ALTERNATIVES TO ESTIMATE THE VOLUME OF INDIVIDUAL TREES IN FOREST FORMATIONS IN THE STATE OF MINAS GERAIS, BRAZIL

• Autor(a) principal: de Abreu, Jadson Coelho
• Data de Publicação: 2020
• Outros Autores: Soares, Carlos Pedro Boechat, Leite, Helio Garcia, Binoti, Daniel Henrique Breda, Silva, Gilson Fernandes da
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Cerne (Online)
• Texto Completo: https://cerne.ufla.br/site/index.php/CERNE/article/view/2413
• topic: Artificial neural networks; mixed linear model; regression; support-vector machine.

The  objective  of  this  study  was  to  compare  different  alternatives  to  estimate  the  stem  volume  of  individual  trees  in  four  different  forest  formations  in  the  Minas  Gerais  state,  Brazil. The data were obtained in a forest inventory procedure performed by the Minas Gerais  Technological  Center  Foundation.  The  stem  volumes  were  computed  by  the  Smalian expression up to the outside bark diameter equal to 4 cm. The volume data of outside bark, diameters (DBH) and total heights were used to fit a Schumacher and Hall equation for each forest formation, considering the structures of the linear fixed and mixed models. Next, 100 Multilayer Perceptron artificial neural networks (ANN) were trained in a supervised manner. In addition, we evaluated eight support-vector machine regression (SVMR). The criteria to evaluate the performance of all the alternatives studied were: the correlation between the observed and estimated volumes, the square root of the mean square error and the frequency distribution by percentage relative error class. After the analyzes, all the alternatives were verified to estimate the volume of the individual trees in the different forest formations. Although the alternatives presented close statistics in the  validation  process,  the  graphical  analysis  of  the  error  distribution  showed  greater  precision of the estimates of the mixed linear models for the four formations. Given the results,  it  is  concluded  that  there  is  no  absolute  superiority  of  one  alternative  over  the  others, and that all of them should be evaluated to find the one which best describes or explains the dataset.