiple linear regressions; Random forests; Soil predictors; Spatial prediction. |
| Ano: 2016 |
URL: http://www.scielo.br/scielo.php?script=sci_arttext&pid=S0103-90162016000600525 |
| |
|
|
| Souza,Eliana de; Pontes,Lucas Machado; Fernandes Filho,Elpídio Inácio; Schaefer,Carlos Ernesto Goncalves Reynaud; Santos,Eliana Elizabet dos. |
| ABSTRACT: Little is known about the groundwater recharge potential of weathered tropical catchments, where increasing water uptake is widespread to meet various water demands. This study aimed to estimate the volume of groundwater recharge of the Doce River Basin, Minas Gerais, Brazil. The BALSEQ model was applied to calculate the water balance over a period of two years (2007-2009). Evapotranspiration, runoff, and potential groundwater recharge (PGR) were calculated, using daily data on rainfall, potential evapotranspiration, and plant-available water. A soil survey was undertaken for all major soils occurring in the basin. Soils samples were used to determine hydraulic conductivity, bulk density, and water content at field capacity and at the permanent... |
| Tipo: Info:eu-repo/semantics/article |
Palavras-chave: Aquifer; Infiltration; Potential recharge; Random Forests Model; Water balance. |
| Ano: 2019 |
URL: http://www.scielo.br/scielo.php?script=sci_arttext&pid=S0100-06832019000100501 |
| |
|
|
|
