Estimação de altura, volume e afilamento de árvores de eucalipto utilizando máquina de vetor de suporte

• Ano de defesa: 2017
• Autor(a) principal: Souza, Luandson Araújo de
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal do Espírito Santo; BR; Mestrado em Ciências Florestais; Centro de Ciências Agrárias e Engenharias; UFES; Programa de Pós-Graduação em Ciências Florestais
• Palavras-chave em Português: Regression Models; Machine Learning; Dendrometric Variables; Eucalipto; Análise de regressão; Aprendizado de computador; Modelos de Regressão; Aprendizagem de Máquinas; Variáveis dendrométricas; Florestas; Medição; Recursos Florestais e Engenharia Florestal; 630
• Link de acesso: http://repositorio.ufes.br/handle/10/7652

Faced with restrictions on the use of uneven-aged forests, the investment in evenaged forests has been increasing. This increases the interest in studies seeking to maximize the yield in volume of these forests. The growth of this sector has driven the search for more accurate methods in the estimation of dendrometric variables in order to obtain reliable estimates of the volumetric stock of the forests stands. This work had as objective to evaluate the accuracy of estimate of total height, volume and stem taper of eucalyptus trees, using Support Vector Machine (SVM). For the realization this work, were used data from a eucalyptus stand. The database were randomly divided into two groups: 70% for fit of regression models and training of MVS and 30% for validation. Were fitted different configurations of SVM and different regression models. The evaluation of the regression models and configurations of SVM was based on the statistics: correlation coefficient, root mean square error and bias. Based on the results obtained, it was observed that the SVM provided greater accuracy in the estimates of total height, individual volume and taper in relation to the classic regression models used.