Search Results (114)

UAVs are essential for forest fire detection due to vast forest areas and inaccessibility of high-risk zones, enabling rapid long-range inspection and detailed close-range surveillance. However, aerial photography faces challenges like multi-scale target recognition and complex scenario adaptation (e.g., deformation, occlusion, lighting variations). RGB-Thermal fusion methods integrate visible-light texture and thermal infrared temperature features effectively, but current approaches are constrained by limited datasets and insufficient exploitation of cross-modal complementary information, ignoring cross-level feature interaction. A time-synchronized multi-scene, multi-angle aerial RGB-Thermal dataset (RGBT-3M) with “Smoke–Fire–Person” annotations and modal alignment via the M-RIFT method was constructed as a way to address the problem of data scarcity in wildfire scenarios. Finally, we propose a CP-YOLOv11-MF fusion detection model based on the advanced YOLOv11 framework, which can learn heterogeneous features complementary to each modality in a progressive manner. Experimental validation proves the superiority of our method, with a precision of 92.5%, a recall of 93.5%, a mAP50 of 96.3%, and a mAP50-95 of 62.9%. The model’s RGB-Thermal fusion capability enhances early fire detection, offering a benchmark dataset and methodological advancement for intelligent forest conservation, with implications for AI-driven ecological protection. Full article

Hurricanes are major drivers of forest structure in the Caribbean. In 2017, Hurricane Maria caused substantial damage to Puerto Rico’s forests. We studied forest structure variation across 75 sites at Las Casas de la Selva, a sustainable forest plantation in Patillas, Puerto Rico, seven years after Hurricane Maria hit the property. At each site we analyzed 360° photos in a 3D VR headset to quantify the vertical structure and transformed them into hemispherical images to quantify canopy closure and ground cover. We also computed the Vertical Habitat Diversity Index (VHDI) from the amount of foliage in four strata: herbaceous, shrub, understory, and canopy. Using the Local Bivariate Relationship tool in ArcGIS Pro, we analyzed the relationship between forest recovery (vertical structure, canopy closure, and ground cover) and damage. Likewise, we analyzed the effects of elevation, slope, and aspect, on damage, canopy closure, and vertical forest structure. We found that canopy closure decreases with increasing elevation and increases with the amount of damage. Higher elevations show a greater amount of damage even seven years post hurricane. We conclude that trees in the mixed tabonuco/plantation forest are more susceptible to hurricanes at higher elevations. The results have implications for plantation forest management under climate-change-driven higher intensity hurricane regimes. Full article

The precise identification and classification of tree species in young forests during their early development stages are vital for forest management and silvicultural efforts that support their growth and renewal. However, achieving accurate geolocation and species classification through field-based surveys is often a labor-intensive and complicated task. Remote sensing technologies combined with machine learning techniques present an encouraging solution, offering a more efficient alternative to conventional field-based methods. This study aimed to detect and classify young forest tree species using remote sensing imagery and machine learning techniques. The study mainly involved two different objectives: first, tree species detection using the latest version of You Only Look Once (YOLOv12), and second, semantic segmentation (classification) using random forest, Categorical Boosting (CatBoost), and a Convolutional Neural Network (CNN). To the best of our knowledge, this marks the first exploration utilizing YOLOv12 for tree species identification, along with the study that integrates digital aerial photogrammetry with Planet imagery to achieve semantic segmentation in young forests. The study used two remote sensing datasets: RGB imagery from unmanned aerial vehicle (UAV) ortho photography and RGB-NIR from PlanetScope. For YOLOv12-based tree species detection, only RGB from ortho photography was used, while semantic segmentation was performed with three sets of data: (1) Ortho RGB (3 bands), (2) Ortho RGB + canopy height model (CHM) + Planet RGB-NIR (8 bands), and (3) ortho RGB + CHM + Planet RGB-NIR + 12 vegetation indices (20 bands). With three models applied to these datasets, nine machine learning models were trained and tested using 57 images (1024 × 1024 pixels) and their corresponding mask tiles. The YOLOv12 model achieved 79% overall accuracy, with Scots pine performing best (precision: 97%, recall: 92%, mAP50: 97%, mAP75: 80%) and Norway spruce showing slightly lower accuracy (precision: 94%, recall: 82%, mAP50: 90%, mAP75: 71%). For semantic segmentation, the CatBoost model with 20 bands outperformed other models, achieving 85% accuracy, 80% Kappa, and 81% MCC, with CHM, EVI, NIRPlanet, GreenPlanet, NDGI, GNDVI, and NDVI being the most influential variables. These results indicate that a simple boosting model like CatBoost can outperform more complex CNNs for semantic segmentation in young forests. Full article

Accurately monitoring forest canopy height is crucial for sustainable forest management, particularly in southeastern North Carolina, USA, where dense forests and limited accessibility pose substantial challenges. This study presents an explainable machine learning framework that integrates sparse GEDI LiDAR samples with multi-sensor remote sensing data to improve both the accuracy and interpretability of forest canopy height estimation. This framework incorporates multitemporal optical observations from Sentinel-2; C-band backscatter and InSAR coherence from Sentinel-1; quad-polarization L-Band backscatter and polarimetric decompositions from the Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR); texture features from the National Agriculture Imagery Program (NAIP) aerial photography; and topographic data derived from an airborne LiDAR-based digital elevation model. We evaluated four machine learning algorithms, K-nearest neighbors (KNN), random forest (RF), support vector machine (SVM), and eXtreme gradient boosting (XGB), and found consistent accuracy across all models. Our evaluation highlights our method’s robustness, evidenced by closely matched R² and RMSE values across models: KNN (R² of 0.496, RMSE of 5.13 m), RF (R² of 0.510, RMSE of 5.06 m), SVM (R² of 0.544, RMSE of 4.88 m), and XGB (R² of 0.548, RMSE of 4.85 m). The integration of comprehensive feature sets, as opposed to subsets, yielded better results, underscoring the value of using multisource remotely sensed data. Crucially, SHapley Additive exPlanations (SHAP) revealed the multi-seasonal red-edge spectral bands of Sentinel-2 as dominant predictors across models, while volume scattering from UAVSAR emerged as a key driver in tree-based algorithms. This study underscores the complementary nature of multi-sensor data and highlights the interpretability of our models. By offering spatially continuous, high-quality canopy height estimates, this cost-effective, data-driven approach advances large-scale forest management and environmental monitoring, paving the way for improved decision-making and conservation strategies. Full article

Leaf Area Index (LAI) is one of the key parameters for characterizing leaf density, vegetation growth status, and canopy structure. Rapid, objective, and accurate acquisition of forest LAI is of great significance for studying forest ecosystems and forestry production. This study focuses on the core issue of accurately segmenting leaf elements from background elements in hemispherical photography used for forest LAI measurement, with a particular focus on meeting the real-time requirements of embedded platforms. The differences in grayscale values and frequency characteristics between leaf regions, trunk regions, and sky regions in vegetation canopy images were leveraged to decompose, process, and reconstruct such images using a 9/7 wavelet-based transformation method, achieving efficient and precise segmentation of leaf regions. Effectively addresses the issue of LAI overestimation caused by trunk regions in traditional threshold-based segmentation methods. Through the extraction of canopy gap fraction, rapid LAI measurement was enabled. Comparative experimental results showed that the proposed inversion method exhibited a high correlation with the LAI-2200C measurement results (r = 0.897, RMSE = 0.431), fully verifying its accuracy across different forest ecological environments. This study provides strong support for the development of portable, high-precision LAI measurement devices and holds practical application value and broad application prospects. Full article

Tree height and vertical forest structure are important attributes in forestry, but their traditional measurement or assessment in the field is expensive, time-consuming, and often inaccurate. One of the main advantages of using remote sensing data to estimate vertical forest structure is the ability to obtain accurate data for larger areas in a more time- and cost-efficient manner. Temporal changes are also important for estimating and analysing tree heights, and in many countries, national airborne laser scanning (ALS) surveys have been conducted either only once or at specific, longer intervals, whereas aerial surveys are more often arranged in cycles with shorter intervals. In this study, we reviewed all freely available national airborne remote sensing data describing three-dimensional forest structures in Slovenia and compared them with traditional field measurements in an area dominated by uneven-aged forests. The comparison of ALS and digital aerial photogrammetry (DAP) data revealed that freely available national ALS data provide better estimates of dominant forest heights, vertical structural diversity, and their changes compared to cyclic DAP data, but they are still useful due to their temporally dense data. Up-to-date data are very important for forest management and the study of forest resilience and resistance to disturbance. Based on field measurements (2013 and 2023) and all remote sensing data, dominant and maximum heights are statistically significantly higher in uneven-aged forests than in mature, even-aged forests. Canopy height diversity (CHD) information, derived from lidar ALS and DAP data, has also proven to be suitable for distinguishing between even-aged and uneven-aged forests. The CHD_ALS 2023 was 1.64, and the CHD_CAS 2022 was 1.38 in uneven-aged stands, which were statistically significantly higher than in even-aged forest stands. Full article

A probabilistic estimation model for forest biomass using unmanned aerial vehicle (UAV) photography was developed. We utilized a machine-learning-based object detection algorithm, a mask region-based convolutional neural network (Mask R-CNN), to detect trees in aerial photographs. Subsequently, Bayesian regression was used to calibrate the model based on an allometric model using the estimated crown diameter (CD) obtained from aerial photographs and analyzed the diameter at breast height (DBH) data acquired through terrestrial laser scanning. The F1 score of the Mask R-CNN for individual tree detection was 0.927. Moreover, CD estimation using the Mask R-CNN was acceptable (rRMSE = 10.17%). Accordingly, the probabilistic DBH estimation model was successfully calibrated using Bayesian regression. A predictive distribution accurately predicted the validation data, with 98.6% and 56.7% of the data being within the 95% and 50% prediction intervals, respectively. Furthermore, the estimated uncertainty of the probabilistic model was more practical and reliable compared to traditional ordinary least squares (OLS). Our model can be applied to estimate forest biomass at the individual tree level. Particularly, the probabilistic approach of this study provides a benefit for risk assessments. Additionally, since the workflow is not interfered by the tree canopy, it can effectively estimate forest biomass in dense canopy conditions. Full article

This paper provides a comprehensive review of advancements in the detection; evaluation; and management of invasive plant species (IPS) using diverse remote sensing (RS) techniques and machine learning (ML) methods. Analyzing the high-resolution datasets received from drones, satellites, and aerial photography enables the perfect cartography technique and analysis of the spread and various impacts of ecology on IPS. The majority of current research on hyperspectral imaging with unmanned aerial vehicle (UAV) enhanced by ML has significantly improved the accuracy and efficiency of identifying mapping IPS, and it also serves as a powerful instrument for ecological management. The integrative association is essential to manage the alien species better, as researchers from multiple other fields participate in modeling innovative methods and structures. Incorporating advanced technologies like light detection and ranging (LiDAR) and hyperspectral imaging shows potential for improving spatial and spectral analysis approaches and utilizing ML approaches such as a support vector machine (SVM), random forest (RF), artificial neural network (ANN), convolutional neural network (CNN), and deep convolutional neural network (DCNN) analysis for detecting complex IPS. The significant results indicate that ML methods, most importantly SVM and RF, are victorious in recognizing the alien species via analyzing RS data. This report emphasizes the importance of continuous research efforts to improve predictive models, fill gaps in our understanding of the connections between climate, urbanization and invasion dynamics, and expands conservation initiatives via utilizing RS techniques. This study also highlights the potential for RS data to refine management plans, enabling the implementation of more efficient strategies for controlling IPS and preserving ecosystems. Full article

Background: Diabetic retinopathy (DR) is a leading cause of blindness in patients with type 2 diabetes mellitus (T2DM). Cardiovascular risk factors, such as hypertension, obesity, and dyslipidemia, may play a crucial role in the development and progression of DR, though the evidence remains mixed. This study aimed to assess cardiovascular risk factors as independent predictors of DR and to develop a predictive model for DR progression in T2DM patients. Methods: A retrospective cross-sectional study was conducted on 377 patients with T2DM who underwent a comprehensive eye exam. Clinical data, including blood pressure, lipid profile, BMI, and smoking status, were collected. DR staging was determined through fundus photography and classified as No DR, Non-Proliferative DR (NPDR), and Mild, Moderate, Severe, or Proliferative DR (PDR). A Multivariate Logistic Regression was used to evaluate the association between cardiovascular risk factors and DR presence. Several machine learning models, including Random Forest, XGBoost, and Support Vector Machines, were applied to assess the predictive value of cardiovascular risk factors and identify key predictors. Model performance was evaluated using accuracy, precision, recall, and ROC-AUC. Results: The prevalence of DR in the cohort was 41.6%, with 34.5% having NPDR and 7.1% having PDR. A multivariate analysis identified systolic blood pressure (SBP), LDL cholesterol, and body mass index (BMI) as independent predictors of DR progression (p < 0.05). The Random Forest model showed a moderate predictive ability, with an AUC of 0.62 for distinguishing between the presence and absence of DR XGBoost showing a better performance, featuring a ROC-AUC of 0.68, while SBP, HDL cholesterol, and BMI were consistently identified as the most important predictors across models. After tuning, the XGBoost model showed a notable improvement, with an ROC-AUC of 0.72. Conclusions: Cardiovascular risk factors, particularly BP and BMI, play a significant role in the progression of DR in patients with T2DM. The predictive models, especially XGBoost, showed moderate accuracy in identifying DR stages, suggesting that integrating these risk factors into clinical practice may improve early detection and intervention strategies for DR. Full article

Accurately assessing maize crop height (CH) and aboveground biomass (AGB) is crucial for understanding crop growth and light-use efficiency. Unmanned aerial vehicle (UAV) remote sensing, with its flexibility and high spatiotemporal resolution, has been widely applied in crop phenotyping studies. Traditional canopy height models (CHMs) are significantly influenced by image resolution and meteorological factors. In contrast, the accumulated incremental height (AIH) extracted from point cloud data offers a more accurate estimation of CH. In this study, vegetation indices and structural features were extracted from optical imagery, nadir and oblique photography, and LiDAR point cloud data. Optuna-optimized models, including random forest regression (RFR), light gradient boosting machine (LightGBM), gradient boosting decision tree (GBDT), and support vector regression (SVR), were employed to estimate maize AGB. Results show that AIH₉₉ has higher accuracy in estimating CH. LiDAR demonstrated the highest accuracy, while oblique photography and nadir photography point clouds were slightly less accurate. Fusion of multi-source data achieved higher estimation accuracy than single-sensor data. Embedding structural features can mitigate spectral saturation, with R² ranging from 0.704 to 0.939 and RMSE ranging from 0.338 to 1.899 t/hm². During the entire growth cycle, the R² for LightGBM and RFR were 0.887 and 0.878, with an RMSE of 1.75 and 1.76 t/hm². LightGBM and RFR also performed well across different growth stages, while SVR showed the poorest performance. As the amount of nitrogen application gradually decreases, the accumulation and accumulation rate of AGB also gradually decrease. This high-throughput crop-phenotyping analysis method offers advantages, such as speed and high accuracy, providing valuable references for precision agriculture management in maize fields. Full article

Accurately assessing forest structure and maintaining up-to-date information about forest structure is crucial for various forest planning efforts, including the development of reliable forest plans and assessments of the sustainable management of natural resources. Field measurements traditionally applied to acquire forest inventory information (e.g., basal area, tree volume, and aboveground biomass) are labor intensive and time consuming. To address this limitation, remote sensing technology has been widely applied in modeling efforts to help estimate forest inventory information. Among various remotely sensed data, LiDAR can potentially help describe forest structure. This study was conducted to estimate and map forest inventory information across the Shoal Creek and Talladega Ranger Districts of the Talladega National Forest by employing ALS-derived data and aerial photography. The quality of the predictive models was evaluated to determine whether additional remotely sensed data can help improve forest structure estimates. Additionally, the quality of general predictive models was compared to that of species group models. This study confirms that quality level 2 LiDAR data were sufficient for developing adequate predictive models (R²_adj. ranging between 0.71 and 0.82), when compared to the predictive models based on LiDAR and aerial imagery. Additionally, this study suggests that species group predictive models were of higher quality than general predictive models. Lastly, landscape level maps were created from the predictive models and these may be helpful to planners, forest managers, and landowners in their management efforts. Full article

Anthocyanins are widely found in plants and have significant functions. The accurate detection and quantitative assessment of anthocyanin content are essential to assess its functions. The anthocyanin content in plant tissues is typically quantified by wet chemistry and spectroscopic techniques. However, these methods are time-consuming, labor-intensive, tedious, expensive, destructive, or require expensive equipment. Digital photography is a fast, economical, efficient, reliable, and non-invasive method for estimating plant pigment content. This study examined the anthocyanin content of Rosa chinensis petals using digital images, a back-propagation neural network (BPNN), and the random forest (RF) algorithm. The objective was to determine whether using RGB indices and BPNN and RF algorithms to accurately predict the anthocyanin content of R. chinensis petals is feasible. The anthocyanin content ranged from 0.832 to 4.549 µmol g⁻¹ for 168 samples. Most RGB indices were strongly correlated with the anthocyanin content. The coefficient of determination (R²) and the ratio of performance to deviation (RPD) of the BPNN and RF models exceeded 0.75 and 2.00, respectively, indicating the high accuracy of both models in predicting the anthocyanin content of R. chinensis petals using RGB indices. The RF model had higher R² and RPD values, and lower root mean square error (RMSE) and mean absolute error (MAE) values than the BPNN, indicating that it outperformed the BPNN model. This study provides an alternative method for determining the anthocyanin content of flowers. Full article

This study concerns the design of a geocultural site in Huta Różaniecka. It is one of 166 sites prepared for the Kamienny Las na Roztoczu (Roztocze Stone Forest) Geopark project. The site is distinguished, on the one hand, by its interesting geology and geomorphology (exposures of Miocene sea shore with numerous fossils) and, on the other hand, by its quarries, stonemasonry traditions, and buildings (ruins of the Greek Catholic church). The aim of this paper is to present a model for building specialized documentation using a wide range of source materials, methods (field inventory, queries, interviews, high-precision Light Detection and Ranging-LiDAR measurements), tools (Leica ScanStation C10 laser scanner), and techniques (photography, Unmanned Aerial Vehicle-UAV, Terrestrial Laser Scanning-TLS). The applied research procedure model led to the construction of specialized documentation relating to the spatial dimension, natural features, and cultural context of the site. Taking into account the collected data, it should be concluded that the projected geocultural site at Huta Różaniecka, irrespective of the creation of a geopark, has great potential to build a tourist product that is attractive to a wide range of visitors. Full article

The three-dimensional reconstruction of forest ecological environment by low-altitude remote sensing photography from Unmanned Aerial Vehicles (UAVs) provides a powerful basis for the fine surveying of forest resources and forest management. A stereo vision system, D-SLAM, is proposed to realize simultaneous localization and dense mapping for UAVs in complex forest ecological environments. The system takes binocular images as input and 3D dense maps as target outputs, while the 3D sparse maps and the camera poses can be obtained. The tracking thread utilizes temporal clue to match sparse map points for zero-drift localization. The relative motion amount and data association between frames are used as constraints for new keyframes selection, and the binocular image spatial clue compensation strategy is proposed to increase the robustness of the algorithm tracking. The dense mapping thread uses Linear Attention Network (LANet) to predict reliable disparity maps in ill-posed regions, which are transformed to depth maps for constructing dense point cloud maps. Evaluations of three datasets, EuRoC, KITTI and Forest, show that the proposed system can run at 30 ordinary frames and 3 keyframes per second with Forest, with a high localization accuracy of several centimeters for Root Mean Squared Absolute Trajectory Error (RMS ATE) on EuRoC and a Relative Root Mean Squared Error (RMSE) with two average values of 0.64 and 0.2 for t_rel and R_rel with KITTI, outperforming most mainstream models in terms of tracking accuracy and robustness. Moreover, the advantage of dense mapping compensates for the shortcomings of sparse mapping in most Smultaneous Localization and Mapping (SLAM) systems and the proposed system meets the requirements of real-time localization and dense mapping in the complex ecological environment of forests. Full article

Leaf Area Index (LAI) is a fundamental indicator of plant growth status in agronomy and environmental research. With the rapid development of drone technology, the estimation of crop LAI based on drone imagery and vegetation indices is becoming increasingly popular. However, there is still a lack of detailed research on the feasibility of using image texture to estimate LAI and the impact of combining texture indices with vegetation indices on LAI estimation accuracy. In this study, two key growth stages of winter wheat (i.e., the stages of green-up and jointing) were selected, and LAI was calculated using digital hemispherical photography. The feasibility of predicting winter wheat LAI was explored under three conditions: vegetation index, texture index, and a combination of vegetation index and texture index, at flight heights of 20 m and 40 m. Two feature selection methods (Lasso and recursive feature elimination) were combined with four machine learning regression models (multiple linear regression, random forest, support vector machine, and backpropagation neural network). The results showed that during the vegetative growth stage of winter wheat, the model combining texture information with vegetation indices performed better than the models using vegetation indices alone or texture information alone. Among them, the best prediction result based on vegetation index was RFECV-MLR at a flight height of 40 m (R² = 0.8943, RMSE = 0.4139, RRMSE = 0.1304, RPD = 3.0763); the best prediction result based on texture index was RFECV-RF at a flight height of 40 m (R² = 0.8894, RMSE = 0.4236, RRMSE = 0.1335, RPD = 3.0063); and the best prediction result combining texture and index was RFECV-RF at a flight height of 40 m (R² = 0.9210, RMSE = 0.3579, RRMSE = 0.1128, RPD = 3.5575). The results of this study demonstrate that combining vegetation indices and texture from multispectral drone imagery can improve the accuracy of LAI estimation during the vegetative growth stage of winter wheat. In addition, selecting a flight height of 40 m can improve efficiency in large-scale agricultural field monitoring, as this study showed that drone data at flight heights of 20 m and 40 m did not significantly affect model accuracy. Full article