Mixed-effect non-linear modelling for diameter estimation along the stem of Tectona grandis in mid-western Brazil

  • Luciano Rodrigo Lanssanova
  • Sebastião do Amaral Machado
  • Alexandre Techy de Almeida Garrett
  • Izabel Passos Bonete
  • Allan Libanio Pelissari
  • Afonso Figueiredo Filho
  • Franciele Alba da Silva
  • Lucas Dalmolin Ciarnoschi
Keywords: accuracy, mixed-effect modelling, modelling, non-linear regression, taper function

Abstract

This study evaluated the efficiency of taper functions and the application of mixed-effect modelling for diameter estimation along the stems of Tectona grandis. We sampled 266 trees of Tectona grandis, measuring the diameter at relative heights for volume determination, grouping the data according to three form-factor classes. Six taper functions were fitted, selecting the function with better fit performance. Six taper functions were fitted, selecting the function with better fit performance. The selected function was fitted in its basic formulation, and with the mixed non-linear modelling technique in different scenarios, and for the stem stratified in three portions of the total height. The precision and selection of the adjusted models were evaluated regarding the coefficient of determination, standard error of estimate, the Akaike information criterion, bias, quadratic error and absolute bias. According to the statistical criteria used, the model of Kozak was selected for the adjustments. For diameter estimation, the scenario with two coefficients as random effects provided an accuracy increase of 11.91%, and the mixed non-linear modelling better estimated the stem diameter for the stratified stems. In conclusion, the model of Kozak can be used to describe the stem shape of Tectona grandis, and the mixed-effect non-linear model approach was the best technique to estimate diameter along the stem of Tectona grandis.

Keywords: accuracy, mixed-effect modelling, modelling, non-linear regression, taper function

Published
2019-05-20
Section
Articles

Journal Identifiers


eISSN: 2070-2639
print ISSN: 2070-2620