Background: Deep Learning Algorithms (DLA) have become prominent as an application of Artificial Intelligence (AI) Techniques since 2010. This paper introduces the DLA to predict the relationships between individual tree height (ITH) and the diameter at breast height (DBH). Methods: A set of 2024 pairs of individual height and diameter at breast height measurements, originating from 150 sample plots located in stands of even aged and pure Anatolian Crimean Pine (Pinus nigra J.F. Arnold ssp. pallasiana (Lamb.) Holmboe) in Konya Forest Enterprise. The present study primarily investigated the capability and usability of DLA models for predicting the relationships between the ITH and the DBH sampled from some stands with different growth structures. The 80 different DLA models, which involve different the alternatives for the numbers of hidden layers and neuron, have been trained and compared to determine optimum and best predictive DLAs network structure. Results: It was determined that the DLA model with 9 layers and 100 neurons has been the best predictive network model compared as those by other different DLA, Artificial Neural Network, Nonlinear Regression and Nonlinear Mixed Effect models. The alternative of 100 # neurons and 9 # hidden layers in deep learning algorithms resulted in best predictive ITH values with root mean squared error (RMSE, 0.5575), percent of the root mean squared error (RMSE%, 4.9504%), Akaike information criterion (AIC, − 998.9540), Bayesian information criterion (BIC, 884.6591), fit index (FI, 0.9436), average absolute error (AAE, 0.4077), maximum absolute error (max. AE, 2.5106), Bias (0.0057) and percent Bias (Bias%, 0.0502%). In addition, these predictive results with DLAs were further validated by the Equivalence tests that showed the DLA models successfully predicted the tree height in the independent dataset. Conclusion: This study has emphasized the capability of the DLA models, novel artificial intelligence technique, for predicting the relationships between individual tree height and the diameter at breast height that can be required information for the management of forests.

Leaf Area Index (LAI) is an important parameter used in monitoring and modeling of forest ecosystems. The aim of this study was to evaluate performance of the artificial neural network (ANN) models to predict the LAI by comparing the regression analysis models as the classical method in these pure and even-aged Crimean pine forest stands. One hundred eight temporary sample plots were collected from Crimean pine forest stands to estimate stand parameters. Each sample plot was imaged with hemispherical photographs to detect the LAI. The partial correlation analysis was used to assess the relationships between the stand LAI values and stand parameters, and the multivariate linear regression analysis was used to predict the LAI from stand parameters. Different artificial neural network models comprising different number of neuron and transfer functions were trained and used to predict the LAI of forest stands. The correlation coefficients between LAI and stand parameters (stand number of trees, basal area, the quadratic mean diameter, stand density and stand age) were significant at the level of 0.01. The stand age, number of trees, site index, and basal area were independent parameters in the most successful regression model predicted LAI values using stand parameters (R²_adj. = 0.5431). As corresponding method to predict the interactions between the stand LAI values and stand parameters, the neural network architecture based on the RBF 4–19-1 with Gaussian activation function in hidden layer and the identity activation function in output layer performed better in predicting LAI (SSE (12.1040), MSE (0.1223), RMSE (0.3497), AIC (0.1040), BIC (− 77.7310) and R² (0.6392)) compared to the other studied techniques. The ANN outperformed the multivariate regression techniques in predicting LAI from stand parameters. The ANN models, developed in this study, may aid in making forest management planning in study forest stands.

This study examines the relationships between forest structural diversity indices and aboveground stand carbon storage for even-aged and pure Scots pine stands located in the Sarıçiçek Forest, Northern Turkey. In the even-aged Scots pine stands, 293 sample plots were selected to represent various stand conditions such as site quality, age, and stand density. The stand structural diversity, including Shannon’s, improved Shannon, Simpson’s, McIntosh, Margalef, and Berger–Parker indices, was used to correlate the stand carbon storage values. Positive partial correlation coefficients between stand carbon storage and forest structural diversity indices, including the improved Shannon index (r = 0.770), Shannon’s index (r = 0.742), Simpson’s index (r = 0.703), the Berger–Parker index (r = 0.657), the Gini index (r = 0.390), and the Margalef index (r = 0.327), were found at the 0.01 level. These results offer an enhancement of theories concerning positive relationships between stand carbon storage and stand structural diversity for pure and single-species forests. Moreover, regarding biodiversity suitability and stand carbon storage as carbon sinks, the results illustrate that forest stands with higher structural diversity may be preferred when used to mitigate global warming.

Oriental spruce [Picea orientalis (L.) Link] is a species native to Turkey, covering about 350,000 ha. The species is of great importance to the production of timber as well as to the creation of social welfare in eastern Black Sea region. There are few studies about ecological variables affecting oriental spruce site productivity. Based on data from 90 sample plots, multiple regression models were developed using topographic, edaphic, soil nutrients, climatic subgroups and all factors integrated. Within the different subgroups of site factors, the integrated model with all ecological variables provided the best statistical results, which explained 77% of index variation. Other topographic, edaphic, soil nutrients and climatic subgroup models were enumerated by the success of modelling site index of oriental spruce from the related site variables. The results show that the integrated model is more successful than the models developed separately for each ecological variable. However, the integrated model included 12 different variables and thus the assessment of some of these model variables, e.g. element content of the soil (Ca²⁺, Mg²⁺, etc.), require potentially laborious soil analyses and costly applications. Therefore, the topographic model with only three variables (R ²=0.656), which can be assessed directly from digital maps by Geographical Information System (GIS), seems to be more promising and convenient, since the model can be easily applied to large areas. The results can be translated into practical recommendations to forest managers for selecting suitable site conditions for oriental spruce.

The goal of this study was to estimate aboveground stand carbon (AGSC) of pure beech stands in Turkey with ground measurements as well as topographic information and remote sensing data. For this purpose, 153 sample plots were collected from pure beech stands in study area. The AGSC of each sample plot was computed. Eight texture images (variance, dissimilarity, homogeneity, entropy, contrast, mean, second moment and correlation) with five window sizes (3 × 3, 5 × 5, 7 × 7, 9 × 9 and 11 × 11) generated from ALOS PALSAR L-band satellite image. The AGSC models predicting the relationships between ALOS PALSAR texture values and topographic information, and sample plot AGSC were developed by using multiple linear regressions (MLR). Also, artificial neural networks (ANNs) architectures were trained by comparing various numbers of neurons and activation functions in its network types. Our results revealed the ability of ANNs was better than MLR models to predict AGSC values.