Evaluation of different modeling approaches for total tree-height estimation in Mediterranean Region of Turkey
Evaluation of different modeling approaches for total tree-height estimation in Mediterranean Region of Turkey
复制标题
DOI：
10.5424/fs/2012213-02338
复制
发表时间：
2012-11
期刊：
影响因子：
0.7
通讯作者：
M. Diamantopoulou;R. Özçelik
中科院分区：
文献类型：
--
作者：
M. Diamantopoulou;R. Özçelik
木材资源的有效管理和木材利用做法需要关于森林资源重要特征的准确和全面的资料，以便评价木材资源的众多管理和利用备选办法。在估算林分木材量和生产力时，树高被认为是最有用的变量之一，其他变量还有蓄积量和胸径。对土耳其西地中海地区森林3种主要树种的树高径数据进行了6个非线性生长函数拟合。广义回归神经网络（GRNN）技术由于能够拟合复杂的非线性模型，也被应用于树高预测。对模型的性能进行了比较和评价。并对所选模型进行了等效性检验。验证表明所有模型预测树高的正确性。根据模型的性能标准，6个非线性生长函数都能很好地捕捉到高度-直径的关系，并能很好地拟合数据，而所构建的广义回归神经网络（GRNN）模型的预测能力优于所有非线性回归模型。
Efficient management of timber resources and wood utilization practices require accurate and versatile information about important characteristics of forest resources for evaluating the numerous management and utilization alternatives for timber resources. Tree height is considered one of the most useful variables along with stocking and diameter at breast height, in estimating forest stand wood volumes and productivity. Six nonlinear growth functions were fitted to tree height-diameter data of three major tree species in Western Mediterranean Region’s forests of Turkey. The generalized regression neural network (GRNN) technique has been applied for tree height prediction, as well, due to its ability to fit complex nonlinear models. The performance of the models was compared and evaluated. Further, equivalence tests of the selected models were conducted. Validation showed the appropriatness of all models to predict tree height. According to the model performance criteria, the six nonlinear growth functions were able to capture the height-diameter relationships and fitted the data almost equally well, while the constructed generalized regression neural network (GRNN) models were found to be superior to all nonlinear regression models, in terms of their predictive ability.