Development of individual tree growth and yield model across multiple contrasting species using nonparametric and parametric methods in the Hyrcanian forests of northern Iran

The Hyrcanian forests of Iran contain many species-rich communities that can only be maintained through an understanding the renewal and development these forests. Located in Jojadeh section Farim forest northern Iran, individual tree growth five distinct species [(Oriental beech (Fagus orientalis Lipsky), chestnut-leaved oak (Quercus castaneifolia Coss. ex J.Gay), Persian maple (Acer velutinum Boiss.), common hornbeam (Carpinus betulus L.) Caucasian alder (Alnus subcordata C.A.Mey.)] were measured on 313 permanent sample plots (0.1 ha) over a 10-year period (2003–2013). In this analysis, various tree-level predictions investigated using available data with application parametric models two artificial neural networks [i.e., multilayer perceptron (MLP) radial basis function (RBF) networks]. Individual diameter showed robust negative relationship basal area larger trees, which was relatively consistent across species. A total height model indicated examined did not differ for given set covariates. survival model, probability Oriental lower than other species, while ingrowth revealed sapling density all increased greater area. network based MLP superior predicted more accurately RBF. Furthermore, also to developed mixed-effect regression. use planning management is imperative, particularly uneven-aged stands, but assessment long-term projection behavior contrasting statistical approaches used warranted despite general superiority nonparametric models.