• en
  • pt-br

Multivariate Analysis and Machine Learning in Properties of Ultisols (Argissolos) of Brazilian Amazon

Cristiano Marcelo Pereira de Souza, André Thomazini, Carlos Ernesto Gonçalves Reynaud Schaefer, Gustavo Vieira Veloso, Guilherme Musse Moreira, Elpídio Inácio Fernandes Filho

26/Nov/2018

ABSTRACT: Ultisols are the most common soil order in the Brazilian Amazon. The Legal Amazon (LA) has an area of 5 × 106 km2, with few accessible areas, which restricts studies of soils at a detailed level. The pedological properties can be estimated more efficiently using statistical procedures and machine learning techniques, tools which are capable of recognizing patterns in a large soil database. We analyzed the main chemical and physical properties of the B horizons of the Ultisols of […]

Selection of Environmental Covariates for Classifier Training Applied in Digital Soil Mapping

Alcinei Ribeiro Campos, Elvio Giasson, José Janderson Ferreira Costa, Israel Rosa Machado, Elisângela Benedet da Silva, Benito Roberto Bonfatti

26/Nov/2018

ABSTRACT A large number of predictor variables can be used in digital soil mapping; however, the presence of irrelevant covariables may compromise the prediction of soil types. Thus, algorithms can be applied to select the most relevant predictors. This study aimed to compare three covariable selection systems (two filter algorithms and one wrapper algorithm) and assess their impacts on the predictive model. The study area was the Lajeado River Watershed in the state of Rio Grande do Sul, Brazil. We […]

Modeling in the Adjustment of Fertilization Recommendation through Leaf Analysis in Fertigated ‘Prata’ Banana

José Aridiano Lima de Deus, Júlio César Lima Neves, Ismail Soares, Víctor Hugo Alvarez V., Fabricio Martinazzo Regis de Albuquerque, Lauana Lopes dos Santos, [...]

26/Nov/2018

ABSTRACT: In banana cultivation, fertilization recommendations are almost exclusively based on soil chemical analysis, without considering leaf analysis and expected yield, which can help in the adjustment of fertilization programs. The aim of this study was to develop a method to recommend macronutrient fertilization rates which integrates data on leaf analysis, soil chemical analysis, and yield. Yield, soil chemical analysis, and leaf analysis data of fertigated plantations of ‘Prata’ banana were obtained for the first and second halves of the […]

Digital Soil Mapping of Soil Properties in the “Mar de Morros” Environment Using Spectral Data

Patrícia Morais da Matta Campbell, Elpídio Inácio Fernandes Filho, Márcio Rocha Francelino, José Alexandre Melo Demattê, Marcos Gervasio Pereira, Clécia Cristina Barbosa Guimarães and, [...]

08/Nov/2018

ABSTRACT Quantification of soil properties is essential for better understanding of the environment and better soil management. The conventional techniques of laboratory analysis are sometimes costly and detrimental to the environment. Thus, development of new techniques for soil analysis that do not generate residues, such as spectroscopy, is increasingly necessary as a viable way to estimate a wide range of soil properties. The objective of this study was to predict the levels of organic carbon (OC), clay, and extractable phosphorus […]

Soil Water Retention Curve as Affected by Sample Height

Maria Laiane do Nascimento Silva, Paulo Leonel Libardi, Fernando Henrique Setti Gimenes

02/Nov/2018

ABSTRACT: The soil water retention curve is one of the main instruments to assess the soil physical quality and to improve soil management. Traditionally, the equipment most used in the laboratory to determine the retention curve has been Haines funnels and Richards chambers. An important factor to which little attention has been given in the use of these equipaments is the height of the undisturbed soil sample. This work proposes to evaluate the influence of different heights of undisturbed samples […]

Determining the In Situ Apparent Thermal Diffusivity of a Sandy Soil

Oscar Fernando Silva Aguilar, Jorge Alberto Andaverde Arredondo, Beatris Adriana Escobedo Trujillo, Artemio Jesús Benitez Fundora

02/Nov/2018

ABSTRACT: The thermal wave amplitude method is used to determine soil thermal diffusivity in situ for a sandy soil in Mexico (Coatzacoalcos, Veracruz). Soil diurnal temperature fluctuations were measured from depths of 0.05 to 0.65 m, in 0.01 m increments, during the months of April and August. Five mean diffusivity values were obtained experimentally, corresponding to the different depths combination. The soil thermal diffusivity ranged between 2.26 × 10−7 and 8.71 × 10−7 m2 s−1. The diffusivity values obtained are […]

Digital Soil Mapping Using Machine Learning Algorithms in a Tropical Mountainous Area

Martin Meier, Eliana de Souza, Marcio Rocha Francelino, Elpídio Inácio Fernandes Filho, Carlos Ernesto Gonçalves Reynaud Schaefer

02/Nov/2018

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 […]

Paleoenvironmental Characterization of a High-Mountain Environment in the Atlantic Forest in Southeastern Brazil

Eduardo Carvalho da Silva Neto, Jaqueline Jesus Santana dos Santos, Marcos Gervasio Pereira, Deyvid Diego Carvalho Maranhão, Fabiana da Costa Barros, Lúcia Helena Cunha dos Anjos

02/Nov/2018

ABSTRACT: Records of changes in the phytosociological structure of vegetation can be observed more clearly in soils that have more significant accumulation of organic matter, like those occurring in high-mountain environments. The aim of this study was to characterize soils formed in high-mountain environments in the Itatiaia National Park (INP), state of Rio de Janeiro, southeastern Brazil, and to discuss the potential of preserved phytoliths as markers of vegetative history and environmental factors. Four profiles were selected, which were morphologically […]

Potassium Dynamics in Ruzigrass Rhizosphere

Marcelo Raphael Volf, Tiara Moraes Guimarães, Daniele Scudeletti, Igor Vilela Cruz, Ciro Antonio Rosolem

02/Nov/2018

ABSTRACT: Ruzigrass (Urochola ruziziensis) has a large capacity to take up K from the soil, including non-exchangeable forms, and can play an important role in nutrient cycling in integrated production systems. However, K transport to roots of brachiarias is not well known, nor the nutrient dynamics in the rhizosphere, where a concentration gradient may be established towards the non-rhizospheric soil, creating a favorable environment for the release of non-exchangeable K. This study aimed to evaluate the effect of ruzigrass on […]

1 2 3 43