ARTIFICIAL NEURAL NETWORKS AND MIXED-EFFECTS MODELING TO DESCRIBE THE STEM PROFILE OF Pinus taeda L.

Izabel Passos Bonete,Afonso Figueiredo Filho,Fabiane Aparecida De Souza Retslaff,Luciano Rodrigo Lanssanova,Julio Eduardo Arce

doi:10.5380/rf.v50i1.61764

Izabel Passos Bonete, Afonso Figueiredo Filho + Show 3 more

Open Access

https://doi.org/10.5380/rf.v50i1.61764

Copy DOI

Journal: FLORESTA	Publication Date: Dec 20, 2019
Citations: 2	License type: cc-by

Affiliation: Universidade Estadual do Centro-Oeste

Abstract

The aim of this study was to compare the effectiveness of artificial neural networks (ANNs) and mixed-effects models (MEMs) in describing the stem profile of Pinus taeda L., using sample data from 246 trees. First, three taper functions of different classes were adjusted: non-segmented, segmented, and variable-form. To adjust the models, the nonlinear regression technique (nls) was used. In the best performance equation for nls-adjusted diameter estimates, the nonlinear MEM (nlme) was applied at two levels, using the age class (ci) and DBH class (cd). For this, three different study scenarios were considered, with the number of coefficients with random effects ranging from one to three in each scenario. The adjustments were made using the nls and nlme functions in R software. The selected mixed-effect equations were compared with ANNs generated in Neuro 4.0 software. The taper function models and ANNs were classified according to statistical criteria and graphical analysis of residues. The tapering equation of Bi (2000) presented better performance for diameter estimates than the non-segmented and segmented equations. Application of the nlme technique in the Bi (2000) equation increased the accuracy of the diameter estimates for Pinus taeda, in relation to the adjustment using the nls technique. In the comparison of ANNs with the variations of the Bi equation of mixed-effects, the networks performed better, indicated in the description of the P. taeda profile.

Highlights

Accurate estimates of forest production are fundamental for companies in the forest sector
The present study investigated the use of nonlinear mixed-effects models (MEMs) and artificial neural networks (ANNs) with the aim to compare the performance of these methodologies in the description of stem profiles of Pinus taeda L
The 5th degree polynomial is one of the most widely used non-segmented models to describe the profiles of P. taeda and P. elliottii in southern Brazil (KOHLER et al, 2013; TEO et al, 2013), the equation occupied the third position in terms of performance in the present study

Summary

Introduction

Accurate estimates of forest production are fundamental for companies in the forest sector. The estimation of tree volume is hampered mainly by variation in the shape of the stem profile. Variation in the shape of the stem is related to the decrease in diameter from the bottom to the top of the stem. This is called tapering, thinning, or taper. The shape and tapering of the trees stem have been the subject of forest research for over a century, considering their relevance and applicability to estimates of diameter and volume by assortment. Many statistical models and multivariate techniques have been tested to describe the shape and tapering of stems In this context there are three different types of models: non-segmented models that describe the tapering of the stem with a FLORESTA, Curitiba, PR, v.

Objectives

Methods

Conclusion