Configuração de algoritmos de aprendizado de máquina na modelagem florestal: um estudo de caso na modelagem da relação hipsométrica.

Serejo da Costa Filho, Sérgio Vinícius; Eduardo Arce, Julio; Rojas Montaño, Razer Nizer; Libanio Pelissari, Allan

In the present study, four machine learning algorithms were applied in the task of modeling the heightdiameter relationship of Pinus taeda L. stands at different ages. Hundreds of parameter combinations were tested for the k-nearest neighbors, random forests, support vector machines, and artificial neural networks algorithms. In order to select the best model for each algorithm, the grid search and the k-fold cross validation methods were applied. The selected models were used to predict the total height of individuals in an independent data set, and the results were compared to those obtained by linear regression models. The machine learning models presented similar statistical indicators to the linear regression models. However, they had less biased dispersion of residues, especially in the stratified analysis by age. The support vector machine and the artificial neural network were the most satisfactory models in precision and dispersion of residues.

ARTIFICIAL neural networks; SUPPORT vector machines; LOBLOLLY pine; MACHINE learning; INDEPENDENT sets; REGRESSION analysis; K-nearest neighbor classification

Ciência Florestal (01039954), 2019, Vol 29, Issue 4, p1501

0103-9954

Academic Journal

10.5902/1980509828392