Search Results (5,673)

The rapid detection and confirmation of Suspicious Regions of Forest Fire (SRoFF) are critical for timely alerts and firefighting operations. In the early stages of forest fires, small flames and heavy occlusion lead to low accuracy, false detections, omissions, and slow inference in existing target-detection algorithms. We constructed the Suspicious Regions of Forest Fire Dataset (SRFFD), comprising publicly available datasets, relevant images collected from online searches, and images generated through various image enhancement techniques. The SRFFD contains a total of 64,584 images. In terms of effectiveness, the individual augmentation techniques rank as follows (in descending order): HSV (Hue Saturation and Value) random enhancement, copy-paste augmentation, and affine transformation. A detection model named SRoFF-Yolover is proposed for identifying suspicious regions of forest fire, based on the YOLOv8. An embedding layer that effectively integrates seasonal and temporal information into the image enhances the prediction accuracy of the SRoFF-Yolover. The SRoFF-Yolover enhances YOLOv8 by (1) adopting dilated convolutions in the Backbone to enlarge feature map receptive fields; (2) incorporating the Convolutional Block Attention Module (CBAM) prior to the Neck’s C2fLayer for small-target attention; and (3) reconfiguring the Backbone-Neck linkage via P2, P4, and SPPF. Compared with the baseline model (YOLOv8s), the SRoFF-Yolover achieves an 18.1% improvement in mAP@0.5, a 4.6% increase in Frames Per Second (FPS), a 2.6% reduction in Giga Floating-Point Operations (GFLOPs), and a 3.2% decrease in the total number of model parameters (#Params). The SRoFF-Yolover can effectively detect suspicious regions of forest fire, particularly during winter nights. Experiments demonstrated that the detection accuracy of the SRoFF-Yolover for suspicious regions of forest fire is higher at night than during daytime in the same season. Full article

Tea is a prominent cash crop in global agriculture, and it is Sri Lanka’s top agricultural export known as ‘Ceylon Tea,’ employing nearly one million people, with land covering an area of 267,000 ha. However, over the past decade, many tea lands in Sri Lanka have been abandoned, leading to a gradual decline in production. This research aims to identify, map, and verify tea land abandonment over time and space by identifying and analyzing a series of land use trajectories with Landsat, Google Earth, and PlanetScope imageries to provide a substantial knowledge base. The study area covers five Divisional Secretariats Divisions in Kandy District, Central Highlands of Sri Lanka: Delthota, Doluwa, Udapalatha, Ganga Ihala Korale, and Pasbage Korale, where around 70% of the tea lands in Kandy District are covered. Six land use/cover (LULC) classes were considered: tea, Home Garden and Other Crop, forest, grass and bare land, built-up area, and Water Body. Abandoned tea lands were identified if the tea land was converted to another land use between 2015 and 2023. The results revealed the following: (1) 85% accuracy in LULC classification, revealing tea as the second-largest land use. Home Garden and Other Crop dominated, with an expanding built-up area. (2) The top 22 trajectories dominating the tea trajectories were identified, indicating that tea abandonment peaked between 2017 and 2023. (3) In total, 12% (5457 ha) of pixels were identified as abandoned tea lands during the observation period (2015–2023) at an accuracy rate of 94.7% in the validation. Significant changes were observed between the two urban centers of Gampola and Nawalapitiya towns. (3) Tea land abandonment over 7 years was the highest at 35% (1892.3 ha), while 5-year and 3-year periods accounted for 535.4 ha and 353.6 ha, respectively, highlighting a significant long-term trend. (4) The predominant conversion observed is the shift in tea towards Home Garden and Other Crop (2986.2 ha) during the timeframe. The findings underscore the extent and dynamics of tea land abandonment, providing critical insights into the patterns and characteristics of abandoned lands. This study fills a key research gap by offering a comprehensive spatial analysis of tea land abandonment in Sri Lanka. The results are valuable for stakeholders in the tea industry, providing essential information for sustainable management, policy-making, and future research on the spatial factors driving tea land abandonment. Full article

Forest ecosystems act as major carbon sinks, highlighting the need for the accurate estimation of aboveground biomass (AGB). The Global Ecosystem Dynamic Investigation (GEDI), a full-waveform spaceborne LiDAR system developed by NASA, provides detailed global observations of three-dimensional forest structures, playing a critical role in quantifying biomass and carbon storage. However, its performance has not yet been assessed in the Mediterranean forest ecosystems of Southern Italy. Therefore, the objectives of this study were to (i) evaluate the utility of the GEDI L4A gridded aboveground biomass density (AGBD) product in the Apulia region by comparing it with the Apulia AGBD map, and (ii) develop GEDI-derived AGBD models using multiple GEDI metrics. The results indicated that the GEDI L4A gridded product significantly underestimated AGBD, showing large discrepancies from the reference data (RMSE = 40.756 Mg/ha, bias = −30.075 Mg/ha). In contrast, GEDI-derived AGBD models using random forest (RF), geographically weighted regression (GWR), and multiscale geographically weighted regression (MGWR) demonstrated improved accuracy. Among them, the MGWR model emerged as the optimal choice for AGBD estimation, achieving the lowest RMSE (14.059 Mg/ha), near-zero bias (0.032 Mg/ha), and the highest R² (0.714). Additionally, the MGWR model consistently outperformed other models across four different plant functional types. These findings underscore the importance of local calibration for GEDI data and demonstrate the capability of the MGWR model to capture scale-dependent relationships in heterogeneous landscapes. Overall, this research highlights the potential of the GEDI to estimate AGBD in the Apulia region and its contribution to enhanced forest management strategies. Full article

Intensified by climate change and anthropogenic activities, flood disasters necessitate rapid and accurate mapping for effective disaster management. This study develops an integrated framework leveraging synthetic aperture radar (SAR) and cloud computing to enhance flood monitoring, with a focus on a 2024 extreme rainfall event in Liaoning Province, China. Utilizing the Google Earth Engine (GEE) platform, we combine three complementary techniques: (1) Otsu automatic thresholding, for efficient extraction of surface water extent from Sentinel-1 GRD time series (154 scenes, January–October 2024), achieving processing times under 2 min with >85% open-water accuracy; (2) random forest (RF) classification, integrating multi-source features (SAR backscatter, terrain parameters from 30 m SRTM DEM, NDVI phenology) to distinguish permanent water bodies, flooded farmland, and urban areas, attaining an overall accuracy of 92.7%; and (3) Fuzzy C-Means (FCM) clustering, incorporating backscatter ratio and topographic constraints to resolve transitional “mixed-pixel” ambiguities in flood boundaries. The RF-FCM synergy effectively mapped submerged agricultural land and urban spill zones, while the Otsu-derived flood frequency highlighted high-risk corridors (recurrence > 10%) along the riverine zones and reservoir. This multi-algorithm approach provides a scalable, high-resolution (10 m) solution for near-real-time flood assessment, supporting emergency response and sustainable water resource management in affected basins. Full article

Mangrove forests are among the world’s most vital coastal ecosystems. Mapping mangrove cover from local to global scales using spectral data and machine learning models is a well-established method. While non-spectral contextual datasets (spatial features) have also been incorporated into such models, the contribution of these additional features to improving mangrove mapping remains underexplored. Using the Mesoamerican Reef Region as a case study, we evaluate the effectiveness of incorporating spatial features in binary mangrove classification to enhance mapping accuracy. We compared an aspatial model that includes only spectral data with three spatial models: two included features such as geographic coordinates, elevation, and proximity to coastlines and streams, while the third integrated a geostatistical approach using Inverse Distance Weighted (IDW) interpolation. Spectral inputs included bands and indices derived from Sentinel-1 and Sentinel-2, and all models were implemented using the Random Forest algorithm in Google Earth Engine. Results show that spatial features reduced omission errors without increasing commission errors, enhancing the model’s ability to capture spatial variability. Models using geographic coordinates and elevation performed comparably to those with additional environmental variables, with storm frequency and distance to streams emerging as important predictors in the Mesoamerican Reef region. In contrast, the IDW-based model underperformed, likely due to overfitting and limited representation of local spectral variation. Spatial analyses show that models incorporating spatial features produced more continuous mangrove patches and removed some false positives in non-mangrove areas. These findings highlight the value of spatial features in improving classification accuracy, especially in regions with ecologically diverse mangroves across varied environments. By integrating spatial context, these models support more accurate, locally relevant mangrove maps that are essential for effective conservation and management. Full article

As the laying cycle is prolonged, the egg albumen quality exhibits a declining trend. A Haugh unit (HU) is a standard measure of the albumen quality, which reflects viscosity and freshness. During the late laying period, the HU not only decreased significantly, but also exhibited greater variability among individuals. The magnum, as the primary site of albumen synthesis, plays a central role in this process; however, the mechanisms by which it regulates the albumen quality remain unclear. To address this, we obtained genomic and transcriptomic data from 254 individuals, along with single-cell RNA sequencing (scRNA-seq) data of the magnum tissue. Genome-wide association studies (GWAS) across five laying stages (66, 72, 80, 90, and 100 weeks of age) identified 77 HU-associated SNPs. Expression quantitative trait locus (eQTL) mapping linked these variants to the expression of 12 genes in magnum tissue. In addition, transcriptomic analysis using linear regression and random forest models identified 259 genes that significantly correlated with the HU. Single-cell RNA sequencing further revealed two key cell types, plasma cells and a subset of epithelial cells, marked by ADAMTSL1 and OVAL, which are functionally relevant to the HU. Through integrated Transcriptome-Wide Association Study (TWAS) and Summary-data-based Mendelian Randomization (SMR) analyses, we identified four robust regulators of the albumen quality: CISD, NQO2, SLC22A23, and CMTM6. These genes are functionally involved in mitochondrial function, antioxidant defense, and membrane transport. Overall, our findings uncovered the genetic and cellular mechanisms underlying age-related decline in the albumen quality and identified potential targets for improving the egg quality in aging flocks. Full article

Geospatial sensing and data-driven technologies (GSDDTs) are playing an increasingly important role in transforming (agro)forestry practices across the Western Balkans 6 region (WB6). This review critically examines the current state of GSDDT application in six WB countries (also known as the WB6 group)—Albania, Bosnia and Herzegovina, Kosovo*, Montenegro, North Macedonia, and Serbia—with a focus on their contributions to sustainable (agro)forest management. The analysis explores the use of unmanned aerial vehicles (UAVs), light detection and ranging (LiDAR), geographic information systems (GIS), and satellite imagery in (agro)forest monitoring, biodiversity assessment, landscape restoration, and the promotion of circular economy models. Drawing on 25 identified case studies across WB6—for example, ALFIS, Forest Beyond Borders, ForestConnect, Kuklica Geosite Survey, CREDIT Vibes, and Project O₂ (including drone-assisted reforestation in Kosovo*)—this review highlights both technological advancements and systemic limitations. Key barriers to effective GSDDT deployment across WB6 in the (agro)forestry sector and its cross-border cooperation initiatives include fragmented legal frameworks, limited technical expertise, weak institutional coordination, and reliance on short-term donor funding. In addition to mapping current practices, this paper offers a comparative overview of UAV regulations across the WB6 region and identifies six major challenges influencing the adoption and scaling of GSDDTs. To address these, it proposes targeted policy interventions, such as establishing national LiDAR inventories, harmonizing UAV legislation, developing national GSDDT strategies, and creating dedicated GSDDT units within forestry agencies. This review also underscores how GSDDTs contribute to compliance with seven European Union (EU) acquis chapters, how they support eight Sustainable Development Goals (SDGs) and their sixteen targets, and how they advance several EU Green Agenda objectives. Strengthening institutional capacities, promoting legal alignment, and enabling cross-border data interoperability are essential for integrating GSDDTs into national (agro)forest policies and research agendas. This review underscores GSDDTs’ untapped potential in forest genetic monitoring and landscape restoration, advocating for their institutional integration as catalysts for evidence-based policy and ecological resilience in WB6 (agro)forestry systems. Full article

Traditional Forest Management Plans (FMPs), which often span hundreds of pages on paper, present significant challenges due to their extensive length and lack of clear spatiotemporal context. This study aimed to integrate complex data from FMPs into an interactive, spatially referenced database. Using Gârda Forest in Romania’s Apuseni Mountains as a case study, we gathered raw data, developed the geodatabase’s spatial and alphanumerical components, and conducted spatial analyses related to ecological and production factors. Our GIS was designed to accommodate multiple attributes within the compartment layer’s attribute table. Unlike previous studies, we incorporated the full range of information from the Compartment Description, not just isolated management aspects. This comprehensive approach enabled spatial analysis to highlight, in maps, key features across the 50 compartments (totaling 752.5 ha) including dominant species (Norway spruce, silver fir, beech), target species composition (Norway spruce as the predominant target), land protection needs (required for 4% of the area), median forest volume (1565 m³ per compartment), elevation range (1020–1420 m), compartments with production functions, and silvicultural treatments. These thematic maps provide a tool for further analyses and clear spatial visualization. Our GIS-based methodology supports rapid condition assessments and aids forest professionals and decision-makers in promoting sustainable forest management. Full article

Addressing limitations in remote sensing irrigation monitoring (insufficient resolution, single-source constraints, poor terrain adaptability), this study developed a high-precision identification framework for Jianping County, China, a semi-arid region. We integrated Sentinel-1 SAR (VV/VH), Sentinel-2 multispectral, and MOD11A1 land surface temperature data. Savitzky–Golay (S-G) filtering reconstructed time-series datasets for NDVI, SAVI, TVDI, and VV/VH backscatter coefficients. Irrigation mapping employed random forest (RF), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN) algorithms. Key results demonstrate the following. (1) RF achieved superior performance with overall accuracies of 91.00% (2022), 88.33% (2023), and 87.78% (2024), and Kappa coefficients of 86.37%, 80.96%, and 80.40%, showing minimal deviation (0.66–3.44%) from statistical data; (2) SAVI and VH exhibited high irrigation sensitivity, with peak differences between irrigated/non-irrigated areas reaching 0.48 units (SAVI, July–August) and 2.78 dB (VH); (3) cropland extraction accuracy showed <3% discrepancy versus governmental statistics. The “Multi-temporal Feature Fusion + S-G Filtering + RF Optimization” framework provides an effective solution for precision irrigation monitoring in complex semi-arid environments. Full article

High-fidelity finite element analysis (FEA) plays a key role in structural engineering by enabling accurate simulation of displacement, stress, and internal forces under static loads. However, its high computational cost limits applicability in real-time control, iterative design, and large-scale uncertainty quantification. Surrogate modeling provides a computationally efficient alternative by learning input–output mappings from precomputed simulations. Yet, the performance of individual surrogates is often sensitive to data distribution and model assumptions. To enhance both accuracy and robustness, we propose a model averaging framework based on Jackknife Model Averaging (JMA) that integrates six surrogate models: polynomial response surfaces (PRSs), support vector regression (SVR), radial basis function (RBF) interpolation, eXtreme Gradient Boosting (XGB), Light Gradient Boosting Machine (LGBM), and Random Forest (RF). Three ensembles are formed: JMA1 (classical models), JMA2 (tree-based models), and JMA3 (all models). JMA assigns optimal convex weights using cross-validated out-of-fold errors without a meta-learner. We evaluate the framework on the Static Analysis Dataset with over 300,000 FEA simulations. Results show that JMA consistently outperforms individual models in root mean squared error, mean absolute error, and the coefficient of determination, while also producing tighter, better-calibrated conformal prediction intervals. These findings support JMA as an effective tool for surrogate-based structural analysis. Full article

Phylogenetic diversity serves as a critical complement to traditional species diversity metrics. However, the performance variations among different computational models in simulating phylogenetic diversity within plant communities in the alpine grasslands of the Qinghai-Xizang Plateau remain insufficiently characterized. Here, we evaluated nine modeling approaches—random forest (RF), generalized boosting regression (GBR), multiple linear regression (MLR), artificial neural network (ANN), generalized linear regression (GLR), conditional inference tree (CIT), extreme gradient boosting (eXGB), support vector machine (SVM), and recursive regression tree (RRT)—for predicting three key phylogenetic diversity metrics [Faith’s phylogenetic diversity (PD), mean pairwise distance (MPD), mean nearest taxon distance (MNTD)] using climate variables and NDVImax. Our comprehensive analysis revealed distinct model performance patterns under grazing vs. fencing regimes. The eXGB algorithm demonstrated superior accuracy for fencing conditions, achieving the lowest relative bias (−0.08%) and RMSE (9.54) for MPD, along with optimal performance for MNTD (bias = 2.95%, RMSE = 44.86). Conversely, RF emerged as the most robust model for grazing scenarios, delivering the lowest bias (−1.63%) and RMSE (16.89) for MPD while maintaining strong predictive capability for MNTD (bias = −1.09%, RMSE = 27.59). Notably, scatterplot analysis revealed that only RF, GBR, and eXGB maintained symmetrical distributions along the 1:1 line, while other models showed problematic one-to-many value mappings or asymmetric patterns. These findings show that machine learning (especially RF and eXGB) enhances phylogenetic diversity predictions by integrating climate and NDVI data, though model performance varies by metric and management context. This study offers a framework for ecological forecasting, emphasizing multi-metric validation in biodiversity modeling. Full article

Cross-modal semantic segmentation of individual tree LiDAR point clouds is critical for accurately characterizing tree attributes, quantifying ecological interactions, and estimating carbon storage. However, in forest environments, this task faces key challenges such as high annotation costs and poor cross-domain generalization. To address these issues, this study proposes a cross-modal semantic transfer framework tailored for individual tree point cloud segmentation in forested scenes. Leveraging co-registered UAV-acquired RGB imagery and LiDAR data, we construct a technical pipeline of “2D semantic inference—3D spatial mapping—cross-modal fusion” to enable annotation-free semantic parsing of 3D individual trees. Specifically, we first introduce a novel Multi-Source Feature Fusion Network (MSFFNet) to achieve accurate instance-level segmentation of individual trees in the 2D image domain. Subsequently, we develop a hierarchical two-stage registration strategy to effectively align dense matched point clouds (MPC) generated from UAV imagery with LiDAR point clouds. On this basis, we propose a probabilistic cross-modal semantic transfer model that builds a semantic probability field through multi-view projection and the expectation–maximization algorithm. By integrating geometric features and semantic confidence, the model establishes semantic correspondences between 2D pixels and 3D points, thereby achieving spatially consistent semantic label mapping. This facilitates the transfer of semantic annotations from the 2D image domain to the 3D point cloud domain. The proposed method is evaluated on two forest datasets. The results demonstrate that the proposed individual tree instance segmentation approach achieves the highest performance, with an IoU of 87.60%, compared to state-of-the-art methods such as Mask R-CNN, SOLOV2, and Mask2Former. Furthermore, the cross-modal semantic label transfer framework significantly outperforms existing mainstream methods in individual tree point cloud semantic segmentation across complex forest scenarios. Full article

The quantification of emotional value and accurate prediction of purchase intention has emerged as a critical interdisciplinary challenge in the evolving emotional economy. Focusing on Generation Z (born 1995–2009), this study proposes a hybrid algorithmic framework integrating text-based sentiment computation, feature selection, and random forest modeling to forecast purchase intention for therapeutic toys and interpret its underlying drivers. First, 856 customer reviews were scraped from Jellycat’s official website and subjected to polarity classification using a fine-tuned RoBERTa-wwm-ext model (F1 = 0.92), with generated sentiment scores and high-frequency keywords mapped as interpretable features. Next, Boruta–SHAP feature selection was applied to 35 structured variables from 336 survey records, retaining 17 significant predictors. The core module employed a RF (random forest) model to estimate continuous “purchase intention” scores, achieving R² = 0.83 and MSE = 0.14 under 10-fold cross-validation. To enhance interpretability, RF model was also utilized to evaluate feature importance, quantifying each feature’s contribution to the model outputs, revealing Social Ostracism (β = 0.307) and Task Overload (β = 0.207) as dominant predictors. Finally, k-means clustering with gap statistics segmented consumers based on emotional relevance, value rationality, and interest level, with model performance compared across clusters. Experimental results demonstrate that our integrated predictive model achieves a balance between forecasting accuracy and decision interpretability in emotional value computation, offering actionable insights for targeted product development and precision marketing in the therapeutic goods sector. Full article

We compare several methods for predicting future built-up land cover using only a short yearly time series of satellite-derived binary urban maps. Existing methods of built-up expansion forecasting often rely on ancillary datasets such as utility networks, distance to transportation nodes, and population density maps, along with remotely sensed aerial or satellite imagery. Such ancillary datasets are not always available and lack the temporal density of satellite imagery. Moreover, existing work often focuses on quantifying the expected volume of built-up expansion, rather than predicting where exactly that expansion will occur. To address these gaps, we evaluate six methods for the creation of prediction maps showing expected areas of future built-up expansion, using yearly built/not-built maps derived from Sentinel-2 imagery as inputs: Cellular Automata, logistic regression, Support Vector Machines, Random Forests, Convolutional Neural Networks (CNNs), and CNNs with the addition of long short-term memory (ConvLSTM). Of these six, we find CNNs to be the best-performing method, with an average Cohen’s kappa score of 0.73 across nine study sites in the continental United States. Full article

The study is devoted to the construction of an avalanche susceptibility map based on ensemble machine learning algorithms (random forest, XGBoost, LightGBM, gradient boosting machines, AdaBoost, NGBoost) for the conditions of the East Kazakhstan region. To train these models, data were collected on avalanche path profiles, meteorological conditions, and historical avalanche events. The quality of the trained machine learning models was assessed using metrics such as accuracy, precision, true positive rate (recall), and F1-score. The obtained metrics indicated that the trained machine learning models achieved reasonably accurate forecasting performance (forecast accuracy from 67% to 73.8%). ROC curves were also constructed for each obtained model for evaluation. The resulting AUCs for these ROC curves showed acceptable levels (from 0.57 to 0.73), which also indicated that the presented models could be used to predict avalanche danger. In addition, for each machine learning model, we determined the importance of the indicators used to predict avalanche danger. Analysis of the importance of the indicators showed that the most significant indicators were meteorological data, namely temperature and snow cover level in avalanche paths. Among the indicators that characterized the avalanche paths’ profiles, the most important were the minimum and maximum slope elevations. Thus, within the framework of this study, a highly accurate model was built using geospatial and meteorological data that allows identifying potentially dangerous slope areas. These results can support territorial planning, the design of protective infrastructure, and the development of early warning systems to mitigate avalanche risks. Full article