Predicting Future Diameter Distributions Given Current Stand Attributes

This study discussed four methods to project a diameter distribution from age A1 to age A2. Method 1 recovers parameters of the distribution at age A2 from stand attributes at that age. Method 2 uses a stand-level model to grow the quadratic mean diameter, and then recovers the distribution parameters from that prediction. Method 3 grows the diameter distribution by assuming tree-level survival and diameter growth functions. Method 4 first converts the diameter distribution at age A1 into a list of individual trees before growing these trees to age A2. In a numerical example employing the Weibull distribution, methods 3 and 4 produced better results based on two types of error indices and the relative predictive error for each diameter class. Method 4 is a novel method that converts a diameter distribution into a list of individual-trees, and in the process, successfully links together diameter distribution, individual-tree, and whole stand models.

Comparison of Classical Methods and Mask R-CNN for Automatic Tree Detection and Mapping Using UAV Imagery

Detecting and mapping individual trees accurately and automatically from remote sensing images is of great significance for precision forest management. Many algorithms, including classical methods and deep learning techniques, have been developed and applied for tree crown detection from remote sensing images. However, few studies have evaluated the accuracy of different individual tree detection (ITD) algorithms and their data and processing requirements. This study explored the accuracy of ITD using local maxima (LM) algorithm, marker-controlled watershed segmentation (MCWS), and Mask Region-based Convolutional Neural Networks (Mask R-CNN) in a young plantation forest with different test images. Manually delineated tree crowns from UAV imagery were used for accuracy assessment of the three methods, followed by an evaluation of the data processing and application requirements for three methods to detect individual trees. Overall, Mask R-CNN can best use the information in multi-band input images for detecting individual trees. The results showed that the Mask R-CNN model with the multi-band combination produced higher accuracy than the model with a single-band image, and the RGB band combination achieved the highest accuracy for ITD (F1 score = 94.68%). Moreover, the Mask R-CNN models with multi-band images are capable of providing higher accuracies for ITD than the LM and MCWS algorithms. The LM algorithm and MCWS algorithm also achieved promising accuracies for ITD when the canopy height model (CHM) was used as the test image (F1 score = 87.86% for LM algorithm, F1 score = 85.92% for MCWS algorithm). The LM and MCWS algorithms are easy to use and lower computer computational requirements, but they are unable to identify tree species and are limited by algorithm parameters, which need to be adjusted for each classification. It is highlighted that the application of deep learning with its end-to-end-learning approach is very efficient and capable of deriving the information from multi-layer images, but an additional training set is needed for model training, robust computer resources are required, and a large number of accurate training samples are necessary. This study provides valuable information for forestry practitioners to select an optimal approach for detecting individual trees.

Performance and Sensitivity of Individual Tree Segmentation Methods for UAV-LiDAR in Multiple Forest Types

Using unmanned aerial vehicles (UAV) as platforms for light detection and ranging (LiDAR) sensors offers the efficient operation and advantages of active remote sensing; hence, UAV-LiDAR plays an important role in forest resource investigations. However, high-precision individual tree segmentation, in which the most appropriate individual tree segmentation method and the optimal algorithm parameter settings must be determined, remains highly challenging when applied to multiple forest types. This article compared the applicability of methods based on a canopy height model (CHM) and a normalized point cloud (NPC) obtained from UAV-LiDAR point cloud data. The watershed algorithm, local maximum method, point cloud-based cluster segmentation, and layer stacking were used to segment individual trees and extract the tree height parameters from nine plots of three forest types. The individual tree segmentation results were evaluated based on experimental field data, and the sensitivity of the parameter settings in the segmentation methods was analyzed. Among all plots, the overall accuracy F of individual tree segmentation was between 0.621 and 1, the average RMSE of tree height extraction was 1.175 m, and the RMSE% was 12.54%. The results indicated that compared with the CHM-based methods, the NPC-based methods exhibited better performance in individual tree segmentation; additionally, the type and complexity of a forest influence the accuracy of individual tree segmentation, and point cloud-based cluster segmentation is the preferred scheme for individual tree segmentation, while layer stacking should be used as a supplement in multilayer forests and extremely complex heterogeneous forests. This research provides important guidance for the use of UAV-LiDAR to accurately obtain forest structure parameters and perform forest resource investigations. In addition, the methods compared in this paper can be employed to extract vegetation indices, such as the canopy height, leaf area index, and vegetation coverage.

Estimation of Individual Tree Biomass in Natural Secondary Forests Based on ALS Data and WorldView-3 Imagery

Individual-tree aboveground biomass (AGB) estimation can highlight the spatial distribution of AGB and is vital for precision forestry. Accurately estimating individual tree AGB is a requisite for accurate forest carbon stock assessment of natural secondary forests (NSFs). In this study, we investigated the performance of three machine learning and three ensemble learning algorithms in tree species classification based on airborne laser scanning (ALS) and WorldView-3 imagery, inversed the diameter at breast height (DBH) using an optimal tree height curve model, and mapped individual tree AGB for a site in northeast China using additive biomass equations, tree species, and inversed DBH. The results showed that the combination of ALS and WorldView-3 performed better than either single data source in tree species classification, and ensemble learning algorithms outperformed machine learning algorithms (except CNN). Seven tree species had satisfactory accuracy of individual tree AGB estimation, with R2 values ranging from 0.68 to 0.85 and RMSE ranging from 7.47 kg to 36.83kg. The average individual tree AGB was 125.32 kg and the forest AGB was 113.58 Mg/ha in the Maoershan study site in Heilongjiang Province, China. This study provides a way to classify tree species and estimate individual tree AGB of NSFs based on ALS data and WorldView-3 imagery.

HARVESTER PRODUCTIVITY AND COSTS IN CLEAR CUTTING Pinus taeda STANDS UNDER DIFFERENT MANAGEMENT REGIMES

The increased demand for several forest products makes it necessary to apply different management regimes in forest stands, which may influence the wood harvesting operations. This study aimed to evaluate the effect of average individual tree volumes obtained through different management regimes on harvester productivity and costs, thereby enabling to generate information for forest managers. The study was carried out in three Pinus taeda L. stands under clear cutting with different average individual tree volumes (AIV): I (0.367 m3); II (0.582 m3); and III (0.766 m3). Working cycle times, productivity per productive machine hour, energy yield and production costs were obtained by a time and motion study, in which the average values obtained were compared by the Tukey-Kramer test (α ≤ 0.05). The work elements of the harvester’s work cycles were affected by forest management regimes, mainly the movement and the processing, with significant statistical difference between stands, but no difference between total working cycle times. The management regime applied to forest stands influenced the spacing and whole trunk volume which consequently increased the average productivity of the machine from 36.8 to 74.1 m³ per productive machine hour in treatments I and III, respectively, and reduced production costs by 50%. The forest management regimes influenced the clear-cutting operation with harvester.