Search Results (79)

Forest structural parameters, such as canopy closure, stand density, diameter at breast height, tree height, leaf area index, stand age, and biomass, are fundamental for quantifying forest ecosystem functioning and supporting sustainable forest management. Remote sensing has become an indispensable tool for forest structural parameter estimation. Commonly used data sources include optical imagery, synthetic aperture radar (SAR), light detection and ranging (LiDAR), unmanned aerial vehicles (UAVs), and multisource data fusion. Correspondingly, modeling approaches have evolved from empirical and statistical methods to machine learning, deep learning, and hybrid physical-data-driven models, enabling improved characterization of nonlinear and complex forest structures. Each data source and modeling strategy offers unique strengths and limitations with respect to accuracy, scalability, interpretability, and transferability. This review provides a concise synthesis of recent advances in remote sensing data sources and model algorithms for forest structural parameter estimation, evaluates the strengths and limitations of different sensors and algorithms, and highlights key challenges related to uncertainty, scalability, transferability, and model interpretability. Finally, future research directions are discussed, emphasizing cross-scale integration, multisource data fusion, and physically informed deep learning frameworks as promising pathways toward more accurate, robust, and ecologically interpretable forest structural parameter modeling at regional to global scales. Full article

Accurate estimation of tree biomass and volume is essential for sustainable forest management, climate change mitigation, and ecosystem service assessment. Recent advances in unmanned aerial vehicle (UAV) technology enable the acquisition of ultra-high-resolution optical and three-dimensional data, providing a resource-efficient alternative to traditional field-based inventories. This review synthesizes 181 peer-reviewed studies on UAV-based estimation of tree biomass and volume across forestry, agricultural, and urban ecosystems, integrating bibliometric analysis with qualitative literature review. The results reveal a clear methodological shift from early structure-from-motion photogrammetry toward integrated frameworks combining three-dimensional canopy metrics, multispectral or LiDAR data, and machine learning or deep learning models. Across applications, tree height, crown geometry, and canopy volume consistently emerge as the most robust predictors of biomass and volume, enabling accurate individual-tree and plot-level estimates while substantially reducing field effort and ecological disturbance. UAV-based approaches demonstrate particularly strong performance in orchards, plantation forests, and urban environments, and increasing applicability in complex systems such as mangroves and mixed forests. Despite significant progress, key challenges remain, including limited methodological standardization, insufficient uncertainty quantification, scaling constraints beyond local extents, and the underrepresentation of biodiversity-rich and structurally complex ecosystems. Addressing these gaps is critical for the operational integration of UAV-derived biomass and volume estimates into sustainable land management, carbon accounting, and climate-resilient monitoring frameworks. Full article

This investigation examines diffusion processes for predicting whole-stand volume, incorporating the variability and uncertainty inherent in regional, operational, and environmental factors. The distribution and spatial organization of trees within a specified forest region, alongside dynamic fluctuations and intricate uncertainties, are modeled by a set of nonsymmetric stochastic differential equations of a sigmoidal nature. The study introduces a three-dimensional system of stochastic differential equations (SDEs) with mixed-effect parameters, designed to quantify the dynamics of the three-dimensional distribution of tree-size components—namely diameter (diameter at breast height), potentially occupied area, and height—with respect to the age of a tree. This research significantly contributes by translating the analysis of tree size variables, specifically height, occupied area, and diameter, into stochastic processes. This transformation facilitates the representation of stand volume changes over time. Crucially, the estimation of model parameters is based exclusively on measurements of tree diameter, occupied area, and height, avoiding the need for direct tree volume assessments. The newly developed model has proven capable of accurately predicting, tracking, and elucidating the dynamics of stand volume yield and growth as trees mature. An empirical dataset composed of mixed-species, uneven-aged permanent experimental plots in Lithuania serves to substantiate the theoretical findings. According to the dataset under examination, the model-based estimates of stand volume per hectare in this region exhibited satisfactory goodness-of-fit statistics. Specifically, the root mean square error (and corresponding relative root mean square error) for the living trees of mixed, pine, spruce, and birch tree species were 68.814 m³ (20.4%), 20.778 m³ (7.8%), 32.776 m³ (37.3%), and 4.825 m³ (26.3%), respectively. The model is executed within Maple, a symbolic algebra system. Full article

The number of rubber plantations has increased significantly since 2000, especially in Southeast Asia and China, and their ecological impacts are becoming more evident. A robust rubber supply monitoring system is currently required at both the production and ecological levels. This study used Sentinel-2 multi-rule remote sensing images and a deep learning method to construct a deep learning model that could generate a distribution map of rubber plantations in Danzhou City, Hainan Province, from 2019 to 2024. For biomass modeling, 52 sample plots (27 of which were historical plots) were integrated, and the canopy structure was extracted as an auxiliary variable from the point cloud data generated by an unmanned aerial vehicle survey. Five algorithms, namely Random Forest (RF), Gradient Boosting Decision Tree, Convolutional Neural Network, Back Propagation Neural Network, and Extreme Gradient Boosting, were used to characterize the spatiotemporal changes in rubber plantation biomass and analyze the driving mechanisms. The developed deep learning model was exceptional at identifying rubber plantations (overall accuracy = 91.63%, Kappa = 0.83). The RF model performed the best in terms of biomass prediction (R² = 0.72, RRMSE = 21.48 Mg/ha). Research shows that canopy height as a characteristic factor enhances the explanatory power and stability of the biomass model. However, due to limitations such as sample plot size, image differences, canopy closure degree, and point cloud density, uncertainties in its generalization across years and regions remain. In summary, the proposed framework effectively captures the spatial and temporal dynamics of rubber plantations and estimates their biomass with high accuracy. This study provides a crucial reference for the refined management and ongoing monitoring of rubber plantations. Full article

The accurate prediction of plant height is crucial for optimizing soybean cultivar selection and improving yield estimations. In this study, we investigate the potential of machine learning (ML) algorithms to predict soybean plant height (PH) based on a diverse set of agronomic parameters analyzed from forty soybean cultivars evaluated across sequential harvests. Using a comprehensive dataset, the models Elastic Net (EN), Extra Trees (ET), Gaussian Process Regressor (GPR), K-Nearest Neighbors, and XGBoost (XGB) were compared in terms of predictive accuracy, uncertainty, and robustness. Our results demonstrate that ET outperformed other models with an average correlation coefficient of 0.674, $R^2$ of 0.426 and the lowest RMSE of 6.859 cm and MAE of 5.361 cm, while also showing the lowest uncertainty (5.07%). The proposed ML framework includes an extensive model evaluation pipeline that incorporates the Performance Index (PI), ANOVA, and feature importance analysis, providing a multidimensional perspective on model behavior. The most influential features for PH prediction were the number of stems (NS) and insertion of the first pod (IFP). This research highlights the viability of integrating explainable ML techniques into agricultural decision support systems, enabling data-driven strategies for cultivar evaluation and phenotypic trait forecasting. Full article

This study develops an interpretable and calibrated XGBoost framework for probabilistic slope stability assessment using a 627-case database of circular-mode failures. Six predictors, namely, unit weight (γ), cohesion (c), friction angle (φ), slope angle (β), slope height (H), and pore-pressure ratio (r_u), were used to train a gradient-boosted tree model optimized through Bayesian hyperparameter search with five-fold stratified cross-validation. Physically based monotone constraints ensured that failure probability (P_f) decreases as c and φ increase and increases with β, H, and r_u. The final model achieved strong performance (AUC = 0.88, Accuracy = 0.80, MCC = 0.61) and reliable calibration, confirmed by a Brier score of 0.14 and ECE/MCE of 0.10/0.19. A 1000-iteration bootstrap quantified both epistemic and aleatoric uncertainties, providing 95% confidence bands for P_f-feature curves. SHAP analysis validated physically consistent influence rankings (φ > H ≈ c > β > γ > r_u). Predicted probabilities were classified into Low (P_f < 0.01), Medium (0.01 ≤ P_f ≤ 0.10), and High (P_f > 0.10) risk levels according to geotechnical reliability practices. The proposed framework integrates calibration, uncertainty quantification, and interpretability into a comprehensive, auditable workflow, supporting transparent and risk-informed slope management for infrastructure, mining, and renewable energy projects. Full article

With the expansion of offshore and subsea infrastructure in Arctic and sub-Arctic regions, concerns are rising, driven by climate change and global warming, over the risk of drifting icebergs colliding with these structures in cold waters. Traditional methods for estimating iceberg underwater height and assessing subgouge soil properties, such as costly and time-consuming underwater surveys or centrifuge tests, are still used, but the industry continues to seek faster and more cost-efficient solutions. In this study, the extra tree regression (ETR) algorithm was employed for the first time to simultaneously model iceberg drafts and subgouge soil properties in both sandy and clay seabeds. The ETR approach first predicted the iceberg draft, then simulated subgouge soil reaction forces and deformations. A total of 22 ETR models were developed, incorporating parameters relevant to both iceberg draft estimation and subgouge soil characterization. The best-performing ETR models, along with the most influential input variables, were identified through a combination of sensitivity, error, discrepancy, and uncertainty analyses. The ETR model predicted iceberg draft with a high level of accuracy (R = 0.920, RMSE = 1.081), while the superior model for vertical reaction force in sand achieved an RMSE of 43.95 with 70% of predictions within 16% error. The methodology demonstrated improved prediction capacity over traditional techniques and can serve early-stage iceberg risk management. Full article

Forest volume is an important information for assessing the economic value and carbon sequestration capacity of forest resources and serves as a key indicator for energy flow and biodiversity. Although remote sensing technology is applied to estimate volume, optical remote sensing data have limitations in capturing forest vertical height information and may suffer from reflectance saturation. While LiDAR data can provide more detailed vertical structural information, they come with high processing costs and limited observation range. Therefore, improving the accuracy of volume estimation through multi-source data fusion has become a crucial challenge and research focus in the field of forest remote sensing. In this study, we integrated Sentinel-2 multispectral data, Resource-3 stereoscopic imagery, UAV-based LiDAR data, and field survey data to quantitatively estimate the forest volume in Saihanwula Nature Reserve, located in Inner Mongolia, China, on the southern part of Daxing’anling Mountains. The study evaluated the performance of multi-source remote sensing features by using recursive feature elimination (RFE) to select the most relevant factors and applied four machine learning models—multiple linear regression (MLR), k-nearest neighbors (kNN), random forest (RF), and gradient boosting regression tree (GBRT)—to develop volume estimation models. The evaluation metrics include the coefficient of determination (R²), root mean square error (RMSE), and relative root mean square error (rRMSE). The results show that (1) forest Canopy Height Model (CHM) data were strongly correlated with forest volume, helping to alleviate the reflectance saturation issues inherent in spectral texture data. The fusion of CHM and spectral data resulted in an improved volume estimation model with R² = 0.75 and RMSE = 8.16 m³/hm², highlighting the importance of integrating multi-source canopy height information for more accurate volume estimation. (2) Volume estimation accuracy varied across different tree species. For Betula platyphylla, we obtained R² = 0.71 and RMSE = 6.96 m³/hm²; for Quercus mongolica, R² = 0.74 and RMSE = 6.90 m³/hm²; and for Populus davidiana, R² = 0.51 and RMSE = 9.29 m³/hm². The total forest volume in the Saihanwula Reserve ranges from 50 to 110 m³/hm². (3) Among the four machine learning models, GBRT consistently outperformed others in all evaluation metrics, achieving the highest R² of 0.86, lowest RMSE of 9.69 m³/hm², and lowest rRMSE of 24.57%, suggesting its potential for forest biomass estimation. In conclusion, accurate estimation of forest volume is critical for evaluating forest management practices and timber resources. While this integrated approach shows promise, its operational application requires further external validation and uncertainty analysis to support policy-relevant decisions. The integration of multi-source remote sensing data provides valuable support for forest resource accounting, economic value assessment, and monitoring dynamic changes in forest ecosystems. Full article

Forest trees have emerged as a promising passive solution for mitigating low-frequency ground vibrations generated by railway operations, offering ecological and cost-effective advantages. This study proposes a three-dimensional semi-analytical method developed for evaluating the dynamic responses of the coupled track–ground–tree system. The thin-layer method is employed to derive an explicit Green’s function corresponding to a har-monic point load acting on a layered half-space, which is subsequently applied to couple the foundation with the track system. The forest trees are modeled as surface oscillators coupled on the ground surface to evaluate the characteristics of multiple scattered wavefields. The vibration attenuation capacity of forest trees in mitigating railway-induced ground vibrations is systematically investigated using the proposed method. In the direction perpendicular to the track on the ground surface, a graded array of forest trees with varying heights is capable of forming a broad mitigation frequency band below 80 Hz. Due to the interaction of wave fields excited by harmonic point loads at multiple locations, the attenuation performance of the tree system varies significantly across different positions on the surface. The influence of variability in tree height, radius, and density on system performance is subsequently examined using a Monte Carlo simulation. Despite the inherent randomness in tree characteristics, the forest still demonstrates notable attenuation effectiveness at frequencies below 80 Hz. Among the considered parameters, variations in tree height exert the most pronounced effect on the uncertainty of attenuation performance, followed sequentially by variations in density and radius. Full article

In the process of plant protection for fruit trees using rotary-wing UAVs, challenges such as droplet drift, insufficient canopy penetration, and low agrochemical utilization efficiency remain prominent. Among these, the uncertainty in the spatio-temporal distribution of downwash airflow is a key factor contributing to non-uniform droplet deposition and increased drift. To address this issue, we developed a wind field numerical simulation model based on an improved hierarchical leaf density model to clarify the spatio-temporal characteristics of downwash airflow, the scale of turbulence regions, and their effects on internal canopy airflow under varying flight altitudes and different rotor speeds. Field experiments were conducted in orchards to validate the accuracy of the model. Simulation results showed that the average error between the simulated and measured wind speeds inside the canopy was 8.4%, representing a 42.11% reduction compared to the non-hierarchical model and significantly improving the prediction accuracy. The coefficient of variation (CV) was 0.26 in the middle canopy layer and 0.29 in the lower layer, indicating a decreasing trend with an increasing canopy height. We systematically analyzed the variation in turbulence region scales under different flight conditions. This study provides theoretical support for optimizing UAV operation parameters to improve droplet deposition uniformity and enhance agrochemical utilization efficiency. Full article

Soil texture, defined by the proportions of sand, silt, and clay particles in the soil, is one of the most essential physical properties of soil. High-resolution soil texture data can provide critical parameter support for soil hydrological modeling, agricultural production management, and ecosystem assessment. In digital soil mapping, previous studies often predicted the sand, silt, and clay contents in soil and then indirectly calculated soil texture. Currently, approaches that directly map soil texture by classification modeling are gaining increasing attention due to the decreased error from data conversion, but few studies have systematically compared these two methods yet. In this study, we comprehensively assessed the performance of direct and indirect predicting soil texture using four machine learning algorithms (e.g., extreme gradient boosting, random forest, gradient boosting decision tree, and extremely randomized tree) with 190 covariates from the Digital Elevation Model, Sentinel-1/2 satellite images, and classification maps and generated a 10 m resolution soil texture map based on 405 topsoil (0–20 cm) sample data collected in Suichuan County, China. The results showed that compared with indirect predictions, direct predictions improved overall accuracy (OA) by 20.57–44.19% and the Kappa coefficient (Kappa) by 0.220–0.402. Among the models used, the XGB model achieved the highest accuracy (OA: 0.948; Kappa: 0.931) and the lowest uncertainty (confusion index: 0.052). The direct prediction map (nine classes recorded) exhibited more detailed and diverse spatial distribution patterns than the indirect prediction map (six classes recorded), aligning better with the actual environment. Based on accuracy validation and spatial distribution, the performance of the XGB model was best during direct prediction. The Shapley additive explanation from the XGB model revealed that the normalized height and stream power indices were the most significant factors driving the soil texture in the study area. Our results provide a reference for future studies on soil texture mapping using machine learning models. Full article

Forests are invaluable natural resources that provide essential ecosystem services, and their carbon storage capacity is critical for climate mitigation efforts. Quantifying this capacity would require accurate estimation of forest structural attributes for deriving their aboveground biomass (AGB). Traditional field measurements, while precise, are labor-intensive and often spatially limited. Handheld Mobile Laser Scanning (HMLS) offers a rapid alternative for building forest inventories; however, its effectiveness and accuracy in diverse subtropical forests with complex canopy structure remain under-investigated. In this study, we employed both HMLS and traditional surveys within structurally complex subtropical forest plots, including old-growth forests (Fung Shui Woods) and secondary forests. These forests are characterized by dense understories with abundant shrubs and lianas, as well as high stem density, which pose challenges in Light Detection and Ranging (LiDAR) point cloud data processing. We assessed tree detection rates and extracted tree attributes, including diameter at breast height (DBH) and canopy height. Additionally, we compared tree-level and plot-level AGB estimates using allometric equations. Our findings indicate that HMLS successfully detected over 90% of trees in both forest types and precisely measured DBH (R² > 0.96), although tree height detection exhibited relatively higher uncertainty (R² > 0.35). The AGB estimates derived from HMLS were comparable to those obtained from traditional field measurements. By producing highly accurate estimates of tree attributes, HMLS demonstrates its potential as an effective and non-destructive method for rapid forest inventory and AGB estimation in subtropical forests, making it a competitive option for aiding carbon storage estimations in complex forest environments. Full article

Stem volume is a critical factor in managing and evaluating forest resources. At present, stem volume is commonly estimated indirectly by constructing a taper model that utilizes sampling, diameter at breast height (DBH), and tree height. However, these estimates are constrained by errors arising from spatial and stand environment variations as well as uncertainties in height measurements. To address these issues, this study aimed to accurately estimate stem volume using light detection and ranging (LiDAR) technology, a key tool in modern precision forestry. LiDAR data were used to build comprehensive three-dimensional models of forests with multi-platform LiDAR systems. This approach allowed for precise measurements of tree heights and stem diameters at various heights, effectively mitigating the limitations of earlier measurement methods. Based on these data, a Kozak taper curve was developed at the individual tree level using LiDAR-derived tree height and diameter estimates. Integrating this curve with LiDAR data enabled a hybrid approach to estimating stem volume, facilitating the calculation of diameters at points not directly identifiable from LiDAR data alone. The proposed method was implemented and evaluated for two economically significant tree species in Korea: Pinus koraiensis and Larix kaempferi. The RMSE comparison between the taper curve-based approach and the hybrid volume estimation method showed that, for Pinus koraiensis, the RMSE was 0.11 m³ using the taper curve-based approach and 0.07 m³ for the hybrid method, while for Larix kaempferi, the RMSE was 0.13 m³ and 0.05 m³, respectively. The estimation error of the hybrid method was approximately half that of the taper curve-based approach. Consequently, the hybrid volume estimation method, which integrates LiDAR and the taper model, overcomes the limitations of conventional taper curve-based approaches and contributes to improving the accuracy of forest resource monitoring. Full article

The relationship between coronary heart disease (CHD) and complex urban built environments remains a subject of considerable uncertainty. The development of predictive models via machine learning to explore the underlying mechanisms of this association, as well as the formulation of intervention policies and planning strategies, has emerged as a pivotal area of research. A cross-sectional dataset of hospital admissions for CHD over the course of a year from a hospital in Dalian City, China, was assembled and matched with multi-source built environment data via residential addresses. This study evaluates five machine learning models, including decision tree (DT), random forest (RF), eXtreme gradient boosting (XGBoost), multi-layer perceptron (MLP), and support vector machine (SVM), and compares them with multiple linear regression models. The results show that DT, RF, and XGBoost exhibit superior predictive capabilities, with all R² values exceeding 0.70. The DT model performed the best, with an R² value of 0.818, and the best performance was based on metrics such as MAE and MSE. Additionally, using explainable AI techniques, this study reveals the contribution of different built environment factors to CHD and identifies the significant factors influencing CHD in cold regions, ranked as age, Digital Elevation Model (DEM), house price (HP), sky view factor (SVF), and interaction factors. Stratified analyses by age and gender show variations in the influencing factors for different groups: for those under 60 years old, Road Density is the most influential factor; for the 61–70 age group, house price is the top factor; for the 71–80 age group, age is the most significant factor; for those over 81 years old, building height is the leading factor; in males, GDP is the most influential factor; and in females, age is the most influential factor. This study explores the feasibility and performance of machine learning in predicting CHD risk in the built environment of cold regions and provides a comprehensive methodology and workflow for predicting cardiovascular disease risk based on refined neighborhood-level built environment factors, offering scientific support for the construction of sustainable healthy cities. Full article

Phenological changes in forests directly influence the spatiotemporal dynamics of carbon fixation and the carbon and water cycles in terrestrial ecosystems. Previous studies have shown that variations in biological factors (e.g., canopy height, leaf area, water use efficiency) can increase uncertainty in forest phenology, and these variations are closely linked to tree species and forest age-class structure. However, the interaction mechanisms through which tree species and forest age-class structure influence phenological changes remain insufficiently explored. In this study, phenological changes and their interactions and response mechanisms to different dominant tree species and forest age-class structures were analyzed via Sentinel-2 normalized difference vegetation index (NDVI) time series data from 2020 and 2021 across 480 typical deciduous forest plots in northeastern China. The results were as follows: (1) There were significant differences (p < 0.05) in the intra-annual phenological responses of temperate deciduous landscapes to the interaction between tree species and forest age-class structure. (2) The indirect effect of forest age-class structure through tree species on phenology exceeded the indirect effect of tree species through forest age-class structure, with a difference of 30.77%–35.09%. (3) When the dominant tree species and forest age-class structure were not distinguished, phenological differences in temperate forests ranged from 3 to 41 days and 2 to 23 days, respectively. This study highlights the differential impacts of key biological factors and their interactions on regional forest phenology, offering valuable insights into how these factors influence forest landscapes and providing a theoretical basis for improving forest management strategies. Full article