Artificial Neural Networks Applied in Forest Biometrics and Modeling: State of the Art (2007 to 2018)

Abstract

Artificial Intelligence has been an important support tool in different spheres of activity, enabling the knowledge aggregation, the process optimization and the application of methodologies capable of solving complex real problems. Although focusing on a wide space of successful metrics, the Artificial Neural Networks (ANN) approach, a technique similar to the central nervous system, has been gaining notoriety and relevance with regard to the classification of standards, intrinsic parameter estimates, remote sense, data mining and other possibilities. This article aims to develop a systematic review, involving some bibliometric aspects, aimed at detecting the application of ANNs in the field of Forest Engineering, particularly in the prognosis of the essential parameters to the forest inventory, analyzing the construction of the scopes, implementation of networks (type – classification), the software used and complementary techniques. From the 1,140 articles collected in three search databases (Science Direct, Scopus and Web of Science), 43 articles underwent such analyzes. The results show that the number of works within this scope has been increasing continuously, and 32% of the analyzed articles predict the final total marketable volume; 78% made use of the Multilayer Perceptron Networks (MLP, Multilayer Perceptron) and 63% were from Brazilian researchers.