Optimizing forest road planning in a sustainable forest management area in the Brazilian Amazon.

The construction of forest roads in Brazilian Amazon is costly and has a significant environmental impact. Several practices and principles must be observed to comply with legislation, to preserve the remaining forest, and to ensure sustainable exploitation. Road planning is complex in this context, based on the number of aspects and variables that must be considered. This research aimed to evaluate computational methods' effectiveness in planning forest roads, optimizing resources to reduce damage to the remaining forest, compared to traditional planning methods. The study area was a native forest under a sustainable forest management regime located in municipalities of Terra Santa and Oriximiná, in Pará, in Brazilian Amazon. Data obtained from area made it possible formulate six instances of different sizes. A binary integer linear programming model was used, solved using CPLEX software, and Dijkstra, Bellman-Ford, Dial, and D'Esopo-Pape shortest path algorithm, implemented in C programming language. During processing of instances, the time taken to obtain the solution increased according to size of instance, however, time difference was not significant. Among the evaluated algorithms, the D'Esopo-Pape algorithm showed the best performance. The evaluated methods were effective in obtaining an optimal solution for proposed forest road planning. The solutions obtained using computational methods more effectively considered the restrictions associated with sustainable forest management, in contrast to those derived from the traditional planning by forestry company.

Computational techniques applied to volume and biomass estimation of trees in Brazilian savanna.

The Brazilian Savannah, known as Cerrado, has the richest flora in the world among the savannas, with a high degree of endemic species. Despite the global ecological importance of the Cerrado, there are few studies focused on the modeling of the volume and biomass of this forest formation. Volume and biomass estimation can be performed using allometric models, artificial intelligence (AI) techniques and mixed regression models. Thus, the aim of this work was to evaluate the use of AI techniques and mixed models to estimate the volume and biomass of individual trees in vegetation of Brazilian central savanna. Numerical variables (diameter at height of 1.30 m of ground, total height, volume and biomass) and categorical variables (species) were used for the training and fitting of AI techniques and mixed models, respectively. The statistical indicators used to evaluate the training and the adjustment were the correlation coefficient, bias and Root mean square error relative. In addition, graphs were elaborated as complementary analysis. The results obtained by the statistical indicators and the graphical analysis show the great potential of AI techniques and mixed models in the estimation of volume and biomass of individual trees in Brazilian savanna vegetation. In addition, the proposed methodologies can be adapted to other biomes, forest typologies and variables of interest.