Davis College of Agriculture, Natural Resources and Design
Division of Forestry and Natural Resources
Linear and nonlinear crown variable functions for 173 Brutian pine (Pinus brutia Ten.) trees were incorporated into a well-known compatible volume and taper equation to evaluate their effect in model prediction accuracy. In addition, the same crown variables were also incorporated into three neural network (NN) types (Back-Propagation, Levenberg-Marquardt and Generalized Regression Neural Networks) to investigate their applicability in over-bark diameter and stem volume predictions. The inclusion of crown ratio and crown ratio with crown length variables resulted in a significant reduction of model sum of squared error, for all models. The incorporation of the crown variables to these models significantly improved model performance. According to results, non-linear regression models were less accurate than the three types of neural network models tested for both over-bark diameter and stem volume predictions in terms of standard error of the estimate and fit index. Specifically, the generated Levenberg-Marquardt Neural Network models outperformed the other models in terms of prediction accuracy. Therefore, this type of neural network model is worth consideration in over-bark diameter and volume prediction modeling, which are some of the most challenging tasks in forest resources management.
Digital Commons Citation
Ozcelik, Ramazan; Diamantopoulou, Maria J.; and Brooks, John R., "* The use of tree crown variables in over-bark diameter and volume prediction models" (2014). Faculty & Staff Scholarship. 2597.
Özçelik, R., Diamantopoulou, M., & Brooks, J. (2014). The use of tree crown variables in over-bark diameter and volume prediction models. iForest - Biogeosciences and Forestry, 7(3), 132–139. https://doi.org/10.3832/ifor0878-007