Search

Early identification of rubber plantations holds significant importance for both optimal plantation management and scientific studies. Even though remote sensing techniques for mapping rubber plantations have evolved considerably since the 2000s, current methods are highly effective in detecting mature rubber plantations (MRPs), which have distinctive forest characteristics, but often fail to identify immature rubber plantations (IRPs) in a timely manner. This leads to an estimated lag of at least five years in the resulting rubber plantation maps. This paper presents a novel algorithm aimed at promptly pinpointing IRPs in the early planting stage by harnessing a composite of multi-source time series satellite imagery on Google Earth Engine (GEE) platform. Twelve scenarios with different time intervals (3 months, 6 months, and 12 months) and datasets (Landsat 8, Sentinel-2, and Sentinel-1) were tested to determine the most efficient strategy for identifying IRPs using a random forest algorithm. The results demonstrate that the data cube constructed from Landsat 8, Sentinel-2, and Sentinel-1 with 3-month time intervals yields the most accurate identification accuracy. Specifically, it achieves a remarkable overall accuracy of 0.78, 0.87, and 0.93 for plantations established during the second, third, and fourth years, respectively. When implemented on Hainan Island, China’s second-largest natural rubber producing base, the algorithm unveiled a significant decline trend in rubber plantation areas since 2015. Additionally, the spatial distribution exhibited pronounced heterogeneity: while the western and northern regions saw dense immature plantation clusters, the eastern coastal regions hosted only sparse plantations. These up-to-date maps of IRPs are valuable in predicting rubber production, enhancing the monitoring and management practices, and promoting the sustainable development of natural rubber industry.

Accurate canopy height mapping is crucial for estimating rubber plantation productivity, carbon storage, and biomass accurately. The prevailing method combines Global Ecosystem Dynamics Investigation (GEDI) data with spatially continuous variables. However, these models often overlook forest growth variables and face challenges with GEDI geolocation errors. This study introduces a novel GEDI filtering technique to screen for high-quality footprints and incorporates rubber plantation age as a key factor. Utilizing a comprehensive dataset from Landsat-8, Sentinel-2, and Phased Array type L-band Synthetic Aperture Radar (PALSAR-2), we established a model for the canopy height of rubber plantations. Our multifaceted approach yields significant improvements: 1) enhanced rubber canopy height estimation accuracy, evidenced by an R-squared value of 0.86 and reduced error metrics (RMSE = 1.68, MAE = 1.32); 2) The mean difference of −2.81 ± 3.05 m compared with Potapov’s study and −5.62 ± 6.64 m compared with Liu’s, indicating superior consistency and reduced underestimation; and 3) Accurately average canopy heights for rubber plantations aged between 3 and 30 years on Hainan Island at 15.67 ± 1.87 m, spanning a height range of 5.02 to 18.59 m. The integration of stand age and the GEDI footprint filtering technique markedly enhances canopy height estimation accuracy, offering valuable insights for ecological monitoring and the advancement of sustainable forest management practices.

Deep learning, which has exhibited considerable potential and effectiveness in forest resource assessment, is vital for comprehending and managing forest resources and ecosystems. However, extensive assessment of forest resources is highly challenging due to the complex and varied nature of forest types sourced from diverse remote sensing platforms, which include images, point clouds, and fusion data. To facilitate further study, we systematically review the current status, applications and prospects of deep learning technologies for different types of forest remote sensing data. After considering more than two hundred forest-related papers published over the past decade, we introduce sensors and devices for forest data acquisition, classify deep learning methods based on their data processing methods and operational principles, and categorize diverse instances of these methods with various forest applications. Moreover, we summarize available datasets related primarily to forest data and examine the global geographic distribution of the relevant literature. Comprehensive insights into the advantages and limitations of each method are described, offering a forward-looking perspective on the trend of applying deep learning technology to forest research. In this paper, we aim to provide an overview of the current trends and challenges of deep learning techniques applied to forest research, creating a comprehensive picture for use as a reference by both academia and industry professionals.

ObjectivesTo compare the inter-rectus distance (IRD), rectus abdominis thickness (RAT), and stiffness in women during pregnancy and postpartum and identify the risk and protective factors affecting diastasis recti abdominis (DRA).Materials and methodsA total of 171 pregnant women who volunteered to participate in this study were recruited. Using an ultrasonographic diagnostic instrument with shear wave elastography function, IRD, RAT and the Young’s modulus of the rectus abdominis muscles were measured at 12 weeks, 37 weeks of pregnancy, and 6 weeks postpartum.ResultsThe IRD at 37 weeks was significantly higher than that at 12 weeks and then decreased at 6 weeks postpartum, but it was still higher than that at 12 weeks (p < 0.001). RAT and Young’s modulus decreased significantly at 37 weeks compared with those at 12 weeks and then recovered at 6 weeks postpartum, but they were lower than those at 12 weeks (p < 0.001). IRD at 12 weeks was significantly higher in multiparae than in primiparae (p < 0.001). Moreover, positive correlation between the RAT and Young’s modulus of rectus abdominis muscles at 12 and 37 weeks of gestation and 6 weeks postpartum (p < 0.001) was observed. Multiple linear regression analysis showed that the regression equation was significant (f = 24.856, p < 001).ConclusionOur study identified differences in IRD, thickness and stiffness of the rectus abdominis muscle between early and advanced pregnancy and the postpartum period. The risk and protective factors of DRA may guide pregnant women’s protection and treatment.

The precise acquisition of phenotypic parameters for individual trees in plantation forests is important for forest management and resource exploration. The use of Light-Detection and Ranging (LiDAR) technology mounted on Unmanned Aerial Vehicles (UAVs) has become a critical method for forest resource monitoring. Achieving the accurate segmentation of individual tree crowns (ITCs) from UAV LiDAR data remains a significant technical challenge, especially in broad-leaved plantations such as rubber plantations. In this study, we designed an individual tree segmentation framework applicable to dense rubber plantations with complex canopy structures. First, the feature extraction module of PointNet++ was enhanced to precisely extract understory branches. Then, a graph-based segmentation algorithm focusing on the extracted branch and trunk points was designed to segment the point cloud of the rubber plantation. During the segmentation process, a directed acyclic graph is constructed using components generated through grey image clustering in the forest. The edge weights in this graph are determined according to scores calculated using the topologies and heights of the components. Subsequently, ITC segmentation is performed by trimming the edges of the graph to obtain multiple subgraphs representing individual trees. Four different plots were selected to validate the effectiveness of our method, and the widths obtained from our segmented ITCs were compared with the field measurement. As results, the improved PointNet++ achieved an average recall of 94.6% for tree trunk detection, along with an average precision of 96.2%. The accuracy of tree-crown segmentation in the four plots achieved maximal and minimal R2 values of 98.2% and 92.5%, respectively. Further comparative analysis revealed that our method outperforms traditional methods in terms of segmentation accuracy, even in rubber plantations characterized by dense canopies with indistinct boundaries. Thus, our algorithm exhibits great potential for the accurate segmentation of rubber trees, facilitating the acquisition of structural information critical to rubber plantation management.

The ongoing global warming trajectory poses extensive challenges to plant ecosystems, with rubber plantations particularly vulnerable due to their influence on not only the longevity of the growth cycle and rubber yield, but also the complex interplay of carbon, water, and energy exchanges between the forest canopy and atmosphere. However, the response mechanism of phenology in rubber plantations to climate change remains unclear. This study concentrates on sub-optimal environment rubber plantations in Yunnan province, Southwest China. Utilizing the Google Earth Engine (GEE) cloud platform, multi-source remote sensing images were synthesized at 8-day intervals with a spatial resolution of 30-meters. The Normalized Difference Vegetation Index (NDVI) time series was reconstructed using the Savitzky-Golay (S-G) filter, coupled with the application of the seasonal amplitude method to extract three crucial phenological indicators, namely the start of the growing season (SOS), the end of the growing season (EOS), and the length of the growing season (LOS). Linear regression method, Pearson correlation coefficient, multiple stepwise regression analysis were used to extract of the phenology trend and find the relationship between SOS, EOS and climate factors. The findings demonstrated that 1) the phenology of rubber plantations has undergone dynamic changes over the past two decades. Specifically, the SOS advanced by 9.4 days per decade (R2 = 0.42, p< 0.01), whereas the EOS was delayed by 3.8 days per decade (R2 = 0.35, p< 0.01). Additionally, the LOS was extended by 13.2 days per decade (R2 = 0.55, p< 0.01); 2) rubber phenology demonstrated a notable sensitivity to temperature fluctuations during the dry season and precipitation patterns during the rainy season. The SOS advanced 2.0 days (r =−0.19, p< 0.01) and the EOS advanced 2.8 days (r =−0.35, p< 0.01) for every 1°C increase in the cool-dry season. Whereas a 100 mm increase in rainy season precipitation caused the SOS to be delayed by 2.0 days (r = 0.24, p< 0.01), a 100 mm increase in hot-dry season precipitation caused the EOS to be advanced by 7.0 days (r =-0.28, p< 0.01); 3) rubber phenology displayed a legacy effect of preseason climate variations. Changes in temperature during the fourth preseason month and precipitation during the fourth and eleventh preseason months are predominantly responsible for the variation in SOS. Meanwhile, temperature changes during the second, fourth, and ninth preseason months are primarily responsible for the variation in EOS. The study aims to enhance our understanding of how rubber plantations respond to climate change in sub-optimal environments and provide valuable insights for sustainable rubber production management in the face of changing environmental conditions.

The gap fraction (GF) of vegetative canopies is an important property related to the contained bulk of reproductive elements and woody facets within the tree crown volume. This work was developed from the perspectives of porous media theory and computer graphics techniques, considering the vegetative elements in the canopy as a solid matrix and treating the gaps between them as pores to guide volume-based GFvol calculations. Woody components and individual leaves were extracted from terrestrial laser scanning data. The concept of equivalent leaf thickness describing the degrees of leaf curling and drooping was proposed to construct hexagonal prisms properly enclosing the scanned points of each leaf, and cylinder models were adopted to fit each branch segment, enabling the calculation of the equivalent leaf and branch volumes within the crown. Finally, the volume-based GFvol of the tree crown following the definition of the void fraction in porous media theory was calculated as one minus the ratio of the total plant leaf and branch volume to the canopy volume. This approach was tested on five tree species and a forest plot with variable canopy architecture, yielding an estimated maximum volume-based GFvol of 0.985 for a small crepe myrtle and a minimal volume-based GFvol of 0.953 for a sakura tree. The 3D morphology of each compositional element in the tree canopy was geometrically defined and the canopy was considered a porous structure to conduct GFvol calculations based on multidisciplinary theory.

Rubber (Hevea brasiliensis Muell.) plantations are among the most critical agricultural ecosystems in tropical regions, playing a vital role in regional carbon balance. Accurate large-scale biomass estimation for these plantations remains a challenging task due to the severe signal saturation problem. Recent advances in remote sensing big data, cloud platforms, and machine learning have facilitated the precise acquisition of key physiological variables, such as stand age (A) and canopy height (H), which are critical parameters for biomass estimation but have been underutilized in prior studies. Using Hainan Island—the second-largest rubber planting base in China—as a case study, we integrated extensive ground surveys, maps of stand age and canopy height, remote sensing indicators (RSIs), and geographical and climate indicators (ECIs) to ascertain the optimal method for estimating rubber plantation biomass. We compared different inputs and estimation approaches (direct and indirect) using the random forest algorithm and analyzed the spatiotemporal characteristics of rubber plantation biomass on Hainan Island. The results indicated that the traditional model (RSIs + ECIs) had low accuracy and significant estimation bias (R2 = 0.24, RMSE = 38.36 mg/ha). The addition of either stand age or canopy height considerably enhance model accuracy (R2 = 0.77, RMSE ≈ 21.12 mg/ha). Moreover, incorporating the DBH obtained through indirect inversion yielded even greater predictive accuracy (R2 = 0.97, RMSE = 7.73 mg/ha), outperforming estimates derived from an allometric equation model input with the DBH (R2 = 0.67, RMSE = 25.43 mg/ha). However, augmenting the model with stand age, canopy height, or their combination based on RSIs, ECIs, and DBH only marginally improved the accuracy. Consequently, it is not recommended in scenarios with limited data and computing resources. Employing the optimal model, we generated biomass maps of rubber plantations on Hainan Island for 2016 and 2020, revealing that the spatiotemporal distribution pattern of the biomass is closely associated with the establishment year of the rubber plantations. While average biomass in a few areas has undergone slight decreases, total biomass has exhibited significant growth, reaching 5.46 × 107 mg by the end of 2020, underscoring its considerable value as a carbon sink.

Deriving individual tree crown (ITC) information from light detection and ranging (LiDAR) data is of great significance to forest resource assessment and smart management. After proof-of-concept studies, advanced deep learning methods have been shown to have high efficiency and accuracy in remote sensing data analysis and geoscience problem solving. This study proposes a novel concept for synergetic use of the YOLO-v4 deep learning network based on heightmaps directly generated from airborne LiDAR data for ITC segmentation and a computer graphics algorithm for refinement of the segmentation results involving overlapping tree crowns. This concept overcomes the limitations experienced by existing ITC segmentation methods that use aerial photographs to obtain texture and crown appearance information and commonly encounter interference due to heterogeneous solar illumination intensities or interlacing branches and leaves. Three generative adversarial networks (WGAN, CycleGAN, and SinGAN) were employed to generate synthetic images. These images were coupled with manually labeled training samples to train the network. Three forest plots, namely, a tree nursery, forest landscape and mixed tree plantation, were used to verify the effectiveness of our approach. The results showed that the overall recall of our method for detecting ITCs in the three forest plot types reached 83.6%, with an overall precision of 81.4%. Compared with reference field measurement data, the coefficient of determination R2 was ≥ 79.93% for tree crown width estimation, and the accuracy of our deep learning method was not influenced by the values of key parameters, yielding 3.9% greater accuracy than the traditional watershed method. The results demonstrate an enhancement of tree crown segmentation in the form of a heightmap for different forest plot types using the concept of deep learning, and our method bypasses the visual complications arising from aerial images featuring diverse textures and unordered scanned points with irregular geometrical properties.

Accurately estimating and mapping forest structural parameters are essential for monitoring forest resources and understanding ecological processes. The novel deep learning algorithm has the potential to be a promising approach to improve the estimation accuracy while combining with advanced remote sensing technology. Airborne light detection and ranging (LiDAR) has the preferable capability to characterize 3-D canopy structure and estimate forest structural parameters. In this study, we developed a deep learning-based algorithm (Deep-RBN) that combined the fully connected network (FCN) deep learning algorithm with the optimized radial basis neural network (RBN) algorithm for forest structural parameter estimation using airborne LiDAR data. The multiple iterations were used to constantly update the internal weights to achieve the optimized accuracy of model fitting, and the optimized RBN algorithm was developed for the limited training sets. We assessed the efficiency and capability of the Deep-RBN in the estimation of forest structural parameters in a subtropical planted forest of southern China, by comparing the traditional FCN algorithm and multiple linear regression. We found that Deep-RBN had the strongest capability in estimates of forest structural parameters (R2 = 0.67-0.86, rRMSE = 6.95%-20.34%). The sensitivity analysis of the key hyperparameters of Deep-RBN algorithm showed that the learning rate is one of the most important parameters that influence the performance of predictive models, and while its value equal is to 0.001, the predictive models had the highest accuracy (mean DBH: RMSE = 1.01, mean height: RMSE = 1.45, volume: RMSE = 26.49, stem density: RMSE = 121.06). With the increase of training samples added in Deep-RBN model, the predictive models performed better; however, no significant improvements of accuracy were observed while the number of training set is larger than 80. This study demonstrates the benefits of jointly using the Deep-RBN algorithm and airborne LiDAR data to improve the accuracy of forest structural parameter estimation and mapping, which provides a promising methodology for sustainable forest resources monitoring.

Nowadays, laser scanning technology has provided an effective andnondestructive approach to reveal the forest's developmental process and physiological properties. For the purpose of obtaining the 3-D spatial structure and skeleton of trees, this article addresses the separation of wood and foliage from the forest using two phases. The first global phase develops a pointwise supervised learning framework to classify forest point clouds. In order to improve the classification accuracy, we design new features for the learning process, which supplements the current geometric features in terms of the topological information. The second local phase designs a new least-cost path model to further separate wood and foliage points. The separation of branch points is formulated as an energy function and optimized by the dynamic programming technique. Experiments on different plots show that points from stems and branches are detected as wood points completely and correctly. The achieved average completeness, correctness, and $F_1$ score of the wood and foliage separation are 91.25%, 90.34%, and 0.91, respectively, which is promising to the phenotyping study related to the organism's physical form and structure.

Forested environments feature a highly complex radiation regime, and solar radiation is hindered from penetrating into the forest by the 3D canopy structure; hence, canopy shortwave radiation varies spatiotemporally, seasonally, and meteorologically, making the radiant flux challenging to both measure and model. Here, we developed a synergetic method using airborne LiDAR data and computer graphics to model the forest canopy and calculate the radiant fluxes of three forest plots (conifer, broadleaf, and mixed). Directional incident solar beams were emitted according to the solar altitude and azimuth angles, and the forest canopy surface was decomposed into triangular elements. A ray tracing algorithm was utilized to simulate the propagation of reflected and transmitted beams within the forest canopy. Our method accurately modeled the solar radiant fluxes and demonstrated good agreement (R2≥0.82) with the plot-scale results of hemispherical photo-based HPEval software and pyranometer measurements. The maximum incident radiant flux appeared in the conifer plot at noon on June 15 due to the largest solar altitude angle (81.21°) and dense clustering of tree crowns; the conifer plot also received the maximum reflected radiant flux (10.91-324.65 kW) due to the higher reflectance of coniferous trees and the better absorption of reflected solar beams. However, the broadleaf plot received more transmitted radiant flux (37.7-226.71 kW) for the trees in the shaded area due to the larger transmittance of broadleaf species. Our method can directly simulate the detailed plot-scale distribution of canopy radiation and is valuable for researching light-dependent biophysiological processes.

Light detection and ranging (LiDAR) technology has become a mainstream tool for forest surveys, significantly contributing to the improved accuracy of forest inventories. However, the accuracy of the scanned data and tree properties derived using LiDAR technology may differ depending on the occlusion effect, scanning configurations, various scanning patterns, and vegetative characteristics of forest plots. Hence, this paper presents a computer simulation program to build a digital forest plot composed of many tree models constructed based on in situ measurement information and two mobile scanning patterns, i.e., airborne laser scanning (ALS) and ground-based mobile laser scanning (MLS). Through the adjustment of scanning parameters and the velocity of vehicle loading LiDAR sensors, the points scanned using two scanning patterns were compared with the original sampling points, derived from the constructed digital forest plots. The results show that only 2% of sampling points were collected by LiDAR sensors with the fastest vehicle speed (10 m/s) and coarsest scanning angular resolution (horizontal angular resolution 0.16° and vertical angular resolution 1.33°), and approximately 50% of sampling points were collected by LiDAR sensors with slow vehicle velocity (1.25 m/s) and a finer scanning angular resolution (horizontal angular resolution 0.08° and vertical angular resolution 0.33°). Meanwhile, the potential extended application of the proposed computer simulation program as a light model of forest plots was discussed to underpin the creation of the forest digital twin. Three main conclusions are drawn: (1) the collected points from airborne laser scanning (ALS) are higher than those collected from ground-based mobile laser scanning (MLS); (2) reducing the vehicle velocity is more efficient at improving the high density of the point cloud data than by increasing the scanning angular resolution; (3) the lateral extension of crown area increasing the light beams’ receptor area and the clumped leaf dispersion augmenting the light penetration with vertical elongation are the two paramount factors influencing the light transmittance of tree crowns.

Monitoring disturbances in tropical forests is important for assessing disturbance-related greenhouse gas emissions and the ability of forests to sequester carbon, and for formulating strategies for sustainable forest management. Thanks to a long-term observation history, large spatial coverage, and support from powerful cloud platforms such as Google Earth Engine (GEE), remote sensing is increasingly used to detect forest disturbances. In this study, three types of forest disturbances (abrupt, gradual, and multiple) were identified since the late 1980s on Hainan Island, the largest tropical island in China, using an improved LandTrendr algorithm and a dense time series of Landsat and Sentinel-2 satellite images on the GEE cloud platform. Results show that: (1) the algorithm identified forest disturbances with high accuracy, with the R2 for abrupt and gradual disturbance detection reaching 0.92 and 0.83, respectively; (2) the total area in which forest disturbances occurred on Hainan Island over the past 30 years accounted for 10.84% (2.33 × 105 hm2 in total area, at 0.35% per year) of the total forest area in 2020 and peaked around 2005; (3) the areas of abrupt, gradual, and multiple disturbances were 1.21 × 105 hm2, 9.96 × 104 hm2, and 1.25 × 104 hm2, accounting for 51.93%, 42.75%, and 5.32% of the total disturbed area, respectively; and (4) most forest disturbance occurred in low-lying (

Digital twins of forests (trees) are computational virtual recreations of forests (trees) in which the entity distributions and physical processes in real-world forests (trees) are duplicated. It is expected that conventional forest science and management can be undertaken in a digital twin of forests (trees) if the recreation of a real-world forest (tree) has accurate and comprehensive enough information. However, due to the various differences between the current tree model and the real tree, these envisioned digital twins of the forests (trees) stay a theoretical concept. In this study, we developed a processing strategy that partially integrated computational virtual measurement (CVM) process into the tree modeling workflow. Owing to the feature of CVM, partial tree skeleton reconstruction procedures were considered to have higher mechanical objectivity compared to conventional mathematical modeling methods. The reason was that we developed a novel method called virtual diameter tape (VDT), which could provide a certain percentage of modeling elements using CVM. Technically, VDT was able to virtually measure diameters and spatial distribution of cross-sectional area of trees, including the basal area, from point clouds. VDT simulated the physical scenario of diameter tapes, observing point clouds of trees. Diameter and the cross-sectional area of stem and branches were obtained by two consecutive physical measurement processes, one in the forest sample site and another in the virtual space. At the same time, VDT obtained better or a similar accuracy compared to the mathematical methods, i.e., Hough transform-based methods, using the same data sets. The root-mean-square deviation (RMSE) of retrieval of diameter at breast height (DBH) using VDT was 1.02 cm, while DBH obtained from three conventional methods varied from 1.29 cm to 1.73 cm. Based on VDT measurement results, tree skeleton reconstruction and actual forest scenario rendering of our sample plots were further implemented. Beyond the visual consistency, we believe that our work might be a small and solid step in the technological evolution from tree models to the digital twin of forests (trees).

In the original article [...]

Hurricanes often devastate trees throughout coastal China; accordingly, developing a method to quantitatively evaluate the changes in tree phenotypic characteristics under continuous strong winds is of great significance for guiding forest cultivation practices and mitigating wind hazards. For this research, we built a lifting steel truss carrying a large forced draft fan near a rubber plantation on Hainan Island, and we aligned three selected small rubber trees in a row in front of the fan (with separation distances from the forced draft fan outlet of approximately 1.3, 3.3, and 5.3 m) to explore the susceptibility of rubber trees to the mechanical loading of hurricane-level winds. By adjusting the power of the forced draft fan, four wind speeds were emitted: 0 m/s, 10.5 m/s, 13.5 m/s, and 17.5 m/s. Meanwhile, point clouds of the three rubber trees under different continuous wind speeds were acquired using two terrestrial laser scanners. Computer algorithms were applied to derive the key parameters of the three rubber trees, namely, the zenith and azimuth angles of each leaf, effective leaf area index (LAI), windward area of each tree, volume of the tree canopy, and trunk tilt angle, from these point clouds under all four wind speeds. The results show that by increasing the wind speed from 0 m/s to 17.5 m/s, the leaf zenith angles of the three rubber trees were unimodally distributed with the peak concentrated at 0°, while the leaf azimuth angles were bimodally distributed with the peaks concentrated at 0° and 360°. The effective LAI values of the three trees increased from 2.97, 4.77, and 3.63 (no wind) to 3.84, 5.9, and 4.29 (wind speed of 17.5 m/s), respectively, due to a decrease in the vertical crown projection area caused by the compression of the tree canopy. We also found that the effective LAI, windward area, and canopy volume of the third rubber tree (the tree farthest from the forced draft fan) varied less than those of the other two trees, reflecting the attenuation of the wind speed by the crowns of the two trees closer to the fan. The experimental results also indicate that the joint use of light detection and ranging (LiDAR) data with computer graphics algorithms to analyse the dynamic changes in tree phenotypic characteristics during the passage of a hurricane is promising, enabling the development of a novel strategy for mitigating wind hazards. The proposed method with the designed device capable of producing an adjustable wind speed also has the potential to study the impacts of wind damage under various forest conditions by further modifying the tree spacing and tree species.

Accurate individual tree crown (ITC) segmentation from scanned point clouds is a fundamental task in forest biomass monitoring and forest ecology management. Light detection and ranging (LiDAR) as a mainstream tool for forest survey is advancing the pattern of forest data acquisition. In this study, we performed a novel deep learning framework directly processing the forest point clouds belonging to the four forest types (i.e., the nursery base, the monastery garden, the mixed forest, and the defoliated forest) to realize the ITC segmentation. The specific steps of our approach were as follows: first, a voxelization strategy was conducted to subdivide the collected point clouds with various tree species from various forest types into many voxels. These voxels containing point clouds were taken as training samples for the PointNet deep learning framework to identify the tree crowns at the voxel scale. Second, based on the initial segmentation results, we used the height-related gradient information to accurately depict the boundaries of each tree crown. Meanwhile, the retrieved tree crown breadths of individual trees were compared with field measurements to verify the effectiveness of our approach. Among the four forest types, our results revealed the best performance for the nursery base (tree crown detection rate r = 0.90; crown breadth estimation R2 > 0.94 and root mean squared error (RMSE) < 0.2m). A sound performance was also achieved for the monastery garden and mixed forest, which had complex forest structures, complicated intersections of branches and different building types, with r = 0.85, R2 > 0.88 and RMSE < 0.6 m for the monastery garden and r = 0.80, R2 > 0.85 and RMSE < 0.8 m for the mixed forest. For the fourth forest plot type with the distribution of crown defoliation across the woodland, we achieved the performance with r = 0.82, R2 > 0.79 and RMSE < 0.7 m. Our method presents a robust framework inspired by the deep learning technology and computer graphics theory that solves the ITC segmentation problem and retrieves forest parameters under various forest conditions.

Rubber (Hevea brasiliensis Muell.) plantations constitute one of the most important agro-ecosystems in the tropical region of China and Southeast Asia, playing an important role in the carbon budget there. Accurately obtaining their biomass over a large area is challenging because of difficulties in acquiring the Diameter at Breast Height (DBH) through remote sensing and the problem of biomass saturation. The stand age, which is closely related to the forest biomass, was proposed for biomass estimation in this study. A stand age map at an annual scale for Hainan Island, which is the second largest natural rubber production base in China, was generated using all Landsat and Sentinel-2 (LS2) data (1987–2017). Scatter plots and the correlation coefficient method were used to explore the relationship (e.g., biomass saturation) between rubber biomass and different LS2-based variables. Subsequently, a regression model fitted with the stand age (R2 = 0.96) and a Random Forest (RF) model parameterizing with LS2-based variables and/or the stand age were respectively employed to estimate rubber biomass for Hainan Island. The results show that rubber biomass was saturated around 65 Mg/ha with all LS2-based variables. The regression model estimated biomass accurately (R2 = 0.79 and Root Mean Square Error (RMSE) = 14.00 Mg/ha) and eliminated the saturation problem significantly. In addition to LS2-based variables, adding a stand age parameter to the RF models was found to significantly improve the prediction accuracy (R2 = 0.82–0.96 and RMSE = 4.08–10.59 Mg/ha, modeling using samples of different biomass sizes). However, all RF models overestimated the biomass of young plantations and underestimated the biomass of old plantations. A hybrid model integrating the optimal results of RF and regression models reduced estimation bias and generated the best performance (R2 = 0.83 and RMSE = 12.48 Mg/ha). The total rubber biomass of Hainan Island in 2017 was about 5.40 × 107 Mg. The northward and westward expansions after 2000 had great impact on the biomass distribution, leading to a higher biomass density for the inland coastal strip from south to northeast and a lower biomass density in the northern and western regions.

Rubber trees along the southeast coast of China always suffer severe damage from hurricanes. Quantitative assessments of the capacity for wind resistance of various rubber tree clones are currently lacking. We focus on a vulnerability assessment of rubber trees of different clones under wind disturbance impacts by employing multidisciplinary approaches incorporating scanned points, aerodynamics, machine learning and computer graphics. Point cloud data from two typical rubber trees belonging to different clones (PR107 and CATAS 7-20-59) were collected using terrestrial laser scanning, and a connection chain of tree skeletons was constructed using a clustering algorithm of machine learning. The concept of foliage clumps based on the trunk and first-order branches was first proposed to optimize rubber tree plot 3D modelling for simulating the wind field and assessing the wind-related parameters. The results from the obtained phenotypic traits show that the variable leaf area index and included angle between the branches and trunk result in variations in the topological structure and gap fraction of tree crowns, respectively, which are the major influencing factors relevant to the rubber tree’s capacity to resist hurricane strikes. The aerodynamics analysis showed that the maximum dynamic pressure, wind velocity and turbulent intensity of the wind-related parameters in rubber tree plots of clone PR107 (300 Pa, 30 m/s and 15%) are larger than that in rubber tree plots of clone CATAS-7-20-59 (120 Pa, 18 m/s and 5%), which results in a higher probability of local strong cyclone occurrence and a higher vulnerability to hurricane damage.

The terrestrial laser scanner (TLS) has been widely used in forest inventories. However, with increasing precision of TLS, storing and transmitting tree point clouds become more challenging. In this paper, a novel compressed sensing (CS) scheme for broad-leaved tree point clouds is proposed by analyzing and comparing different sparse bases, observation matrices, and reconstruction algorithms. Our scheme starts by eliminating outliers and simplifying point clouds with statistical filtering and voxel filtering. The scheme then applies Haar sparse basis to thin the coordinate data based on the characteristics of the broad-leaved tree point clouds. An observation procedure down-samples the point clouds with the partial Fourier matrix. The regularized orthogonal matching pursuit algorithm (ROMP) finally reconstructs the original point clouds. The experimental results illustrate that the proposed scheme can preserve morphological attributes of the broad-leaved tree within a range of relative error: 0.0010%−3.3937%, and robustly extend to plot-level within a range of mean square error (MSE): 0.0063−0.2245.

In recent years, terrestrial laser scanning has been widely used in complex scene investigation and space object measurement. However, due to the irregular and complex topology of leaves and also multi-view occlusion and interference caused by external environment, reconstructing real 3D leaf model based on the point cloud data is a challenging task. In this paper, we propose a method for leaf surface reconstruction and deformation under external force. Firstly, the polynomial fitting method is designed to locate the accurate leaf boundaries from scanned point cloud. Moreover leaf midvein and lateral veins are delineated by designed skeleton extraction algorithm. Secondly, in order to get lifelike and smoothing leaf surface and eliminate interference caused by leaf jitter in the wind, the generalized tensor product bicubic Bezier surface method is adopted to fit the foliar point cloud data and construct the real 3D leaf model. Thirdly, according to solid mechanics force theory, leaf surface is divided into two parts of mesophyll and vein with different material properties. Then each part is subdivided by tetrahedron mesh, and new stress deformation equations based on the nonlinear finite element are constructed to simulate leaf deformation under various external force. Finally, verified by experimental results, our method is feasible and reasonable to the broad-leaved tree's leaves, and our methodology and simulation process also provide the great potential for further study on evolutions of flowers and leaves under various environmental conditions.

Rubber trees in southern China are often impacted by natural disturbances that can result in a tilted tree body. Accurate crown segmentation for individual rubber trees from scanned point clouds is an essential prerequisite for accurate tree parameter retrieval. In this paper, three plots of different rubber tree clones, PR107, CATAS 7-20-59, and CATAS 8-7-9, were taken as the study subjects. Through data collection using ground-based mobile light detection and ranging (LiDAR), a voxelisation method based on the scanned tree trunk data was proposed, and deep images (i.e., images normally used for deep learning) were generated through frontal and lateral projection transform of point clouds in each voxel with a length of 8 m and a width of 3 m. These images provided the training and testing samples for the faster region-based convolutional neural network (Faster R-CNN) of deep learning. Consequently, the Faster R-CNN combined with the generated training samples comprising 802 deep images with pre-marked trunk locations was trained to automatically recognize the trunk locations in the testing samples, which comprised 359 deep images. Finally, the point clouds for the lower parts of each trunk were extracted through back-projection transform from the recognized trunk locations in the testing samples and used as the seed points for the region’s growing algorithm to accomplish individual rubber tree crown segmentation. Compared with the visual inspection results, the recognition rate of our method reached 100% for the deep images of the testing samples when the images contained one or two trunks or the trunk information was slightly occluded by leaves. For the complicated cases, i.e., multiple trunks or overlapping trunks in one deep image or a trunk appearing in two adjacent deep images, the recognition accuracy of our method was greater than 90%. Our work represents a new method that combines a deep learning framework with point cloud processing for individual rubber tree crown segmentation based on ground-based mobile LiDAR scanned data.

Rubber trees in southern China are often impacted by natural disturbances, and accurate rubber tree crown segmentation and property retrieval are of great significance for forest cultivation treatments and silvicultural risk management. Here, three plots of different rubber tree clones, PR107, CATAS 7-20-59 and CATAS 8-7-9, that were recently impacted by hurricanes and chilling injury were taken as the study targets. Through data collection using ground-based mobile light detection and ranging (LiDAR) technology, a weighted Rayleigh entropy method based on the scanned branch data obtained from the region growing algorithm was proposed to calculate the trunk inclination angle and crown centre of each tree. A watershed algorithm based on the extracted crown centres was then adopted for tree crown segmentation, and a variety of tree properties were successfully extracted to evaluate the susceptibility of different rubber tree clones facing natural disturbances. The results show that the angles between the first-order branches and trunk ranged from 35.1–67.7° for rubber tree clone PR107, which is larger than the angles for clone CATAS 7-20-59, which ranged from 20.2–43.2°. Clone PR107 had the maximum number of scanned leaf points, lowest tree height and a crown volume that was larger than that of CATAS 7-20-59, which generates more frontal leaf area to oppose wind flow and reduces the gaps among tree crowns, inducing strong wind loading on the tree body. These factors result in more severe hurricane damage, resulting in trunk inclination angles that are larger for PR107 than CATAS 7-20-59. In addition, the rubber tree clone CATAS 8-7-9 had the minimal number of scanned leaf points and the smallest tree crown volume, reflecting its vulnerability to both hurricanes and chilling injury. The results are verified by field measurements. The work quantitatively assesses the susceptibility of different rubber tree clones under the impacts of natural disturbances using ground-based mobile LiDAR.

This paper presents a novel framework to extract metro tunnel cross sections (profiles) from Terrestrial Laser Scanning point clouds. The entire framework consists of two steps: tunnel central axis extraction and cross section determination. In tunnel central extraction, we propose a slice-based method to obtain an initial central axis, which is further divided into linear and nonlinear circular segments by an enhanced Random Sample Consensus (RANSAC) tunnel axis segmentation algorithm. This algorithm transforms the problem of hybrid linear and nonlinear segment extraction into a sole segmentation of linear elements defined at the tangent space rather than raw data space, significantly simplifying the tunnel axis segmentation. The extracted axis segments are then provided as input to the step of the cross section determination which generates the coarse cross-sectional points by intersecting a series of straight lines that rotate orthogonally around the tunnel axis with their local fitted quadric surface, i.e., cylindrical surface. These generated profile points are further refined and densified via solving a constrained nonlinear least squares problem. Our experiments on Nanjing metro tunnel show that the cross sectional fitting error is only 1.69 mm. Compared with the designed radius of the metro tunnel, the RMSE (Root Mean Square Error) of extracted cross sections’ radii only keeps 1.60 mm. We also test our algorithm on another metro tunnel in Shanghai, and the results show that the RMSE of radii only keeps 4.60 mm which is superior to a state-of-the-art method of 6.00 mm. Apart from the accurate geometry, our approach can maintain the correct topology among cross sections, thereby guaranteeing the production of geometric tunnel model without crack defects. Moreover, we prove that our algorithm is insensitive to the missing data and point density.

Accurate and reliable information on tree volume distributions, which describe tree frequencies in volume classes, plays a key role in guiding timber harvest, managing carbon budgets, and supplying ecosystem services. Airborne Light Detection and Ranging (LiDAR) has the capability of offering reliable estimates of the distributions of structure attributes in forests. In this study, we predicted individual tree volume distributions over a subtropical forest of southeast China using airborne LiDAR data and field measurements. We first estimated the plot-level total volume by LiDAR-derived standard and canopy metrics. Then the performances of three Weibull parameter prediction methods, i.e., parameter prediction method (PPM), percentile-based parameter recover method (PPRM), and moment-based parameter recover method (MPRM) were assessed to estimate the Weibull scale and shape parameters. Stem density for each plot was calculated by dividing the estimated plot total volume using mean tree volume (i.e., mean value of distributions) derived from the LiDAR-estimated Weibull parameters. Finally, the individual tree volume distributions were generated by the predicted scale and shape parameters, and then scaled by the predicted stem density. The results demonstrated that, compared with the general models, the forest type-specific (i.e., coniferous forests, broadleaved forests, and mixed forests) models had relatively higher accuracies for estimating total volume and stem density, as well as predicting Weibull parameters, percentiles, and raw moments. The relationship between the predicted and reference volume distributions showed a relatively high agreement when the predicted frequencies were scaled to the LiDAR-predicted stem density (mean Reynolds error index eR = 31.47–54.07, mean Packalén error index eP = 0.14–0.21). In addition, the predicted individual tree volume distributions predicted by PPRM of (average mean eR = 37.75) performed the best, followed by MPRM (average mean eR = 40.43) and PPM (average mean eR = 41.22). This study demonstrated that the LiDAR can potentially offer improved estimates of the distributions of tree volume in subtropical forests.

Leaf attribute estimation is crucial for understanding photosynthesis, respiration, transpiration, and carbon and nutrient cycling in vegetation and evaluating the biological parameters of plants or forests. Terrestrial laser scanning (TLS) has the capability to provide detailed characterisations of individual trees at both the branch and leaf scales and to extract accurate structural parameters of stems and crowns. In this paper, we developed a computer graphic-based 3D point cloud segmentation approach for accurately and efficiently detecting tree leaves and their morphological features (i.e., leaf area and leaf angle distributions (leaf azimuthal angle and leaf inclination angle)) from single leaves. To this end, we adopted a sphere neighbourhood model with an adaptive radius to extract the central area points of individual leaves with different morphological structures and complex spatial distributions; meanwhile, four auxiliary criteria were defined to ensure the accuracy of the extracted central area points of individual leaf surfaces. Then, the density-based spatial clustering of applications with noise (DBSCAN) algorithm was used to cluster the central area points of leaves and to obtain the centre point corresponding to each leaf surface. We also achieved segmentation of individual leaf blades using an advanced 3D watershed algorithm based on the extracted centre point of each leaf surface and two morphology-related parameters. Finally, the leaf attributes (leaf area and leaf angle distributions) were calculated and assessed by analysing the segmented single-leaf point cloud. To validate the final results, the actual leaf area, leaf inclination and azimuthal angle data of designated leaves on the experimental trees were manually measured during field activities. In addition, a sensitivity analysis investigated the effect of the parameters in our segmentation algorithm. The results demonstrated that the segmentation accuracy of Ehretia macrophylla (94.0%) was higher than that of crape myrtle (90.6%) and Fatsia japonica (88.8%). The segmentation accuracy of Fatsia japonica was the lowest of the three experimental trees. In addition, the single-leaf area estimation accuracy for Ehretia macrophylla (95.39%) was still the highest among the three experimental trees, and the single-leaf area estimation accuracy for crape myrtle (91.92%) was lower than that for Ehretia macrophylla (95.39%) and Fatsia japonica (92.48%). Third, the method proposed in this paper provided accurate leaf inclination and azimuthal angles for the three experimental trees (Ehretia macrophylla: leaf inclination angle: R 2 = 0.908, RMSE = 6.806° and leaf azimuth angle: R 2 = 0.981, RMSE = 7.680°; crape myrtle: leaf inclination angle: R 2 = 0.901, RMSE = 8.365° and leaf azimuth angle: R 2 = 0.938, RMSE = 7.573°; Fatsia japonica: leaf inclination angle: R 2 = 0.849, RMSE = 6.158° and leaf azimuth angle: R 2 = 0.947, RMSE = 3.946°). The results indicate that the proposed method is effective and operational for providing accurate, detailed information on single leaves and vegetation structure from scanned data. This capability facilitates improvements in applications such as the estimation of leaf area, leaf angle distribution and biomass.

Trophoblasts (TR) are specialized cells of the placenta and play an important role in embryo implantation. The in vitro culture of trophoblasts provided an important tool to investigate the mechanisms of implantation. In the present study, porcine trophoblast cells were derived from pig in vitro fertilized (IVF) and parthenogenetically activated (PA) blastocysts via culturing in medium supplemented with KnockOut serum replacement (KOSR) and basic fibroblast growth factor (bFGF) on STO feeder layers, and the effect of ROCK (Rho-associated coiled-coil protein kinases) inhibiter Y-27632 on the cell lines culture was tested. 5 PA blastocyst derived cell lines and 2 IVF blastocyst derived cell lines have been cultured more than 20 passages; one PA cell lines reached 110 passages without obvious morphological alteration. The derived trophoblast cells exhibited epithelium-like morphology, rich in lipid droplets, and had obvious defined boundaries with the feeder cells. The cells were histochemically stained positive for alkaline phosphatase. The expression of TR lineage markers, such as CDX2, KRT7, KRT18, TEAD4, ELF5 and HAND1, imprinted genes such as IGF2, PEG1 and PEG10, and telomerase activity related genes TERC and TERF2 were detected by immunofluorescence staining, reverse transcription PCR and quantitative real-time PCR analyses. Both PA and IVF blastocysts derived trophoblast cells possessed the ability to differentiate into mature trophoblast cells in vitro. The addition of Y-27632 improved the growth of both PA and IVF blastocyst derived cell lines and increased the expression of trophoblast genes. This study has provided an alternative highly efficient method to establish trophoblast for research focused on peri-implantation and placenta development in IVF and PA embryos.