Height-diameter relationship for Pinus koraiensis in Mengjiagang Forest Farm of Northeast China using nonlinear regressions and artificial neural network models

Abstract

Korean pine (Pinus koraiensis Sieb. et Zucc.) is one of the highly commercial woody species in Northeast China. In this study, six nonlinear equations and artificial neural network (ANN) models were employed to model and validate height-diameter (H-DBH) relationship in three different stand densities of one Korean pine plantation. Data were collected in 12 plots in a 43-year-old even-aged stand of P. koraiensis in Mengjiagang Forest Farm, China. The data were randomly split into two datasets for model development (9 plots) and for model validation (3 plots). All candidate models showed a good perfomance in explaining H-DBH relationship with error estimation of tree height ranging from 0.61 to 1.52 m. Especially, ANN models could reduce the root mean square error (RMSE) by the highest 40%, compared with Power function for the density level of 600 trees. In general, our results showed that ANN models were superior to other six nonlinear models. The H-DBH relationship appeared to differ between stand density levels, thus it is necessary to establish H-DBH models for specific stand densities to provide more accurate estimation of tree height.

Estimation of Tree Heights in an Uneven-Aged, Mixed Forest in Northern Iran Using Artificial Intelligence and Empirical Models

“…They concluded that the ANN and the ANFIS models had greater accuracy than empirical models in diameter and height estimation. Nguyen Thanh et al [24] examined the usefulness of nonlinear equations and ANN models for describing height-diameter relationships in three diverse stand densities of a Korean pine plantation, and found that while all models performed well in describing height-diameter relationships, ANN models could decrease the RMSE the greatest. Zhou et al [11] estimated DBH in a forest area in China using multivariate linear regression and generalized regression neural network models, and found that the latter provided better results with stronger generalizability.…”

A Nonlinear Mixed-Effects Height-Diameter Model with Interaction Effects of Stand Density and Site Index for Larix olgensis in Northeast China

“…The height-diameter relationship can be influenced by the stand density [5][6][7]42], site index [8,13], and the interaction effect of the stand density and site index [14]. In our study, we assumed that the substantial proportion of the tree height variations was better explained by the interaction effect of the stand density and site index than the random effects of single stand density or single site index.…”

“…However, it can be seen from the residual plots (Figure 4) of the interactive NLME height-diameter model that, compared with large-diameter trees, the height of small-diameter trees varies largely, which may be because the trees first focus on the height growth to win glory and then use their resources to increase the diameter [7]. To a certain extent, the altitude may affect the impact of the interaction effects between the stand density and site index on tree height, which requires further experiments to prove.…”

“…For example, Zeide and Vanderschaaf [6] documented that Pinus taeda L. in higher density stands were taller than those in lower density stands. Thanh and Dinh [7] documented that the height-diameter relationship of Pinus koraiensis appears to differ between stand density classes. In addition, the authors of these studies [8][9][10][11] used stand density as an independent variable to construct the height-diameter models and were able to significantly improve the prediction accuracy.…”

Allometric relationships among tree-size variables under tropical forest stages in Gia Lai, Vietnam

“…Crown width was determined by projecting the crown's edges to the ground and then measuring the distance from edge to edge along the widest and shortest axes (Brack, 1999;Philip, 1998). The plot data were divided into two parts: 70% of the data (called fitting data) and 30% of the data (called validation data) (Anacioco et al, 2018;Thanh et al, 2019). The fitting data (7 plots in each of the two forest stages) were used to build nonlinear models, and the validation data (3 plots in each of the two forest stages) were used to validate the models.…”