Main Article Content

Published:
Mar 31, 2021
Keywords:
artificial intelligence
artificial neural networks
support vector machines
forest biomass

Abstract

The increasing awareness of global climate change has drawn attention to the role of forests as mitigators of this process as they act as carbon sinks to the atmosphere. Understanding the process of carbon storage in forests and its drivers, as well as presenting consistent models for their estimation, is a current demand. In this sense, the aim of this study was to evaluate the performance of machine learning techniques: support vector machines (SVM) and to propose a new nonlinear model extracted from the training of an artificial neural network (ANN) in the modeling of above ground carbon stock in a secondary semideciduous forest. SVM and ANN construction and training process considered independent variables selected by stepwise: minimum DBH (diameter of breast height - 1.3 m), maximum DBH, mean DBH, total height and number of trees, all by plot. SVM and the model extracted from ANN were applied to the data set intended for validation. Both techniques presented satisfactory performance in modeling carbon stock by plot, with homogeneous distribution and low dispersion of residues and predicted values close to those observed. Analysis criteria indicated superior performance of the model extracted from the artificial neural network, which presented a mean relative error of 6.94 %, while the support vector machine presented 13.52 %, combined with lower bias values and higher correlation between predictions and observations.

Daniel Dantas
Marcela de Castro Nunes Santos Terra
Luis Paulo Baldissera Schorr
Natalino Calegario
Author Biographies

Daniel Dantas, Federal University of Lavras, Departament of Forest Sciences, Lavras, Minas Gerais, Brazil.

Federal University of Lavras, Departament of Forest Sciences, Lavras, Minas Gerais, Brazil, tel.: 5538991237493

Marcela de Castro Nunes Santos Terra, Federal University of Lavras, Departament of Forest Sciences, Lavras, Minas Gerais, Brazil.

Federal University of Lavras, Departament of Forest Sciences, Lavras, Minas Gerais, Brazil, tel.: 5538991237493

Luis Paulo Baldissera Schorr, Federal University of Lavras, Departament of Forest Sciences, Lavras, Minas Gerais, Brazil.

Federal University of Lavras, Departament of Forest Sciences, Lavras, Minas Gerais, Brazil, tel.: 5538991237493

Natalino Calegario, Federal University of Lavras, Departament of Forest Sciences, Lavras, Minas Gerais, Brazil.

Federal University of Lavras, Departament of Forest Sciences, Lavras, Minas Gerais, Brazil, tel.: 5538991237493

How to Cite
Dantas, D., de Castro Nunes Santos Terra, M., Baldissera Schorr, L. P., & Calegario, N. (2021). Machine learning for carbon stock prediction in a tropical forest in Southeastern Brazil. Revista Bosque, 42(1), 131–140. Retrieved from https://revistabosque.org/index.php/bosque/article/view/230

Downloads

Download data is not yet available.

Article Details

Similar Articles

You may also start an advanced similarity search for this article.