Comparison of traditional regression models and artificial neural network models for height-diameter modeling in uneven-aged fir stands

Abstract

Forests have been constantly growing with their dynamic structure. In order for this dynamic structure must be managed based on sustainable perspective. Diameter, height, age, stand structure, etc. parameters are used in the inventory stage of the planning. The easiest to measure among these parameters is the diameter. Therefore, the developed models are usually aimed at reaching other forest parameters from the diameter. In this article, 9 different height-diameter models were fitted using regression models, and feed-forward backpropagation artificial neural network model methods for uneven-aged fir (Abies nordmanniana subsp. equi-trojani) stands in Kökez, Bolu region of Turkey. The models compared based on adjusted R², bias, absolute bias, and root mean square error (RMSE). It was observed that the best result was obtained from the artificial neural network model, and the worst result was obtained from the power model.