Análise dos atributos do solo e da produtividade da cultura de cana-de-açúcar com o uso da geoestatística e árvore de decisão

Souza, Zigomar Menezes de; Cerri, Domingos Guilherme Pellegrino; Colet, Marcelo José; Rodrigues, Luiz Henrique Antunes; Magalhães, Paulo Sérgio Graziano; Mandoni, Rafael Junqueira Araújo

doi:10.1590/s0103-84782010005000048

Cited by 29 publications

(37 citation statements)

References 15 publications

(12 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In addition, the knowledge found in a decision tree is represented by rules and the algorithm achieves satisfactory results when compared with other more sophisticated approaches available in the literature (HAN et al, 2011). That is why decision tree induction is seen as a promising approach in data analysis (SOUZA et al, 2010).…”

Section: Introductionmentioning

confidence: 99%

Classification of the Initial Development of Eucaliptus Using Data Mining Techniques

Lima¹,

Souza²,

Montanari

et al. 2017

CERNE

Self Cite

View full text Add to dashboard Cite

ABSTRACT:Eucalyptus plantation has expanded considerably in Brazil, especially in regions where soils have low fertility, such as in Brazilian Cerrados. To achieve greater productivity, it is essential to know the needs of the soil and the right moment to correct it. Mathematical and computational models have been used as a promising alternative to help in this decisionmaking process. The aim of this study was to model the influence of climate and physicochemical attributes in the development of Eucalyptus urograndis in Entisol quartzipsamment soil using the decision tree induction technique. To do so, we used 30 attributes, 29 of them are predictive and one is the target-attribute or response variable regarding the height of the eucalyptus. We defined four approaches to select these features: no selection, Correlationbased Feature Selection (CFS), Chi-square test (χ 2 ) and Wrapper. To classify the data, we used the decision tree induction technique available in the Weka software 3.6. This data mining technique allowed us to create a classification model for the initial development of eucalyptus. From this model, one can predict new cases in different production classes, in which the individual wood volume (IWV) and the diameter at breast height (DBH) are crucial features to predict the growth of Eucalyptus urograndis, in addition to the presence of chemical soil components such as: magnesium (Mg +2 ), phosphorus (P), aluminum (Al +3 ), potassium (K + ), potential acidity (H + Al), hydrogen potential (pH), and physical attributes such as soil resistance to penetration and related to climate, such as minimum temperature. CLASSIFICAÇÃO DO DESENVOLVIMENTO INICIAL DO EUCALIPTO UTILIZANDO TÉCNICAS DE MINERAÇÃO DE DADOSRESUMO: O cultivo de eucalipto tem se expandido consideravelmente no Brasil, sobretudo em regiões em que os solos apresentam baixa fertilidade, como nos Cerrados brasileiros. Para alcançar maiores produtividades, é fundamental saber a necessidade e o momento adequado para correção do solo. Para auxiliar esse processo de tomada de decisão, modelos matemáticos e computacionais têm sido utilizados e são uma alternativa promissora. O objetivo deste trabalho foi modelar a influência dos atributos físico-químicos do solo e climáticos no desenvolvimento do Eucalyptus urograndis em Neossolo Quartzarênico, por meio da técnica de indução da árvore de decisão. Para isso foram utilizados 30 atributos, sendo 29 preditivos e um atributo-meta ou variável resposta, a saber, a altura do eucalipto. Foram avaliadas quatro abordagens para seleção de atributos: sem seleção, seleção de atributos baseado em correlação (CFS), método do Qui-quadrado (χ 2 ) e Wrapper. Para classificar os dados foi utilizada a técnica de indução de árvore de decisão por meio do software Weka 3.6. As técnicas de mineração de dados através da indução de árvore de decisão permitem o desenvolvimento de um modelo de classificação do desenvolvimento inicial de eucalipto eficiente para previsão de novos casos em diferentes classes de produção, onde o v...

show abstract

Section: Introductionmentioning

confidence: 99%

Classification of the Initial Development of Eucaliptus Using Data Mining Techniques

Lima¹,

Souza²,

Montanari

et al. 2017

CERNE

Self Cite

View full text Add to dashboard Cite

show abstract

“…According to Isaaks and Srivastava (1989), normality is not the determinant factor for the realization of the geostatistical analysis, being more important the existence of sills well defined in the semivariograms. Rachid Junior et al (2006), and Souza et al (2010), realize the geostatistical evaluation of the variables that did not present normality and obtained well defined sills. The coefficient of variation (CV) obtained for the physical variables of the soil samples was considered low (CV < 12%), as proposed by Warrick and Nielsen (1980), except for the silt and macroporosity, that presented moderate variation (12% < CV > 60%).…”

Section: Resultsmentioning

confidence: 99%

Spatial variability of soil physical and chemical aspects in a Brazil nut tree stand in the Brazilian Amazon

Guerreiro¹,

JÃonior²,

Santos³

et al. 2017

Afr. J. Agric. Res.

View full text Add to dashboard Cite

The Brazil nut is considered one of the noblest trees of the Amazon biome and contains social, ecologic and economic importance to this region. The study of the spatial variance of the edaphic properties in native nut trees can direct future researches about more efficient samplings. The Geostatistics is the methodology utilized for this type of study, once that it considers the structural and random characteristics of a variable spatially distributed. This work sought to get a higher knowledge about the distribution of the nutrients in the soil, verifying the relationship with the occurrence of this species, to thereby provide subsidies to future forest management and maintenance/enlargement of the productivity in these areas. The soil samples were collected from 30 × 30 m on the line, in all of the lines in part of the study, totaling 60 samples. All of the points were georeferenced. The preparation of the samples for the sample preparation for the chemical analysis and the methods and calculations to determine the physicochemical variables studied were described by Nogueira and Souza (2005). The statistical and geostatistical analysis were conducted using the R computational environment, version 3.2.2. Most of the studied variables presented defined level. For the physical variables, there was predominance of the adjustment to the model of the gaussian variogram, follower by the spherical model. In the case of the chemical variables, there were two occurrences for each adjustment model (spherical, exponential and gaussian). The variables that best presented spatial relation with the occurrence of Brazil nut trees were the silt, clay, macroporosity, pH, phosphorus, zinc and copper.

show abstract

“…Por outro lado, os atributos do solo, com dependência espacial, apresentaram r 2 entre médio (0,494) e muito alto (0,923), ADE entre muito baixa (20,0%) e média (60,0%) e coeficientes angulares ficando entre 0,798 e 0,900 (Tabela 3, Figuras 3 e 4). Esses dados foram muito semelhantes àqueles obtidos por Chaves e Farias (2008), Montanari et al (2010) e Souza et al (2010), quando pesquisaram as culturas da cana-de-açúcar, do feijoeiro e da cana-de-açúcar, respectivamente, bem como atributos do solo.…”

Section: Methodsunclassified

Produtividade da cana-de-açúcar e definição de zonas específicas de manejo do solo

Dalchiavon

Carvalho²,

Andrade³

et al. 2013

Sem. Ci. Agr.

View full text Add to dashboard Cite

ResumoA correta intervenção espacial na administração da lavoura, decorrente das zonas específicas de manejo do solo, pode aumentar sua produtividade e a lucratividade agrícola. No ano de 2010, no município de Suzanápolis, no estado de São Paulo (20°27'33'' S lat.; 51°08'05'' W long.), foram verificadas as correlações (espaciais e lineares), entre atributos da cana-de-açúcar e alguns atributos químicos de um Argissolo Vermelho distrófico, visando encontrar aqueles que melhor se correlacionassem com a produtividade da cultura. Para tanto, instalou-se a malha para a coleta de dados do solo e da planta, com 118 pontos amostrais, num talhão de 10,5 ha com a cana-de-açúcar de terceiro corte. AbstractThe correct spatial intervention in the administration of the plantation, arising from specific areas of soil mapping, can increase your productivity as well as profitability and yields in agriculture. The spatial and Pearson's relationships between sugarcane attributes and chemical attributes of a Typic Tropustalf were studied in the growing season of 2010, in Suzanápolis, State of São Paulo, Brazil (20°27'33" S lat.; 51°08'05" W long.), in order to obtain the attributes that had the best sugarcane productivity relationship. To this end, a geostatistical grid containing 118 sample points was installed for soil and plant data collection in an area of 10.5 ha with the third crop cut. The productivity of sugarcane (PRO) represented the attribute of the plant, while the attributes of the soil were: K + , Ca +2 , Mg +2 and organic matter at depths of 0-0.20 m and 0.20-0.40 m. Relationships were calculated between the PRO and the attributes of the soil. Semivariograms were adjusted for all attributes, obtaining the respective krigings

show abstract

Análise dos atributos do solo e da produtividade da cultura de cana-de-açúcar com o uso da geoestatística e árvore de decisão

Abstract: Análise dos atributos do solo e da produtividade da cultura de cana-de-açúcar com o uso da geoestatística e árvore de decisão

Cited by 29 publications

References 15 publications

Classification of the Initial Development of Eucaliptus Using Data Mining Techniques

Classification of the Initial Development of Eucaliptus Using Data Mining Techniques

Spatial variability of soil physical and chemical aspects in a Brazil nut tree stand in the Brazilian Amazon

Produtividade da cana-de-açúcar e definição de zonas específicas de manejo do solo

Contact Info

Product

Resources

About