Advanced search
Start date
Betweenand
(Reference retrieved automatically from Web of Science through information on FAPESP grant and its corresponding number as mentioned in the publication by the authors.)

Artificial Intelligence Procedures for Tree Taper Estimation within a Complex Vegetation Mosaic in Brazil

Full text
Author(s):
Nunes, Matheus Henrique [1, 2] ; Gorgens, Eric Bastos [2, 3]
Total Authors: 2
Affiliation:
[1] Univ Cambridge, Dept Plant Sci, Forest Ecol & Conservat Grp, Cambridge CB2 3EA - England
[2] Univ Sao Paulo, Coll Agr, Dept Forest Sci, BR-13418900 Piracicaba, SP - Brazil
[3] Univ Fed Vales do Jequitinhonha e Mucuri, Dept Forestry, BR-39100000 Diamantina, MG - Brazil
Total Affiliations: 3
Document type: Journal article
Source: PLoS One; v. 11, n. 5 MAY 17 2016.
Web of Science Citations: 5
Abstract

Tree stem form in native tropical forests is very irregular, posing a challenge to establishing taper equations that can accurately predict the diameter at any height along the stem and subsequently merchantable volume. Artificial intelligence approaches can be useful techniques in minimizing estimation errors within complex variations of vegetation. We evaluated the performance of Random Forest (R) regression tree and Artificial Neural Network procedures in modelling stem taper. Diameters and volume outside bark were compared to a traditional taper-based equation across a tropical Brazilian savanna, a seasonal semideciduous forest and a rainforest. Neural network models were found to be more accurate than the traditional taper equation. Random forest showed trends in the residuals from the diameter prediction and provided the least precise and accurate estimations for all forest types. This study provides insights into the superiority of a neural network, which provided advantages regarding the handling of local effects. (AU)

FAPESP's process: 11/19236-9 - Determination the relative height and sampling intensity using analytic geometry in native forests for estimation of individuals volume and taper
Grantee:Hilton Thadeu Zarate Do Couto
Support type: Regular Research Grants
FAPESP's process: 10/13723-2 - Determination the relative height of sampling intensity and using analytic geometry in native forests for estimation of individuals volume and taper.
Grantee:Matheus Henrique Nunes
Support type: Scholarships in Brazil - Master
FAPESP's process: 12/01044-9 - Determination of the relative height and sampling intensity and using analytic geometry in natural forests, to estimate the individual volume and taper
Grantee:Matheus Henrique Nunes
Support type: Scholarships abroad - Research Internship - Master's degree