EFFECTS OF MODELING METHODS AND SAMPLE SIZE FOR LIDAR-DERIVED BASAL AREA ESTIMATION IN EUCALYPTUS FOREST

Vol 19, 2019 - 96886
Pôster
Download
Favoritar este trabalho
Como citar esse trabalho?
Resumo

This study aimed to compare the effects of two modeling methods for estimating basal area in Eucalyptus forest plantation using airbone LiDAR data. The study was conducted at the municipalities of Pilar do Sul and São Miguel Arcanjo, southeast region of the state of São Paulo, Brazil, based on LiDAR and field inventory collected in a set of 158 circular plots in 2013. Random Forest (RF) and Linear Regression (LM) were compared in terms of RMSE, Bias and adj.R² with 500 replicates. The best performance was verified for the LM method.

Instituições
  • 1 Universidade Federal Rural de Pernambuco
  • 2 University of Maryland\NASA Goddard Space Flight Center
  • 3 Universidade Federal de São João Del Rei
  • 4 North Carolina State University
  • 5 Universidade Federal do Paraná
  • 6 Suzano Papel e Celulose S. A.
Eixo Temático
  • LIDAR: sensores e aplicações
Palavras-chave
LiDAR
Eucalyptus
Basal Area
Machine Learning
Remote Sensing