Métodos para análise de configurações pontuais em redes lineares

• Ano de defesa: 2018
• Autor(a) principal: Silva, Victor Ferreira da
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de Lavras; Programa de Pós-Graduação em Estatística e Experimentação Agropecuária; UFLA; brasil; Departamento de Ciências Exatas
• Palavras-chave em Português: Redes lineares; Processos pontuais; Manejo florestal; Matas ciliares; Linear network; Pontual processes; Forest management; Riparian forests; Estatística
• Link de acesso: http://repositorio.ufla.br/jspui/handle/1/29695

In order to understand patterns using puntual processes in a scenario different from the usual one where we have a spatial area of study most often bivariate, that is, the observations scattered over a surface where the observed points can be located anywhere in that area , being able to be georeferenced by latitude and longitude, aiming to present and describe the methodology under study when the points are positioned on a section of line, that when united is called a linear network. Knowing that Brazil has the largest rainforest in the world and in it is also situated the largest hydrographic basin in the world. It will be used as a linear network a river, which cuts off the Fazenda Canário located in the state of Acre, which will be playing the role of linear network and the georeferenced event observed along the banks of this river will be the Heura Crepitans with properties above the established slaughtering measure. It is proposed to analyze how they are distributed in this type of network space scenario. From the analysis of first-order effects, using linear kernel smoothing, where it was shown to be better than the planar kernel which in turn underestimated the intesity rates. Using K-linear function for second-order effects, the results show no clustering present along the river, effective compared to the planar approach that verified the clustering patterns, thus the method is effective for the study and important for the analysis in a forest river census of the Amazon Forest, defining its patterns.