Search Results (241)

The Yellow River Basin contains abundant coal resources; however, its ecological environment is inherently fragile, and vegetation degradation has been further intensified by extensive mining activities. Accurate classification of individual tree species in mining-affected areas is therefore essential for assessing ecological conditions and establishing a scientific foundation for targeted restoration and sustainable management. To address this need, an evaluated machine learning framework was developed and evaluated for individual tree species classification in a coal mining area of the Yellow River Basin using integrated unmanned aerial vehicle (UAV) data. A comprehensive feature set was constructed by extracting 278 attributes per tree. These attributes included 224 spectral bands and 29 hyperspectral indices derived from hyperspectral imagery, 24 textural metrics obtained from RGB orthophotos, and one canopy height feature generated from a LiDAR-derived model. Based on ground-truth data from 1095 individual trees, seven machine learning algorithms were trained and systematically compared: Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Decision Tree (DT), Gradient Boosting (GB), Logistic Regression (LR), and XGBoost. Statistical significance testing using 5 × 5 repeated cross-validation, together with the Friedman test and post hoc Nemenyi test, and additional model stability analysis consistently identified XGBoost as the optimal classifier. On an independent test set, XGBoost achieved high accuracy (Overall Accuracy = 0.897, Kappa = 0.811) with an efficient training time of 2.36 s. Further analysis demonstrated the critical and complementary roles of hyperspectral and structural features in species discrimination. The optimized model was subsequently applied to generate a detailed wall-to-wall tree species map across the entire mining area. Overall, this study presents a statistically informed comparison of classifiers for multi-source feature-based species discrimination and delivers an evaluated and practical pipeline for effective vegetation monitoring. The proposed framework provides a scientific tool for assessing and managing ecological recovery in complex mining environments, particularly within ecologically sensitive regions such as the Yellow River Basin. Full article

Integrating existing tree-level information into harvester operator decision-making can significantly enhance precision forest management, particularly with respect to biodiversity preservation and climate-smart adaptation. During harvester operations, a primary challenge lies in positioning the machine with sufficient accuracy in real time to relate a priori individual-tree-level reference information to the operator. We propose a lightweight procedure using tree-to-tree matching to continuously register a real-time tree map collected from a harvester (or another mobile laser scanning system) to a precomputed reference map derived from an airborne laser scanner (ALS). We assess the robustness of the method using simulated tree maps and validate its real-world performance in experiments using a LiDAR-equipped harvester performing a thinning operation in a boreal forest. In simulations, registration was found to be robust up to a moderate tree density of approximately 1700 ha⁻¹, even when using a reference map with a lower positional accuracy and higher error rates than in our harvester experiments. Using real-world data from the thinning operation, the registration method was demonstrated to successfully mitigate meter-scale positioning drifts remaining in the LiDAR-inertial trajectory. After the continuous registration procedure, the positioning error was reduced to the level of 0.5 m, constrained by the accuracy of the prior map derived from sparse ALS data with ∼5 transmissions/m². Importantly, the registration procedure was shown to update in real time (at most 20 ms update time for stands with densities of at most 2000 ha⁻¹, after an initial computational phase. Notable features of the registration procedure are its low memory consumption, fast runtime and capacity to accurately position the harvester despite LiDAR-inertial positioning drift. While these results demonstrate the potential for real-time operation, full implementation requires the development of real-time tree detection and estimation of tree attributes. Full article

Genetic diversity is fundamental for the conservation and sustainable utilization of plant species. Triadica cochinchinensis, a tree species native to southern China, is an important ornamental and nectar-producing plant with considerable economic value. However, the levels of genetic diversity and the patterns of population differentiation across its natural populations remain unexplored. Here, we developed 24 highly polymorphic SSR markers and used them to assess the genetic diversity and differentiation among 280 individuals collected from 10 natural populations of T. cochinchinensis. The results showed that the average expected heterozygosity (He) revealed by the SSR markers was 0.774, and the average Shannon diversity index (I) was 1.660, indicating a high level of genetic diversity at the species level of T. cochinchinensis. Analysis using SSR markers revealed a low average observed heterozygosity (Ho = 0.323) and a relatively high average inbreeding coefficient within populations (F = 0.466). These findings suggest that inbreeding is likely occurring, which may contribute to a loss of heterozygosity within the studied populations. Notably, not all populations had high genetic diversity. For example, the He of SC2 population (0.490), QY population (0.568), and SC1 population (0.585) were all below the mean He (0.607), suggesting that attention should be given to protecting populations with low genetic diversity. The results further showed that the average genetic differentiation coefficient (F_ST) between populations was 0.094, and the average gene flow (Nm) was 2.278, indicating that the natural populations of T. cochinchinensis had low genetic differentiation and relatively high gene flow. AMOVA indicated that 74% of the total variation was distributed within populations. Notably, populations SC1 and SC2 exhibited higher genetic differentiation from all others (F_ST > 0.1), which is likely attributed to mountain barriers restricting gene flow. Therefore, it is recommended to enhance in situ conservation efforts while also facilitating assisted gene flow, such as through artificial introduction. For the first time, this study reveals the genetic information of natural populations of T. cochinchinensis at the molecular level, thereby offering a valuable reference for the conservation and utilization of its germplasm resources. Full article

Artificial intelligence (AI), cloud computing, robotics, automation, and remote sensing technologies are all contributing to digital transformation in forestry. Improving on low-accuracy Global Navigation Satellite Systems (GNSS) positioning affected by multipath error and interception under forest canopies is critical for integrating smart and digital technologies into equipment in forest operations. In an era where lidar-derived individual tree locations are now increasingly available in digital forest inventories, a possible alternative approach to positioning resources such as people or equipment accurately could be to match locally-measured tree positions and attributes in the forest with an existing global reference map based on prior remote sensing missions, effectively using the trees themselves as satellites to circumvent the need for GNSS-based positioning. We evaluated a lidar-based alternative to GNSS positioning using predicted tree positions from local terrestrial laser scanning (TLS) matched with a global stem map derived from prior airborne laser scanning (ALS), a methodology we refer to as TreePS. The horizontal error of the TreePS system was estimated using 154 permanent single-tree inventory plots on the University of Idaho Experimental Forest with two different workflows based on two common R packages (lidR v. 4.3.0, FORTLS v. 1.6.2) using either spatial coordinates or spatial plus stem DBH predicted using one or both segmentation routines and a custom matching algorithm. Mean TreePS error using lidR for below and above-canopy segmentation had mean error of 1.04 and 2.04 m with 93.5% and 91.6% of plots with viable match solutions on spatial and spatial plus DBH matching. The second workflow with both FORTLS (TLS point cloud) and lidR (ALS point cloud) had errors of 1.09 and 2.67 m but only 57.9% and 54.2% of plots with solutions using spatial and spatial plus DBH, respectively. There is room for improvement in the matching algorithm but the TreePS methodology and similar feature-matching solutions may be useful for below-canopy positioning of equipment, people or other resources under dense forests and other GNSS-degraded environments to help advance smart and digital forestry. Full article

Extreme drought events are increasingly destabilizing European lowland oak forests, yet within-stand variation in drought legacy effects remains poorly characterized. This study integrates UAV-LiDAR canopy structural analysis with a 68-year dendrochronological record (1952–2019) to examine divergent radial growth responses to the 2012 extreme drought in Turkey oak (Quercus cerris L.) forests of Vojvodina, northern Serbia. LiDAR scanning (Wingtra Gen II, 90 m altitude, spring 2024) enabled objective classification of 180 increment cores from 90 trees across four 5–7 ha experimental plots into two structural zones: a preserved-structure zone (PS; gap fraction ≤ 10%) and a disturbed-structure zone (DS; gap fraction > 10%). Ring width index (RWI) chronologies were developed using the modified negative exponential function and analyzed with linear mixed-effects models (LMMs) incorporating AR(1) temporal autocorrelation. Lloret resilience indices (a reference window of seven years) were computed per individual tree and compared between zones using Mann–Whitney U tests with Bonferroni correction. The key finding is a statistically significant zone × period interaction in all four plots (p = 0.0009–0.033): DS zone trees exhibited a marked post-drought RWI increase (mean +0.22–0.36 units; t-test p < 0.0001 in all plots), while PS zone trees showed no significant post-drought change (p = 0.147–0.258). Pooled Lloret analysis revealed significantly higher recovery (Rt: DS median = 1.693 vs. PS = 1.237; U = 1633, p < 0.0001, r = 0.532) and resilience (Rs: DS = 1.232 vs. PS = 0.932; U = 1574, p < 0.0001, r = 0.482), while resistance (Rc) did not differ between zones (p = 0.569), indicating that DS zone trees were equally susceptible to the drought but recovered far more strongly. The equivalence of Rc between zones critically implies that divergent post-drought trajectories cannot be attributed to differential drought tolerance but instead reflect a structural mechanism operating exclusively in the post-drought period. These results are consistent with a competition release mechanism: drought-induced canopy gap formation in DS zones reduced inter-tree competition for surviving trees, enabling accelerated radial growth recovery. Full article

Diabetes mellitus is a chronic condition that frequently leads to severe complications that are difficult to detect in their early stages using conventional clinical monitoring. This paper presents a data-driven framework for predicting multiple diabetes-related complications using structured electronic health record data while ensuring clinically meaningful explainability. The proposed approach adapts a pretrained electronic health record foundation model to operate on static patient data and integrates it with classical machine learning baselines to address class imbalance, feature sparsity, and interpretability challenges. A multi-label prediction setting covering eight common diabetes complications is evaluated using a real-world dataset from a regional diabetes center in the United Arab Emirates. Synthetic data generation and clinical constraint enforcement are applied to improve robustness for underrepresented outcomes, while feature selection is guided by model importance and attribution-based explanations. The best-performing configuration, a weighted ensemble combining a low-rank adapted Hyena-based foundation model with a tree-based predictor, achieved an average F1-score of 0.77, an average recall of 0.85, and an example-based F1-score of 0.71, outperforming all individual models. In addition, this ensemble produced the most stable explanations under input perturbations, indicating improved consistency of dominant clinical risk drivers. These results demonstrate that explainable foundation model-based ensembles can deliver accurate, robust, and clinically transparent risk prediction for diabetes complications. Full article

On university campuses, trees and green spaces shape how students and staff move and use outdoor spaces. To support planning, tree species information is needed at the level of individual trees. Tree species classification from UAV RGB imagery remains difficult in complex campus scenes because roads, buildings, shadows and subtle inter species differences degrade recognition. To address background interference, the loss of subtle fine-grained cues before tokenization, and insufficient local structure modeling in lightweight transformer-based classification, we propose TreeSpecViT for tree species classification. It uses a MobileViT backbone and a Background Suppression Module (BSM) to reduce clutter from non-canopy regions. A Fine-Grained Feature Guidance (FGF) module is inserted before the unfold operation to enhance canopy details and guide tokenization toward key regions. $1\times 1$ convolutional neck layers align channels, and a Global and Local Fusion (GLF) module jointly models overall crown semantics and local textures for species recognition. From the predicted masks and species labels, we build an individual tree digital archive. The archive stores per tree geometric attributes and can be linked with grids of campus activity intensity to analyze how activity patterns relate to vegetation structure. TreeSpecViT achieves an Accuracy of 87.88% (+6.06%) and an F1 score of 76.48% (+5.08%) on the SZUTreeDataset. On our self constructed NJFUDataset, it reaches 76.30% (+5.10%) in Accuracy and 70.10% (+7.20%) in F1. These results surpass mainstream models. Ablation experiments show that the modules jointly reduce background clutter and enhance canopy features. Overall, TreeSpecViT supports campus scale analyses that link human activity intensity to vegetation patterns and provides a practical basis for planning and adjusting campus green spaces. Full article

Rising temperatures and droughts are triggering forest die-off in climate warming hotspots such as the Mediterranean Basin. UAVs equipped with LiDAR and multispectral sensors offer a powerful tool for surveys of tree vigor at landscape level. We used UAV-acquired LiDAR data and multispectral camera imagery to segment individual tree crowns, classify species, and assess the health status in two drought-affected forests in northeastern Spain: a mixed Pinus pinaster–Quercus ilex forest and a Pinus halepensis forest. Individual trees were segmented and classified using object-based image analysis with the Random Forest algorithm incorporating spectral, structural, and topographic variables. Greenness indices (NDVI and EVI) were analyzed in relation to crown height, topography (slope and elevation) and solar radiation, and their interactions. Analyses showed satisfactory crown segmentation (F-Score = 0.85–0.86) and species classification (Overall accuracy = 0.86–0.99), though distinguishing spectrally similar classes remained challenging. Taller P. pinaster trees exhibited higher NDVI, while taller P. halepensis displayed higher NDVI values in dense neighborhoods and on gentle slopes. These findings highlight the potential of high-resolution UAV-based remote sensing for effective near-real-time detection and attribution of forest die-off. Future research should aim to improve algorithm accuracy and better integrate field-based validation across different forest types. Full article

Amazonian large trees act as central elements of forest ecosystems, storing a disproportionate fraction of aboveground biomass. However, these trees are not randomly distributed across the landscape, and it is expected that edaphic attributes influence floristic composition, forest structure, and vegetation biomass. In this study, we investigated how variation in soil chemical and physical properties affects the diversity and biomass of large trees. Forest inventories were conducted at five sites within protected areas in the states of Pará and Amapá. Aboveground biomass was estimated using allometric equations, while soil samples were analyzed for their physical and chemical properties. Diversity indices, rarefaction, Redundancy Analysis, and Generalized Additive Models were applied. Edaphic variables such as soil pH, organic matter, phosphorus, and aluminum were associated with floristic composition and the biomass of these individuals. Trees with a diameter at breast height greater than or equal to 70 cm accounted for up to 80% of total biomass, revealing a pattern of biomass hyperdominance. The results indicate that the occurrence of large trees is related to edaphic and structural attributes, such as tree density and size distribution, suggesting that these individuals are not randomly distributed along soil gradients. Understanding these patterns is essential for improving ecological models, biomass extrapolations, and management strategies aimed at conserving the Amazon rainforest. Full article

The proliferation of high-spatial-resolution remote sensing data is transforming forest attribute estimation, replacing traditional manual approaches with deep learning-based Individual Tree Crown Delineation (ITCD). Nevertheless, accurate ITCD boundary extraction from aerial RGB imagery faces persistent challenges: boundary ambiguity from complex crown occlusion in mixed forests, scarcity of high-quality annotations, and computational limitations of existing methods in dense forests. The latter manifests particularly in overlapping crown scenarios through constrained receptive fields, leading to substantial parameter requirements, computational inefficiency, and compromised accuracy. To overcome these limitations, we propose CrownViM, a novel architecture based on a bidirectional State Space Model (SSM). The framework integrates a linear-complexity Context Clustering Vision Mamba (CCViM) encoder for efficient global context modeling and employs a MaskFormer decoder for precise boundary prediction. We further introduce a partial-supervision loss function to reduce dependence on exhaustively annotated crown masks. Evaluations on OAM-TCD and the single-tree segmentation dataset (SSD) show CrownViM achieves significant segmentation accuracy improvements while maintaining a lightweight profile (39.6 M parameters). It substantially outperforms Convolutional Neural Network (CNN), Vision Transformer (ViT), and hybrid-based baselines when processing overlapping crowns and structurally complex scenes. As the first implementation of state space models in ITCD, CrownViM effectively addresses core limitations in global context capture, computational efficiency, and boundary definition. Our efficient architecture and sparse-annotation loss strategy enable high-accuracy, robust individual tree mapping, advancing tools for large-scale forest monitoring and accurate carbon stock quantification. Full article

Growing interest in natural therapies has increased the demand for essential oils; however, the complex interactions within their mixtures that dictate their final efficacy remain poorly understood. This study aimed to optimize a blend of ginger, cinnamon, tea tree, and geranium essential oils to develop an active ingredient, with synergistic multifunctional bioactivities, that was relevant to cutaneous healing. Initially, the composition and cytotoxicity for individual oils were determined; subsequently, a D-optimal mixture design was employed to evaluate three biological responses related to skin recovery: ultraviolet B radiation absorption, red blood cell lysis inhibition, and catalase enzyme activity. GC-FID analysis revealed the following major components (% w/w): cinnamon (cinnamaldehyde, 77.56%), ginger (α-zingiberene, 33.77%), geranium (citronellol, 33.6%), and tea tree (terpinen-4-ol, 38.38%). Dose–response data from essential oils tested against Detroit ATCC 551 skin fibroblasts revealed a clear cytotoxic hierarchy (IC₅₀ µg/mL): cinnamon (21.03) > ginger (25.3) > tea tree (41.67) > geranium (92.51). Cinnamaldehyde content was the primary contributor to photoprotective capacity, with a maximum sun protection factor (SPF) of 4.5. Inhibition against erythrocyte membrane lysis was not attributable to a single component; maximum protection (98.4%) was achieved through synergy between oxygenated monoterpenoids (geranium and tea tree), sesquiterpenes (ginger), and aromatic aldehydes (cinnamon). Highest catalase activity (160.86 kU/g Hb) was reached in mixtures with high cinnamaldehyde and eugenol contents, whereas an antagonistic effect was observed between tea tree and geranium oils. Finally, an optimal formulation (desirability = 0.927) was identified (% w/w): 31.7% ginger, 39.1% cinnamon, 14.5% tea tree, and 14.7% geranium. Experimental validation confirmed no significant difference compared with developed predictive models. This optimized mixture constitutes a bioactive natural component with potential for use in products aimed at promoting skin health, warranting further investigation into direct models of skin healing. Full article

Rare event detection in large tabular data remains a computationally challenging problem due to class imbalance, heterogeneous feature distributions, and unstable thresholds. Traditional machine learning approaches based on individual models and fixed thresholds often exhibit limited robustness and reproducibility in such settings. This paper proposes a hybrid ensemble framework for rare event detection that integrates heterogeneous machine learning models through threshold-aware probabilistic aggregation. The framework combines gradient-boosted decision trees, regularized linear models, and neural networks, leveraging their complementary inductive biases. To ensure reproducibility and robust performance evaluation under severe class imbalance, a leaky-controlled evaluation protocol is employed, including rootwise summation, probability calibration, and validation-based threshold optimization. The proposed approach is evaluated on a large tabular dataset containing approximately 50,000 observations. Experimental results demonstrate improved rare event detection and robust generalization performance compared to individual baseline models. Explainability is achieved through Shapley Additive Explanations (SHAP)-based attribution analysis and clustering in the explanation space, enabling transparent analysis of ensemble decision-making behavior. The proposed framework represents a general-purpose computational solution for rare event detection and can be applied to a wide range of data-driven decision-making and anomaly detection problems. Full article

Local Differential Privacy (LDP) and its personalized variants (PLDP) have been widely used for privacy-preserving data analytics. However, existing schemes often enforce a uniform indistinguishability level among users, failing to accommodate the nuanced privacy needs of diverse individuals. To address this, we propose User-Distinguished Local Differential Privacy (UDPLDP), a novel framework that formalizes user-level distinguishability to support more flexible, non-uniform privacy budgets. Under this framework, we tackle the fundamental task of frequency range queries, namely UDPLDP-Tree, which overcomes the challenge due to limited user-level distinguishability, insufficient robustness in estimation under complex data distributions, and the assumption of uniform privacy requirements across different attributes in existing multi-dimensional schemes. To demonstrate the effectiveness, we conduct extensive experiments and the results show that UDPLDP-Tree reduces the mean squared error (MSE) by about 30–50% compared with a recent state-of-the-art baseline. Full article

The genetic diversity and population structure of five tapertail anchovy (Coilia nasus) populations—four wild populations from the Yangtze River (Taizhou, Anqing, Shanghai, Hukou) and one cultured population from Yangzhong—were analyzed using 18 highly polymorphic microsatellite loci. All loci exhibited high polymorphism, with genetic parameters as follows: mean number of alleles = 20.567, expected heterozygosity = 13.506, Shannon information index = 2.743, and polymorphic information content = 0.9624. F-statistics ranged from 0.02898 to 0.05714, indicating varying degrees of genetic differentiation between all populations. Analysis of molecular variance revealed that 4% of the total genetic variation was attributable to differences among populations, 23% to variation among individuals within populations, and 73% to within-individual genetic variation. A UPGMA phylogenetic tree based on Nei’s genetic distance showed that the Shanghai population clustered first with Anqing, followed by Taizhou, Hukou, and finally Yangzhong. Additionally, discriminant functions developed from microsatellite data enabled accurate population assignment for all individuals. These findings provide critical insights into the genetic relationships and structure of C. nasus populations, offering valuable implications for their conservation and management. Full article

Vitellaria paradoxa subsp. paradoxa C.F.Gaertn., is one of the most important components of sub-Saharan agroforestry systems, providing to rural communities, especially women, with socio- economic, environmental, and nutritional benefits. Despite its importance, the species is threatened and remains semi-domesticated. To better preserve and improve this resource, the genetic diversity and structure of 88 mother trees originated from Senegal and Burkina Faso were studied by analysing 17 phenotypic traits and 3196 SNP markers. The results revealed similar level of observed heterozygosity (Ho) between the Senegalese and Burkinabe populations (Ho = 0.16), whereas the average number of alleles per population (Na) and the expected heterozygosity (He) ranged from 0.33 to 0.34 and 0.38 to 0.39, respectively, indicating moderate to low genetic diversity. Furthermore, the polymorphic information content ranged from 0.15 for Senegal to 0.25 for Burkina Faso. Both ADMIXTURE and cluster analysis delineated our collection into two groups depending on the origin. The AMOVA showed that the highest fraction of variation was within individual, indicating a very low genetic differentiation (Fst = 0.0006) between population. At the phenotypic level, the G2 cluster representing the Senegalese genepool recorded the highest performance in terms of nut and kernel attributes, cariten and unsaponifiable matters contents, while higher crude fat, Diglyceride, Triglyceride, and Triacylglycerol Mono Stearoyl Olein Stearin contents were observed in the Burkina Faso collection (G1). The present findings on the species’ genetic diversity and genetic structure constitute a good start to strengthen the species tree improvement and conservation programs. Full article