Search Results (3,163)

Fire suppression in the upper U.S. Midwest has led to the expansion of flammable coniferous ladder fuels, necessitating precise tracking of conifer species basal area (BA) for fire risk management. This study benchmarks four subset-selection pipelines—xPLS, GA-xPLS, RF-xPLS, and SVR-xPLS—to optimize the fusion of high-dimensional, collinear data from Sentinel-2, Landsat-9, and LiDAR sensors. Using 141 field plots in Minnesota’s Kawishiwi Ranger District of the Superior National Forest, we evaluated 175 predictors against eight BA response variables. Results show that RF-xPLS provided the superior accuracy–parsimony trade-off, achieving the highest pooled R² (≈0.86) and lowest error with a compact 27-predictor block. GA-xPLS ranked second, excelling for specific species such as Pinus resinosa. The most effective predictors combined SWIR-based moisture indices, red-edge/NIR structure, and a single LiDAR-derived surface of vertical-structure (quadratic mean height). Our findings demonstrate that integrating machine learning selection engines with multi-sensor fusion substantially enhances the scalability and precision of forest inventory and fuels monitoring. This comparative framework offers practical insights for sustainable management and fire risk mitigation in northern temperate–boreal forests. Full article

Effective interpretation of coherent and usable information from aerial images (e.g., satellite imagery or high-altitude drone photography) can greatly reduce human effort in many situations, both natural (e.g., earthquakes, forest fires, tsunamis) and man-made (e.g., highway pile-ups, traffic congestion), particularly in disaster management. This research proposes a novel encoder–decoder framework for captioning of remote sensing images that integrates self-supervised DINOv3 visual features with a hybrid Transformer–LSTM decoder. Unlike existing approaches that rely on supervised CNN-based encoders (e.g., ResNet, VGG), the proposed method leverages DINOv3’s self-supervised learning capabilities to extract dense, semantically rich features from aerial images without requiring domain-specific labeled pretraining. The proposed hybrid decoder combines Transformer layers for global context modeling with LSTM layers for sequential caption generation, producing coherent and context-aware descriptions. Feature extraction is performed using the DINOv3 model, which employs the gram-anchoring technique to stabilize dense feature maps. Captions are generated through a hybrid of Transformer with Long Short-Term Memory (LSTM) layers, which adds contextual meaning to captions through sequential hidden layer modeling with gated memory. The model is first evaluated on two traditional remote sensing image captioning datasets: RSICD and UCM-Captions. Multiple evaluation metrics like Bilingual Evaluation Understudy (BLEU), Consensus-based Image Description Evaluation (CIDEr), Recall-Oriented Understudy for Gisting Evaluation (ROUGE-L), and Metric for Evaluation of Translation with Explicit Ordering (METEOR), are used to quantify the performance and robustness of the proposed DINOv3 hybrid model. The proposed model outperforms conventional Convolutional Neural Network (CNN) and Vision Transformers (ViT)-based models by approximately 9–12% across most evaluation metrics. Attention heatmaps are also employed to qualitatively validate the proposed model when identifying and describing key spatial elements. In addition, the proposed model is evaluated on advanced remote sensing datasets, including RSITMD, DisasterM3, and GeoChat. The results demonstrate that self-supervised vision transformers are robust encoders for multi-modal understanding in remote sensing image analysis and captioning. Full article

Transmission lines traversing forested areas pose significant fire risks, necessitating timely and efficient inspection mechanisms. Traditional manual patrols and cloud-based UAV inspections suffer from high latency, bandwidth dependence, and delayed response times. To address these challenges, this study proposes an integrated, real-time UAV-edge computing system for the early identification of fire risks and structural hazards along transmission corridors. The system integrates a DJI M300 RTK UAV with a Manifold 2-G edge computing unit (based on NVIDIA Jetson TX2), deploying a lightweight, TensorRT-optimized YOLOv8 model. By leveraging FP16 precision quantization and operator fusion, the system achieves a real-time inference speed of 32 FPS on the embedded platform. Furthermore, a custom Payload SDK integration ensures automated image acquisition and closed-loop data transmission via a dual-mode (4G/5G + Wi-Fi) communication link. Field experiments demonstrate that the system significantly reduces data transmission latency while maintaining high detection accuracy (mAP > 94%), providing a robust and replicable solution for intelligent power grid maintenance in resource-constrained environments. Full article

Due to climate change, drought periods are becoming more frequent and more intense, posing substantial stress to Central European forest stands, especially climatically sensitive conifer forests. The early detection and accurate spatial delineation of forest damage are essential for supporting adaptive forest management decisions. This study presents a two-tier, multi-step forest damage assessment approach that combines Sentinel-2 satellite-based NDVI double-difference analysis with UAV-based high-resolution photogrammetric evaluation. In the first phase, potential damaged forest patches were identified in two sample areas of the Sopron Mountains using double-difference maps derived from monthly window NDVI maxima calculated from Sentinel-2 data. In the second phase, UAV surveys were carried out over the selected forest compartments, resulting in individual-tree-level canopy segmentation and object-based NDVI analysis. The photogrammetric point clouds were combined with ground points derived from airborne laser scanning to enable the accurate generation of canopy height models. The results confirmed that NDVI double-difference analysis is suitable for the spatial detection of both gradual drought-related damage and sudden disturbances—such as forest fire—even under sequences of drought and moderate years occurring in a sporadic pattern. The UAV-based analysis corroborated the satellite observations in detail and enabled an accurate inventory of damaged trees as well as the exploration of their spatial distribution. The proposed methodology provides an efficient, cost-effective, and operational tool for multi-scale monitoring of forest damage, contributing to the timely recognition of climate-change impacts and to the substantiation of targeted forest management interventions. Full article

Background/Objectives: Fire is a dominant ecological force in Mediterranean ecosystems, shaping the adaptive traits of forest species such as Pinus brutia. Prescribed burning (also called controlled burning) is the intentional, carefully planned use of fire under specific environmental conditions to manage vegetation and reduce wildfire risk. While morphological and physiological fire adaptations are well-documented, emerging evidence highlights the role of epigenetic mechanisms—such as DNA methylation and histone modifications—in mediating stress responses. Methods: This study investigates genome-wide epigenetic changes in P. brutia following a prescribed burning experiment on Chios Island, Greece. Using methylation-sensitive amplified polymorphism (MSAP) analysis, we compared temporal shifts on epigenetic profiles before and after fire exposure extracting DNA from the same trees. Results: A significant increase in polymorphic epiloci, epigenetic diversity indices, and private epigenetic bands after prescribed burning was revealed, suggesting a stress-induced reprogramming of the epigenome. Concurrent measurements of midday needle water potential indicated an exploratory association between water stress and epigenetic shifts. Furthermore, Fireline Intensity (FI) correlated with epigenetic diversity index signaling an immediate response of the tree. Conclusions: These findings support the hypothesis that fire stress induces epigenetic responses in P. brutia, potentially enhancing resilience to future environmental challenges. Further research is required to address the level of heritability of these epigenetic changes in next generation and connect these indexes with adaptation and sustainability of forest ecosystems. Full article

Forest fires are a major concern due to their significant impact on the environment, economy, and wildlife habitats. Efficient early detection systems can significantly mitigate their devastating effects. This paper provides a comprehensive review of forest fire detection (FFD) techniques and traces their evolution from basic lookout-based methods to sophisticated remote sensing technologies, including recent Internet of Things (IoT)- and Unmanned Aerial Vehicle (UAV)-based sensor network systems. Historical methods, characterized primarily by human surveillance and basic electronic sensors, laid the foundation for modern techniques. Recently, there has been a noticeable shift toward ground-based sensors, automated camera systems, aerial surveillance using drones and aircraft, and satellite imaging. Moreover, the rise of Artificial Intelligence (AI), Machine Learning (ML), and the IoT introduces a new era of advanced detection capabilities. These detection systems are being actively deployed in wildfire-prone regions, where early alerts have proven critical in minimizing damage and aiding rapid response. All FFD techniques follow a common path of data collection, pre-processing, data compression, transmission, and post-processing. Providing sufficient power to complete these tasks is also an important area of research. Recent research focuses on image compression techniques, data transmission, the application of ML and AI at edge nodes and servers, and the minimization of energy consumption, among other emerging directions. However, to build a sustainable FFD model, proper sensor deployment is essential. Sensors can be either fixed at specific geographic locations or attached to UAVs. In some cases, a combination of fixed and UAV-mounted sensors may be used. Careful planning of sensor deployment is essential for the success of the model. Moreover, ensuring adequate energy supply for both ground-based and UAV-based sensors is important. Replacing sensor batteries or recharging UAVs in remote areas is highly challenging, particularly in the absence of an operator. Hence, future FFD systems must prioritize not only detection accuracy but also long-term energy autonomy and strategic sensor placement. Integrating renewable energy sources, optimizing data processing, and ensuring minimal human intervention will be key to developing truly sustainable and scalable solutions. This review aims to guide researchers and developers in designing next-generation FFD systems aligned with practical field demands and environmental resilience. Full article

Wildland fires, including surface and crown fires, present significant challenges for ecosystems and forest management. Accurate fire modelling is crucial for risk assessment and mitigation strategies. The Fire Dynamics Simulator (FDS) v6.8.0, developed by the National Institute of Standards and Technology (NIST), is a physics-based model that simulates fire behaviour by incorporating advanced physics and chemistry. However, its reliability requires thorough validation. This study validates FDS 6.8.0’s performance in modelling both surface fires and single tree burning. Two separate simulation sets were conducted. For surface fires, pine needle fuel beds were used at a laboratory scale to examine fire behaviour on slopes of 0°, 10°, and 20°. The results were validated against experimental data. A burning Douglas fir tree was simulated, and the results were compared with experimental measurements. The surface fire simulations at 0° and 10° slopes showed strong agreement with experimental data. In single-tree burning, both experimental and simulated results exhibited similar trends, with a rapid increase to a peak mass-loss rate (MLR) followed by a gradual decline. Validating FDS 6.8.0 forms an essential first step toward supporting the investigation of complex wildland fire behaviour, such as surface-to-crown fire transition, canyon fire, and dynamic escalation, using the same FDS version. Full article

Unmanned aerial vehicle (UAV) forest fire detection is vital for forest safety. However, early-stage UAV fire scenarios often involve small targets, weak smoke signals, and strict onboard resource constraints, which pose significant challenges to existing detectors. To improve the speed and accuracy of UAV forest fire detection, this paper proposes a lightweight fire detection algorithm, AHE-YOLO, specifically designed for UAVs. The proposed method adopts a coordinated lightweight design to improve feature preservation and cross-scale representation under limited computational budgets. Specifically, the Adaptive Downsampling (ADown) module preserves shallow fire-related cues during spatial reduction, improving sensitivity to small flame and smoke targets. The high-level screening-feature fusion pyramid network (HS-FPN) introduces cross-scale attention to promote more discriminative multi-level feature interaction while reducing redundant computation. Furthermore, the Efficient Mobile Inverted Bottleneck Convolution (EMBC) module is employed to improve receptive-field efficiency and feature selectivity under lightweight constraints, further enhancing detection accuracy and inference speed. Finally, the performance of AHE-YOLO is comprehensively evaluated through ablation and comparative experiments on the same dataset. The final experimental results show that YOLO-AHE achieves a mean average precision (mAP) of 94.8% while reducing model parameters by 39.7%, decreasing FLOPs by 27.0%, and shrinking the model size by 36.4%. In addition, its inference speed improves by 16.5%. Beyond detection performance, the proposed framework supports sustainable forest monitoring by enabling early fire warning with reduced computational and energy demands, showing strong potential for real-time deployment on resource-constrained UAV and edge platforms. Full article

In August 2023, a large forest fire burned more than 60% of the Dadia–Lefkimi–Soufli Forest National Park in northeastern Greece, following another large fire in 2022. To quantify the effects of these fires on local herpetofauna, we analyzed community composition, abundance, and diversity before and after the 2023 event. Standardized visual encounter surveys were conducted across 29 sites between 2015 and 2024, spanning burned and unburned areas. Species richness, abundance, and diversity metrics, together with Bray–Curtis community dissimilarities, were compared across sampling periods and fire-severity classes. Amphibian assemblages showed high postfire persistence, with 82% of regional species still detected and no significant changes in diversity indices, likely reflecting the buffering role of perennial streams and other hydrologically stable refugia. In contrast, reptile communities showed clear compositional shifts and experienced severe declines: overall reptile species richness decreased to 30% of prefire levels and diversity indices dropped significantly. Tortoises (i.e., Testudo graeca, T. hermanni) declined by nearly 90% relative to prefire estimates, indicating high vulnerability of low-mobility, long-lived species. Snakes were not detected in any burned sites, whereas only a few small-bodied lizards and the freshwater turtle Mauremys rivulata persisted locally. These findings demonstrate that extreme, landscape-scale fires can restructure reptile communities in Mediterranean forests, particularly where long-term habitat change and drought had already reduced population resilience. The study underscores the need for targeted postfire restoration, conservation planning for slow-dispersing taxa, and long-term biodiversity monitoring under increasingly frequent fire regimes. Full article

Lightning is a major natural ignition source of wildfires across forest, grassland, and cropland ecosystems. Accurate prediction of lightning-ignited fire occurrence remains challenging due to uncertainties in spatiotemporal alignment caused by vegetation-dependent smoldering delays and the difficulty of representing heterogeneous fuel conditions in mixed-vegetation regions. This study proposes a semi-automated lightning–fire alignment framework that integrates land cover information and historical fire records to improve spatiotemporal matching across different vegetation types and to reduce misclassification from human-induced fires in agricultural areas. To better characterize fuel conditions, two feature-level vegetation fusion parameters—total vegetation cover and leaf area index weight—are introduced and combined with hourly meteorological variables and lightning characteristics to develop a tuned random forest prediction model. The framework is applied at a regional scale in the Greater Khingan Mountains and southwestern forest regions of China, with predictions conducted at an event-based temporal scale using hourly inputs. The vegetation-fused model achieves an AUC of 0.93, outperforming models without vegetation fusion. Analysis of model outputs indicates that hourly maximum temperature, leaf area index weight, precipitation, and wind speed are key factors influencing lightning-ignited fire occurrence. This study demonstrates the value of semi-automated alignment and vegetation feature fusion for improving lightning-ignited fire prediction in heterogeneous landscapes, supporting regional wildfire risk assessment and potential early-warning applications. Full article

To improve diagnostics and prediction of changes caused by increased impact of anthropogenic activity, it is necessary to increase the comparative analysis of measurements and modeling of ozone—one of the climatically important atmospheric gases due to the decisive influence of stratospheric ozone on the radiation balance of the Earth-atmosphere system and the role of tropospheric ozone, the third most significant anthropogenic factor contributing to the greenhouse effect. This task is particularly relevant for Russia, as its geographical location makes it more vulnerable to climate change than other countries, whereas its regional tendencies in ozone variability have not yet been studied in sufficient detail. An analysis of IKFS-2 tropospheric ozone content (TrOC) measurements for 2015–2022 revealed that in Siberian, Far Eastern, North Caucasian, and Southern federal districts of Russia TrOC maximum, caused by photochemical formation of ground-level ozone, is observed in July (up to 30–35 DU for monthly means in surface-400 hPa layer). In Northwestern federal district, TrOC maximum (up to 25–30 DU), determined by meridional transport, is observed in late spring. No statistically significant linear trends in TrOC are detected. The WRF-Chem model qualitatively describes the seasonal variations of TrOC as well as the anomalous increase in TrOC caused by forest fires. The variability of total ozone content (TOC) is analyzed by OMI (2005–2023) and IKFS-2 (2015–2022) measurements as well as by SOCOLv3 simulations. Ozone negative anomalies in spring (up to 15% for monthly means) are generally observed with positive Arctic oscillation index values and a westerly phase of Quasi-biennial oscillations. For the 2008–2022 period, a statistically significant increase in TOC (+1.6–1.7% per year) is obtained for European Russia and Western and Central Siberia in November. Full article

The 2025 fire season in Portugal was marked by large fires, underscoring the vulnerability of the forested areas to fire. The study analyzes the main meteorological conditions during a critical period of fire activity and addresses the following question: Why can the northeast (NE) weather pattern be so critical for fire danger in Portugal? Fire severity in the Arouca wildfire, the largest fire of the period, was estimated using a methodology that integrates foundation vision models with computer vision algorithms. ECMWF analyses and convection-permitting Meso-NH simulations are used to examine large-scale circulation and the mesoscale environment, respectively. Synoptic-scale analysis revealed the Azores anticyclone centered slightly northwest of the Iberian Peninsula (IP), with its eastern sector directly affecting the northern IP under north/northeast winds. The hectometric-scale simulation demonstrated that orographically enhanced wind gusts over the northern Portuguese mountains substantially intensified near-surface fire-weather conditions when the winds were nearly easterly. Furthermore, strong low-level winds and atmospheric stability constrained vertical plume growth, favoring horizontal smoke transport. In addition, the study highlights that Arouca’s fire had 88% of its area affected with moderate to high severity. Overall, the results demonstrate that the interaction between large-scale NE circulation and local orography plays a decisive role in amplifying fire danger in northern Portugal, emphasizing the need for high-resolution atmospheric modeling to identify fire-prone regions under specific synoptic patterns. Full article

In this study, a deep learning-based multimodal framework is presented for forest fire detection using RGB images, which synthetically generates night-vision-like, white-hot, and green-hot pseudo-thermal representations. The synthetic modalities are derived directly from RGB data and integrated into a hardware-independent multimodal learning pipeline to increase visual diversity without relying on additional sensing hardware. Each modality is processed using an ImageNet-pretrained convolutional backbone, and modality-specific feature vectors are combined through feature-level concatenation before classification. The proposed framework was evaluated using multiple backbone architectures, including ResNet18, EfficientNet-B0, and DenseNet121, which were assessed independently under a unified experimental protocol. Experiments were conducted on two datasets with substantially different scales and characteristics: the FLAME dataset (39,375 images, binary classification) and the FireStage dataset (791 images, three-class classification). For both datasets, stratified 80–20% training–validation splits were employed, and online stochastic data augmentation was applied exclusively to the training sets. On the FLAME dataset, the proposed framework achieved consistently high performance across different backbone and modality configurations. The best-performing models reached an accuracy of 99.66%, precision of 99.80%, recall of 99.66%, F1-score of 99.73%, and ROC AUC value of 0.9998. On the more challenging FireStage dataset, the framework demonstrated stable performance despite limited data availability, achieving an accuracy of 93.71% for RGB-only configurations and up to 93.08% for selected multimodal combinations, while macro-averaged F1-scores exceeded 0.92, and ROC AUC values reached up to 0.9919. Per-class analysis further indicates that early-stage fire (Start Fire) patterns can be discriminated, achieving ROC AUC values above 0.96, depending on the backbone and modality combination. Overall, the results suggest that synthetic-modality-based multimodal learning can provide competitive performance for both large-scale and data-limited fire detection scenarios, offering a flexible and hardware-independent alternative for forest fire monitoring applications. Full article

This study focuses on enhancing wind speed prediction for wildfire spread simulation by proposing an integrated forecasting approach. The original wind speed series is first processed via variational mode decomposition (VMD), with its parameters [K, $\alpha$] optimized via particle swarm optimization (PSO). Every intrinsic mode function (IMF) resulting from this decomposition is predicted using a bidirectional long short-term memory model incorporating an attention mechanism (AM-BiLSTM), and the final wind series is reconstructed from these predictions. Model training and validation were conducted using data from controlled burning experiments in the Mao’er Mountain area of Heilongjiang Province, China. Predictive performance is evaluated through multiple statistical metrics, error distribution analysis, and Taylor diagrams. To assess practical utility, the predicted wind field is further applied in FARSITE to drive wildfire spread simulations. Results demonstrate that the PSO-VMD-AM-BiLSTM model provides reliable wind forecasts and contributes to improved fire spread prediction accuracy, indicating its potential for decision support in wildfire management. To achieve accurate forest fire spread prediction, we construct the MCNN model, which is based on early perception of understory wind fields using predicted wind speed data and adopts a multi-branch convolutional neural network architecture to extract fire spread features. FARSITE is employed to simulate forest fire spread in the Mao’er Mountain region, generating a dataset for model training and testing. After 50 training epochs, the loss value of the MCNN model converges, achieving optimal prediction performance when the combustion threshold is set to 0.7. Compared to models such as CNN, DCIGN, and DNN, MCNN shows improvements in evaluation metrics including precision, recall, Sørensen coefficient, and Kappa coefficient. To validate the model’s predictive performance in real fire scenarios, four field ignition experiments were conducted at the Liutiao Village test site: homogeneous fuel combustion, long fire line combustion, alternating fuel combustion, and multiple ignition source merging combustion. Comprehensive evaluation across the four experiments indicates that the model achieves precision, recall, Sørensen coefficient, and Kappa coefficient values of 0.940, 0.965, 0.953, and 0.940, respectively, with stable prediction errors below 6%. These results represent improvements over the comparative models DCIGN and DNN. The proposed MCNN model can adapt to forest fire spread prediction under different scenarios, offering a novel approach for accurate forest fire prediction and prevention. Full article

Biomass burning aerosols (BBA) released from large-scale wildfires pose a serious threat worldwide, necessitating a comprehensive understanding of their plume characteristics. To address this challenge, this study used satellite data provided by the Second-generation Global Imager (SGLI) aboard the Global Change Observation Mission-C and regional-scale numerical chemical transport model (CTM) simulations to characterize BBA plumes. The SGLI data and CTM simulations were compared and verified, and the 3D characteristics of BBA plumes, including concentration, diffusion range, spatial variation in optical properties, plume top height, and vertical profile, were subsequently derived. In this study, we focused on large-scale forest fires that occurred in western North America in September 2020 and Indonesia in September 2019. In both cases, Aerosol optical thickness (AOT) and Ångström Exponent (AE) values show a positive correlation with the height of the BBA plume top. The results showed that the higher the BBA plume top, the thicker the plume and the smaller the aerosol size. This point is what we particularly wish to highlight in this study. The SGLI polarization data proved useful for characterizing the upper layers of the BBA plumes. By understanding the detailed characteristics at the top of the plume, it is possible to predict the BBA plume’s advection and lifetime. Full article