Search Results (74)

Canada’s vast forests play a substantial role in the global carbon balance but require laborious and expensive forest inventory campaigns to monitor changes in aboveground biomass (AGB). Light detection and ranging (LiDAR) or reflectance observations onboard airborne or unoccupied aerial vehicles (UAVs) may address scalability limitations associated with traditional forest inventory but require simple forest structures or large sets of manually delineated crowns. Here, we introduce a deep learning approach for crown delineation and AGB estimation reproducible for complex forest structures without relying on hand annotations for training. Firstly, we detect treetops and delineate crowns with a LiDAR point cloud using marker-controlled watershed segmentation (MCWS). Then we train a deep learning model on annotations derived from MCWS to make crown predictions on UAV red, blue, and green (RGB) tiles. Finally, we estimate AGB metrics from tree height- and crown diameter-based allometric equations, all derived from UAV data. We validate our approach using 14 ha mixed forest stands with various experimental tree densities in Southern Ontario, Canada. Our results show that using an unsupervised LiDAR-only algorithm for tree crown delineation alongside a self-supervised RGB deep learning model trained on LiDAR-derived annotations leads to an 18% improvement in AGB estimation accuracy. In unharvested stands, the self-supervised RGB model performs well for height (adjusted R², R_a² = 0.79) and AGB (R_a² = 0.80) estimation. In thinned stands, the performance of both unsupervised and self-supervised methods varied with stand density, crown clumping, canopy height variation, and species diversity. These findings suggest that MCWS can be supplemented with self-supervised deep learning to directly estimate biomass components in complex forest structures as well as atypical forest conditions where stand density and spatial patterns are manipulated. Full article

In the management of forests, the boundaries of individual units of land containing similar forest resources (e.g., stands) are delineated and used to guide the implementation of management activities. Traditionally, stand boundaries are drawn or digitized by hand; however, work recently has been conducted to automate the process using aerial imagery or airborne light detection and ranging (LiDAR) data as supporting resources. The work described here applies an object-based image analysis (OBIA) process to aerial imagery and to a landform index database. The size and shape of stands in the outcomes of these applications are then adjusted to conform to the desired product of land managers. These products are then intersected as they each contain information of value in the stand delineation process. The intersected database is then adjusted once again to conform to the desired product of land managers. Conformity of the size and shape of the resulting stand boundaries to a reference database drawn subjectively by hand was low to moderate. Specifically, the overall agreement for spatial and thematic (class names) accuracies was 43.0% and 56.8%, respectively. Nevertheless, the process of automating the stand delineation effort remains promising for achieving an efficient and non-subjective characterization of a structurally complex forested environment. Full article

Accurate characterization of tree stems is critical for assessing commercial forest health, estimating merchantable timber volume, and informing sustainable value management strategies. Conventional ground-based manual measurements, although precise, are labor-intensive and impractical at large scales, while remote sensing approaches using satellite or UAV imagery often lack the spatial resolution needed to capture individual tree attributes in complex forest environments. To address these challenges, this study provides a significant contribution by introducing a large-scale dataset encompassing 40 plots in Western Australia (WA) with varying tree densities, derived from Hovermap LiDAR acquisitions and destructive sampling. The dataset includes parameters such as plot and tree identifiers, DBH, tree height, stem length, section lengths, and detailed diameter measurements (e.g., DiaMin, DiaMax, DiaMean) across various heights, enabling precise ground-truth calibration and validation. Based on this dataset, we present the Forest Stem Extraction and Modeling (FoSEM) framework, a LiDAR-driven methodology that efficiently and reliably models individual tree stems from dense 3D point clouds. FoSEM integrates ground segmentation, height normalization, and K-means clustering at a predefined elevation to isolate stem cores. It then applies circle fitting to capture cross-sectional geometry and employs MLESAC-based cylinder fitting for robust stem delineation. Experimental evaluations conducted across various radiata pine plots of varying complexity demonstrate that FoSEM consistently achieves high accuracy, with a DBH RMSE of 1.19 cm (rRMSE = 4.67%) and a height RMSE of 1.00 m (rRMSE = 4.24%). These results surpass those of existing methods and highlight FoSEM’s adaptability to heterogeneous stand conditions. By providing both a robust method and an extensive dataset, this work advances the state of the art in LiDAR-based forest inventory, enabling more efficient and accurate tree-level assessments in support of sustainable forest management. Full article

By assessing the short-term impact that various logging intensities have on stand state in middle-aged P. massoniana plantations, this investigation aimed to establish a theoretical foundation to support the judicious management of Pinus massoniana plantations. Five distinct logging intensity categories were delineated (0%, 10%, 20%, 30%, 40%). To construct a robust stand-state evaluation framework, nine representative indicators across the three dimensions of structure, vitality, and diversity were selected. We scrutinized the short-term impacts of logging intensity by employing the unit circle method. The findings revealed that (1) four indicators—stand density, tree health, species composition, and species diversity—exhibited pronounced sensitivity to logging intensity. These four exhibited significant improvements in the short-term post-logging (p < 0.05). Conversely, the indicators of species evenness, diameter distribution, height distribution, tree dominance, and stand growth exhibited a more subdued response to logging intensity. These five necessitated an extended period to begin to improve. (2) The comprehensive evaluation values measuring the stand state of middle-aged P. massoniana plantations initially ascended but then subsequently descended as logging intensity escalated. The stand-state zenith was pinpointed at an approximate 30% logging intensity. (3) A highly significant linear correlation emerged between the unit circle method results and the principal component analysis results in evaluating stand state (R² = 0.909, p < 0.001), and the unit circle method proved to be more intuitive and responsive. In summation, logging intensity exerted a substantial influence on stand state in middle-aged P. massoniana plantations, with moderate logging (circa 30% logging intensity) enhancing stand state the most. The unit circle method proficiently and effectively illuminated the short-term effects of logging intensity on the stand dynamics of middle-aged P. massoniana plantations, so it thereby may provide invaluable guidance for the formulation of specific forest management strategies. Full article

Accurate individual tree crown delineation (ITCD), which can be used to estimate various forest parameters such as biomass, stem density, and carbon storage, stands as an essential component of precision forestry. Currently, raster data such as the canopy height model derived from airborne light detection and ranging (LiDAR) data have been widely used in large-scale ITCD. However, the accuracy of current existing algorithms is limited due to the influence of understory vegetation and variations in tree crown geometry (e.g., the delineated crown boundaries consistently extend beyond their actual boundaries). In this study, we achieved more accurate crown delineation results based on an expansion process. First, the initial crown boundaries were extracted through watershed segmentation. Then, a “from the inside out” expansion process was guided by a novel gradient feature to obtain accurate crown delineation results across different forest conditions. Results show that our method produced much better performance (~75% matched on average) than other commonly used methods across all test forest plots. The erroneous situation of “match but over-grow” is significantly reduced, regardless of forest conditions. Compared to other methods, our method demonstrates a notable increase in the precisely matched rate across different plot types, with an average increase of 25% in broadleaf plots, 18% in coniferous plots, 23% in mixed plots, 15% in high-density plots, and 32% in medium-density plots, without increasing over- and under- segmentation errors. Our method demonstrates potential applicability across various forest conditions, facilitating future large-scale ITCD tasks and precision forestry applications. Full article

Tree species mapping from the individual crown to landscape scales provides crucial information on the diversity and richness of forest ecosystems, supporting major conservation decisions under ongoing climate change. With the emergence of Remote Piloted Aircraft (RPA), high spatial resolution datasets can be obtained and analyzed to inherently improve the current understanding of broadleaf tree species distribution. The utility of RPA for mapping broadleaf species at broader scales using satellite data needs to be explored. This study investigates the use of RPA RGB imagery captured during peak fall foliage to leverage coloration commonly exhibited by different broadleaf tree species during phenology transition to delineate individual tree crowns and map species distribution. Initially, a two-step hybrid segmentation procedure was designed to delineate tree crowns for two broadleaf forests using RPA imagery collected during the fall season. With the tree crowns, a subsequent Object-based Random Forest (ORF) model was tested for classifying common and economically important broadleaf tree species groups. The classified map was further utilized to improve ground reference data for mapping species distribution at the stand and landscape scales using multispectral satellite imagery (1.4 m to 10 m). The results indicated an improvement in the overall accuracy of 0.13 (from 0.68 to 0.81) and a MICE metric of 0.14 (from 0.61 to 0.75) using reference samples derived from RPA data. The results of this preliminary study are promising in utilizing RPA for multi-scale mapping of broadleaf tree species effectively. Full article

Accurately understanding the stand composition of shelter forests is essential for the construction and benefit evaluation of shelter forest projects. This study explores classification methods for dominant tree species in shelter forests using UAV-derived RGB, hyperspectral, and LiDAR data. It also investigates the impact of individual tree crown (ITC) delineation accuracy, crown morphological parameters, and various data sources and classifiers. First, as a result of the overlap and complex structure of tree crowns in shelterbelt forests, existing ITC delineation methods often lead to over-segmentation or segmentation errors. To address this challenge, we propose a watershed and multi-feature-controlled spectral clustering (WMF-SCS) algorithm for ITC delineation based on UAV RGB and LiDAR data, which offers clearer and more reliable classification objects, features, and training data for tree species classification. Second, spectral, texture, structural, and crown morphological parameters were extracted using UAV hyperspectral and LiDAR data combined with ITC delineation results. Twenty-one classification images were constructed using RF, SVM, MLP, and SAMME for tree species classification. The results show that (1) the proposed WMF-SCS algorithm demonstrates significant performance in ITC delineation in complex mixed forest scenarios (Precision = 0.88, Recall = 0.87, F1-Score = 0.87), resulting in a 1.85% increase in overall classification accuracy; (2) the inclusion of crown morphological parameters derived from LiDAR data improves the overall accuracy of the random forest classifier by 5.82%; (3) compared to using LiDAR or hyperspectral data alone, the classification accuracy using multi-source data improves by an average of 7.94% and 7.52%, respectively; (4) the random forest classifier combined with multi-source data achieves the highest classification accuracy and consistency (OA = 90.70%, Kappa = 0.8747). Full article

For the accurate and automatic mapping of forest stands based on very-high-resolution satellite imagery and digital orthophotos, precise object detection at the individual tree level is necessary. Currently, supervised deep learning models are primarily applied for this task. To train a reliable model, it is crucial to have an accurate tree crown annotation dataset. The current method of generating these training datasets still relies on manual annotation and labeling. Because of the intricate contours of tree crowns, vegetation density in natural forests and the insufficient ground sampling distance of the imagery, manually generated annotations are error-prone. It is unlikely that the manually delineated tree crowns represent the true conditions on the ground. If these error-prone annotations are used as training data for deep learning models, this may lead to inaccurate mapping results for the models. This study critically validates manual tree crown annotations on two study sites: a forest-like plantation on a cemetery and a natural city forest. The validation is based on tree reference data in the form of an official tree register and tree segments extracted from UAV laser scanning (ULS) data for the quality assessment of a training dataset. The validation results reveal that the manual annotations detect only 37% of the tree crowns in the forest-like plantation area and 10% of the tree crowns in the natural forest correctly. Furthermore, it is frequent for multiple trees to be interpreted in the annotation as a single tree at both study sites. Full article

Old-growth forests provide many ecosystem services and benefits. However, they are becoming increasingly rare and thus are an urgent priority for conservation. Accurately mapping old-growth forests is a critical step in this process. Here, we used LiDAR, an improved individual tree crown delineation algorithm for broadleaved forests, Gaussian mixture modelling, and a rule-based classification key to map the extent and location of old-growth forests across a topographically and ecologically complex landscape of 337,548 ha in southeastern Australia. We found that variation in old growth extent was largely driven by the old growth definition, which is a human construct, rather than by uncertainty in the technical aspect of the work. Current regulations define a stand as old growth if it was recruited prior to 1900 (i.e., >120 years old) and is undisturbed (i.e., <10% regrowth canopy cover and no visible disturbance traces). Only 2.7% (95% confidence intervals ranging from 1.4 to 4.9%) of the forests in the study landscape met these criteria. However, this definition is overly restrictive as it leaves many multi-aged stands with ecologically mature elements (e.g., one or more legacy trees amid regrowth) unprotected. Removing the regrowth filter, an indicator of past disturbances, increased the proportion of old-growth forests from 2.7% to 15% of the landscape. Our analyses also revealed that 60% of giant trees (>250 cm in diameter at breast height) were located within 50 m of cool temperate rainforests and cool temperate mixed forests (i.e., streamlines). We discuss the implication of our findings for the conservation and management of high-conservation-value forests in the region. Full article

Dendrogenomics is a new interdisciplinary approach that allows joint analysis of dendrological and genomic data and opens up new ways to study the temporal dynamics of forest treelines, delineate spatial and temporal population structures, decipher individual tree responses to abiotic and biotic stresses, and evaluate the adaptive genetic potential of forest tree populations. These data are needed for the prediction of climate change effects and mitigation of the negative effects. We present here an association analysis of the variation of 27 individual tree traits, including adaptive dendrophenotypes reflecting the individual responses of trees to drought stress, such as the resistance (Rt), recovery (Rc), resilience (Rs), and relative resilience (RRs) indexes measured in 136 Siberian larch trees in 5 populations in the foothills of the Batenevsky Ridge (Kuznetsk Alatau, Republic of Khakassia, Russia), with variation of 9742 SNPs genotyped using ddRADseq in the same trees. The population structure of five closely located Siberian larch populations was relatively weak (F_ST = 0.018). We found that the level of individual heterozygosity positively correlated with the Rc and RR indices for the five studied drought periods and partly with the Rs indices for three drought periods. It seems that higher individual heterozygosity improves the adaptive capabilities of the tree. We also discovered a significant negative relationship between individual heterozygosity and the Rt index in four out of five periods, which means that growth slows down during droughts more in trees with higher individual heterozygosity and is likely associated with energy and internal resource reallocation toward more efficient water and energy usage and optimization of larch growth during drought years. We found 371 SNPs with potentially adaptive variations significantly associated with the variation of adaptive dendrophenotypes based on all three different methods of association analysis. Among them, 26 SNPs were located in genomic regions carrying functional genes: 21 in intergenic regions and 5 in gene-coding regions. Based on the obtained results, it can be assumed that these populations of Siberian larch have relatively high standing adaptive genetic variation and adaptive potential underlying the adaptations of larch to various climatic conditions. Full article

Mangrove forests provide valuable ecosystem services to coastal communities across tropical and subtropical regions. Current anthropogenic stressors threaten these ecosystems and urge researchers to create improved monitoring methods for better environmental management. Recent efforts that have focused on automatically quantifying the above-ground biomass using image analysis have found some success on high resolution imagery of mangrove forests that have sparse vegetation. In this study, we focus on stands of mangrove forests with dense vegetation consisting of the endemic Pelliciera rhizophorae and the more widespread Rhizophora mangle mangrove species located in the remote Utría National Park in the Colombian Pacific coast. Our developed workflow used consumer-grade Unoccupied Aerial System (UAS) imagery of the mangrove forests, from which large orthophoto mosaics and digital surface models are built. We apply convolutional neural networks (CNNs) for instance segmentation to accurately delineate (33% instance average precision) individual tree canopies for the Pelliciera rhizophorae species. We also apply CNNs for semantic segmentation to accurately identify (97% precision and 87% recall) the area coverage of the Rhizophora mangle mangrove tree species as well as the area coverage of surrounding mud and water land-cover classes. We provide a novel algorithm for merging predicted instance segmentation tiles of trees to recover tree shapes and sizes in overlapping border regions of tiles. Using the automatically segmented ground areas we interpolate their height from the digital surface model to generate a digital elevation model, significantly reducing the effort for ground pixel selection. Finally, we calculate a canopy height model from the digital surface and elevation models and combine it with the inventory of Pelliciera rhizophorae trees to derive the height of each individual mangrove tree. The resulting inventory of a mangrove forest, with individual P. rhizophorae tree height information, as well as crown shape and size descriptions, enables the use of allometric equations to calculate important monitoring metrics, such as above-ground biomass and carbon stocks. Full article

Aerial laser scanning technology has excellent potential in landscape management and forestry. Due to its specific characteristics, the application of this type of data is the subject of intensive research, with the search for new areas of application. This work aims to identify the boundaries of forest stands, and forest patches on non-forest land. The research objectives cover the diversity of conditions in the forest landscapes of Slovakia, with its high variability of tree species composition (coniferous, mixed, deciduous stands), age, height, and stand density. A semi-automatic procedure was designed and verified (consisting of the creation of a digital terrain model, a digital surface model, and the identification of peaks and contours of tree crowns), which allows after identification of homogeneous areas of forest stands and/or forest patches (areas covered with trees species canopy) with selected parameters (height, crown size, gap size), with high accuracy. The applicability of the proposed procedure increases the use of freely available ALS data (provided by the Office of Geodesy, Cartography, and Cadastre of the Slovak Republic) and freely distributable software tools (QGIS, CloudCompare). Full article

Invasive species significantly impact ecosystems, which is fostered by global warming. Their removal generates high costs to the greenery managers; therefore, quick and accurate identification methods can allow action to be taken with minimal impact on ecosystems. Remote sensing techniques such as Airborne Laser Scanning (ALS) have been widely applied for this purpose. However, many species of invasive plants, such as Acer negundo L., penetrate the forests under the leaves and thus make recognition difficult. The strongly contaminated riverside forests in the Vistula valley were examined in the gradient of the center of Warsaw and beyond its limits within a Natura 2000 priority habitat (91E0), namely, alluvial and willow forests and poplars. This work aimed to assess the potentiality of a dual-wavelength ALS in identifying the stage of the A. negundo invasion. The research was carried out using over 500 test areas of 4 m diameter within the riparian forests, where the habitats did not show any significant traces of transformation. LiDAR bi-spectral data with a density of 6 points/m² in both channels were acquired with a Riegl VQ-1560i-DW scanner. The implemented approach is based on crown parameters obtained from point cloud segmentation. The Adaptive Mean Shift 3D algorithm was used to separate individual crowns. This method allows for the delineation of individual dominant trees both in the canopy (horizontal segmentation) and undergrowth (vertical segmentation), taking into account the diversified structure of tree stands. The geometrical features and distribution characteristics of the GNDVI (Green Normalized Vegetation Index) were calculated for all crown segments. These features were found to be essential to distinguish A. negundo from other tree species. The classification was based on the sequential additive modeling algorithm using a multi-class loss function. Results with a high accuracy, exceeding 80%, allowed for identifying and localizing tree crowns belonging to the invasive species. With the presented method, we could determine dendrometric traits such as the age of the tree, its height, and the height of the covering leaves of the trees. Full article

Increased use of laser scanning in forest inventories is leading to the adoption and development of automated stand delineation methods. The most common categories of these methods are region merging and region growing. However, recent literature proposes alternative methods that are based on the ideas of cellular automata, self-organizing maps, and combinatorial optimization. The studies where these methods have been described suggest that the new methods are potential options for the automated segmentation of a forest into homogeneous stands. However, no studies are available that compare the new methods to each other and to the traditional region-merging and region-growing algorithms. This study provided a detailed comparison of four methods using LiDAR metrics calculated for grids of 5 m by 5 m raster cells as the data. The tested segmentation methods were region growing (RG), cellular automaton (CA), self-organizing map (SOM), and simulated annealing (SA), which is a heuristic algorithm developed for combinatorial optimization. The case study area was located in the Heilongjiang province of northeast China. The LiDAR data were collected from an unmanned aerial vehicle for three 1500-ha test areas. The proportion of variation in the LiDAR metrics that was explained by the segmentation was mostly the best for the SA method. The RG method produced more heterogeneous segments than the other methods. The CA method resulted in the smallest number of segments and the largest average segment area. The proportion of small segments (smaller than 0.3 ha) was the highest in the RG method while the SA method always produced the fewest small stands. The shapes of the segments were the best (most circular) for the CA and SA methods, but the shape metrics were good for all methods. The results of the study suggest that CA, SOM, and SA may all outperform RG in automated stand delineation. Full article

There is debate on which tree species can sustain forest ecosystem services in a drier and warmer future. In Europe, the use of non-native timber species, such as Douglas fir (Pseudotsuga menziesii [Mirb.] Franco), is suggested as a solution to mitigate climate change impacts because of their high growth resilience to drought. However, the biogeographical, climatic and ecological limits for widely planted timber species still need to be defined. Here, we study the growth response to climate variables and drought of four Douglas fir plantations in northern Spain subjected to contrasting climate conditions. Further, we measure wood density in one of the sites to obtain a better understanding of growth responses to climate. Correlative analyses and simulations based on the Vaganov–Shaskin process-based model confirm that growth of Douglas fir is constrained by warm and dry conditions during summer and early autumn, particularly in the driest study site. Minimum wood density increased in response to dry spring conditions. Therefore, planting Douglas fir in sites with a marked summer drought will result in reduced growth but a dense earlywood. Stands inhabiting dry sites are vulnerable to late-summer drought stress and can act as “sentinel plantations”, delineating the tolerance climate limits of timber species. Full article