Predicting stem taper using artificial neural network and regression models for Scots pine (Pinus sylvestris L.) in northwestern Türkiye

ABSTRACT

Stem taper models are helpful tools for predicting diameter of a tree at any height or volume of any stem section. In this study, traditional and artificial neural network (ANN) approaches were used to predict stem tapers of Scots pine individuals. The data used in this study correspond to destructively sampled trees in even-aged forest stands located in the three important locations where Scots pine grows naturally in northwestern Türkiye. In total, three regression type stem taper models from different categories and an ANN model were developed and evaluated both statistically and graphically. The best results were obtained by Kozak’s taper model accounting for the 99% of the total variance in stem diameter predictions.

KEYWORDS:

• Artificial intelligence
• Bayesian
• machine learning
• segmented model
• stem diameter
• taper model
• variable-form model

Acknowledgements

I very much appreciate the comments from associate editor and four anonymous reviewers. The assistance in field data collection by the staff at Küre, Taşköprü and Yenice Forest Enterprises, and comments from Dr. Ferhat Bolat about ANN modeling are greatly appreciated.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Funding statement

The author declares no specific funding for this work.