Stem taper estimations with artificial neural networks for mixed Oriental beech and Kazdaği fir stands in Karabük region, Turkey. CERNE, v. 24, n. 4, p. 439-451, 2018. HIGHLIGHTS The volume of a stem or any part of a tree can be accurately estimated depends on the stem taper estimations. The ANN models and taper equations were compared for estimating stem diameters for a mixed stand in Turkey. The ANN models were superior to taper equations for stem diameter predictions. ANN models offer some advantages to overcome the problems such as multicollinearity and autocorrelation.
Aim of study: The aim of this study was to evaluate the relationships between stump diameters (d0.10 and d0.30) at two different stump heights (10 cm and 30 cm above ground level) and diameter at breast height (d1.30) for mixed stands of Oriental beech (Fagus orientalis) and Kazdağı fir (Abies nordmanniana subsp. equi-trojani) located in Karabük region. Area of study: Study area is located on Büyükdüz Forest Planning Unit of Karabük Forest Enterprise of Zonguldak Regional Directorate of Forestry at Western Blacksea region of Turkey. Material and Methods: A total of 516 sample trees (238 for Oriental beech and 278 for Kazdağı fir) were measured for d0.10, d0.30 and d1.30. To model the relationships between stump diameters and diameter at breast height, ten candidate equations were tested. These equations were ranked according to Coefficient of Determination (R 2), Root Mean Square Error (RMSE) and Mean Absolute Error (MAE), and successful models were selected based on average rank values. Main results: Among equations tested, the power equation had the lowest average rank values for determining d0.10-d1.30 and d0.30-d1.30 relationships of both species and provided the best d1.30 predictions. R 2 , RMSE and MAE values of the power equation are 0.981, 3.64 and 2.58 for d0.10-d1.30 relationship and 0.989, 2.01 and 1.36 for d0.30-d1.30 relationship for Oriental beech, and 0.955, 3.80 and 2.81 for d0.10-d1.30 relationship and 0.988, 1.96 and 1.28 for d0.30-d1.30 relationship for Kazdağı fir, respectively. Research highlights: The equations developed can be used to estimate diameters at breast height of trees extracted from the stand for any reason, and volume of these trees can be predicted in a practical way by using single entry volume equations with the estimated diameters at breast heights.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.