1- Faculty of Natural Resources, University of Guilan, Rasht, Iran
2- Faculty of Natural Resources and Marine Sciences, Tarbiat Modares University, Noor, Iran
2- Faculty of Natural Resources and Marine Sciences, Tarbiat Modares University, Noor, Iran
Abstract: (735 Views)
Extended Abstract
Background: The Zagros forests play a vital role in climate regulation, biodiversity conservation, and carbon sequestration. The Zagros forests, covering approximately five million hectares, as one of the most valuable forest ecosystems in Iran, play an important role in mitigating the impacts of global warming and in soil conservation. The Leaf Area Index (LAI), as one of the most crucial ecological indicators, reflects the productive capacity of forest ecosystems and is essential for modeling photosynthesis, carbon cycle, and evapotranspiration processes. Leaf Area Index (LAI), as one of the most critical ecological indicators, reflects the productive capacity of forest ecosystems, and is applied in modeling the processes of photosynthesis, carbon cycling, and evapotranspiration. Given the challenges of direct LAI measurement, employing non-destructive machine learning-based methods for LAI estimation becomes imperative. This study aimed to model LAI based on tree structural characteristics (including diameter at breast height [DBH], tree height, and canopy cover percentage) using machine learning algorithms in the northern Zagros forests (the Marivan region, Kurdistan Province). The research seeks to provide an accurate and cost-effective solution for monitoring ecosystem changes and sustainable forest management.
Methods: The study was conducted in the northern Zagros forests (Marivan County) characterized by cold and semi-humid climate. Field data were collected from 80 systematically randomized square plots (20×20 m). In each plot, structural characteristics, including DBH, tree height, canopy cover percentage, and LAI, were measured using hemispherical photography and Gap Light Analyzer (GLA) software. In each sample plot, five microplots (1 m²) were established. The herbaceous cover survey was conducted during the growing season, when most plant species had reached full growth. In each microplot, herbaceous species were identified, and their percentage cover was visually estimated using the Van Der Marel criterion. Aboveground biomass (AGB) was estimated using a polynomial regression model with DBH as the independent variable. In this study, four machine learning algorithms namely Random Forest (RF), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Gaussian Process Regression (GPR) were compared to select the most appropriate algorithm for investigating the relationship between Leaf Area Index (LAI) and forest stand-related variables. In the RF model, 500 trees were considered for the number of trees parameter (ntree), and two features were selected for the number of features considered at each split (mtry). The KNN model was implemented with seven neighbors and sample weighting using a Gaussian kernel function, and the distance between samples was calculated using the Euclidean distance metric. The SVM model was implemented using a radial basis function, with its optimized parameters set to gamma=0.01, epsilon=0.1, and cost coefficient C=1. Furthermore, the GPR model was developed using a Gaussian kernel function. All models were implemented in the R programming language using the random Forest, kknn, e1071, and kernlab packages, respectively. The dataset was divided into training (70%) and validation (30%) subsets, with model performance evaluated using the coefficient of determination (R²), root mean square error (RMSE), relative RMSE (rRMSE), and mean absolute error (MAE).
Results: LAI values in the study area ranged from 0.151 to 4.623, indicating high vegetation density variability. LAI showed a very strong correlation with canopy cover percentage (r = 0.92), and moderate correlations with DBH (r = 0.70) and tree height (r = 0.78). Aboveground biomass demonstrated moderate correlation with LAI (r = 0.64). Among the machine learning algorithms, RF achieved the highest accuracy (R² = 0.96 in training, R² = 0.90 in validation) and was identified as the optimal model. GPR and KNN algorithms performed similarly (R² = 0.91), followed by SVM (R² = 0.88). The correlation matrix confirmed the strong influence of structural characteristics on LAI, while the Shannon-Wiener diversity index showed weak correlation with the other variables.
Conclusion: This study demonstrates that the RF algorithm, with its capability to model complex nonlinear relationships, serves as an effective tool for indirect LAI estimation in Zagros forests. The strong correlation between LAI and both canopy cover and structural tree characteristics enables the use of these variables as physical proxies for leaf density. From the perspective of natural resource management and conservation of the Zagros forests, this research is of great importance. Accurate modeling of the Leaf Area Index and understanding its relationship with structural characteristics can contribute to monitoring changes in forest ecosystems, assessing the impacts of climate change, and designing sustainable management programs. Furthermore, this index can serve as a sensitive indicator for identifying environmental stresses and damages caused by biotic agents. The findings provide a scientific basis for the sustainable management planning of Zagros forests, climate change monitoring, and environmental stress assessment. Future studies should consider integrating remote sensing data with deep learning approaches to enhance model accuracy. This research represents a significant step toward conserving the valuable Zagros ecosystems and promoting evidence-based decision-making.
Background: The Zagros forests play a vital role in climate regulation, biodiversity conservation, and carbon sequestration. The Zagros forests, covering approximately five million hectares, as one of the most valuable forest ecosystems in Iran, play an important role in mitigating the impacts of global warming and in soil conservation. The Leaf Area Index (LAI), as one of the most crucial ecological indicators, reflects the productive capacity of forest ecosystems and is essential for modeling photosynthesis, carbon cycle, and evapotranspiration processes. Leaf Area Index (LAI), as one of the most critical ecological indicators, reflects the productive capacity of forest ecosystems, and is applied in modeling the processes of photosynthesis, carbon cycling, and evapotranspiration. Given the challenges of direct LAI measurement, employing non-destructive machine learning-based methods for LAI estimation becomes imperative. This study aimed to model LAI based on tree structural characteristics (including diameter at breast height [DBH], tree height, and canopy cover percentage) using machine learning algorithms in the northern Zagros forests (the Marivan region, Kurdistan Province). The research seeks to provide an accurate and cost-effective solution for monitoring ecosystem changes and sustainable forest management.
Methods: The study was conducted in the northern Zagros forests (Marivan County) characterized by cold and semi-humid climate. Field data were collected from 80 systematically randomized square plots (20×20 m). In each plot, structural characteristics, including DBH, tree height, canopy cover percentage, and LAI, were measured using hemispherical photography and Gap Light Analyzer (GLA) software. In each sample plot, five microplots (1 m²) were established. The herbaceous cover survey was conducted during the growing season, when most plant species had reached full growth. In each microplot, herbaceous species were identified, and their percentage cover was visually estimated using the Van Der Marel criterion. Aboveground biomass (AGB) was estimated using a polynomial regression model with DBH as the independent variable. In this study, four machine learning algorithms namely Random Forest (RF), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Gaussian Process Regression (GPR) were compared to select the most appropriate algorithm for investigating the relationship between Leaf Area Index (LAI) and forest stand-related variables. In the RF model, 500 trees were considered for the number of trees parameter (ntree), and two features were selected for the number of features considered at each split (mtry). The KNN model was implemented with seven neighbors and sample weighting using a Gaussian kernel function, and the distance between samples was calculated using the Euclidean distance metric. The SVM model was implemented using a radial basis function, with its optimized parameters set to gamma=0.01, epsilon=0.1, and cost coefficient C=1. Furthermore, the GPR model was developed using a Gaussian kernel function. All models were implemented in the R programming language using the random Forest, kknn, e1071, and kernlab packages, respectively. The dataset was divided into training (70%) and validation (30%) subsets, with model performance evaluated using the coefficient of determination (R²), root mean square error (RMSE), relative RMSE (rRMSE), and mean absolute error (MAE).
Results: LAI values in the study area ranged from 0.151 to 4.623, indicating high vegetation density variability. LAI showed a very strong correlation with canopy cover percentage (r = 0.92), and moderate correlations with DBH (r = 0.70) and tree height (r = 0.78). Aboveground biomass demonstrated moderate correlation with LAI (r = 0.64). Among the machine learning algorithms, RF achieved the highest accuracy (R² = 0.96 in training, R² = 0.90 in validation) and was identified as the optimal model. GPR and KNN algorithms performed similarly (R² = 0.91), followed by SVM (R² = 0.88). The correlation matrix confirmed the strong influence of structural characteristics on LAI, while the Shannon-Wiener diversity index showed weak correlation with the other variables.
Conclusion: This study demonstrates that the RF algorithm, with its capability to model complex nonlinear relationships, serves as an effective tool for indirect LAI estimation in Zagros forests. The strong correlation between LAI and both canopy cover and structural tree characteristics enables the use of these variables as physical proxies for leaf density. From the perspective of natural resource management and conservation of the Zagros forests, this research is of great importance. Accurate modeling of the Leaf Area Index and understanding its relationship with structural characteristics can contribute to monitoring changes in forest ecosystems, assessing the impacts of climate change, and designing sustainable management programs. Furthermore, this index can serve as a sensitive indicator for identifying environmental stresses and damages caused by biotic agents. The findings provide a scientific basis for the sustainable management planning of Zagros forests, climate change monitoring, and environmental stress assessment. Future studies should consider integrating remote sensing data with deep learning approaches to enhance model accuracy. This research represents a significant step toward conserving the valuable Zagros ecosystems and promoting evidence-based decision-making.
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
