Search Results (276)

There are significant scale and morphological differences between fire and smoke features in forest fire detection. This paper proposes a detection method based on dual-branch multi-scale adaptive feature fusion network (DMAFNet). In this method, convolutional neural network (CNN) and transformer are used to form a dual-branch backbone network to extract local texture and global context information, respectively. In order to overcome the difference in feature distribution and response scale between the two branches, a feature correction module (FCM) is designed. Through space and channel correction mechanisms, the adaptive alignment of two branch features is realized. The Fusion Feature Module (FFM) is further introduced to fully integrate dual-branch features based on the two-way cross-attention mechanism and effectively suppress redundant information. Finally, the Multi-Scale Fusion Attention Unit (MSFAU) is designed to enhance the multi-scale detection capability of fire targets. Experimental results show that the proposed DMAFNet has significantly improved in mAP (mean average precision) indicators compared with existing mainstream detection methods. Full article

In the United States, ecosystems regularly experience wildfires and as fire seasons lengthen, fires are becoming a more important disturbance. While all types of disturbance have impacts on the carbon cycle, fires result in immediate emissions into the atmosphere. To assist managers in assessing wildland fire impacts, particularly on federally managed land, we developed estimates of area burned and related emissions for a 21-year period. These estimates are based on wildland fires defined by the interagency Monitoring Trends in Burn Severity database; emissions are simulated through the Wildland Fire Emissions Inventory System; and the classification of public land is performed according to the US Geological Survey’s Protected Areas Database of the United States. Wildland fires on federal land contributed 62 percent of all annual CO₂ emissions from wildfires in the United States between 2001 and 2021. During this period, emissions from the forest fire subset of wildland fires ranged from 328 Tg CO₂ in 2004 to 37 Tg CO₂ in 2001. While forest fires averaged 38 percent of burned area, they represent the majority—59 to 89 percent of annual emissions—relative to fires in all ecosystems, including non-forest. Wildland fire emissions on land belonging to the federal government accounted for 44 to 77 percent of total annual fire emissions for the entire United States. Land managed by three federal agencies—the Forest Service, the Bureau of Land Management, and the Fish and Wildlife Service—accounted for 93 percent of fire emissions from federal land over the course of the study period, but year-to-year contributions varied. Full article

Wildfires accelerate soil erosion. Preventive fuel management and post-fire control measures are two distinct strategies that can be used to mitigate wildfire-induced soil loss with varying effectiveness and costs. Here, we quantified the impacts and effectiveness of pre- versus post-fire treatment strategies on soil loss mitigation. We coupled fire simulations with soil erosion modelling to estimate annual wildfire-induced soil loss for two watersheds in Portugal. We identified optimal treatment locations with the aim of maximizing the reduction in soil loss, and estimated treatment effectiveness using treatment leverage and cost-effectiveness. Both mitigation strategies were predicted to reduce post-fire soil loss, with effects increasing with treatment extent. Treatments had a strong mitigation effect particularly in extreme fire years. Results indicated that there was no single mitigation strategy that fits all watersheds, and the choice was largely influenced by wildfire and treatment frequency. For the most fire-prone watershed, Castelo de Bode, fuel treatments were the most effective strategy, being approximately 2-fold cheaper and more effective than post-fire treatments. Treatments were more effective and exhibited lower variability in years with higher soil loss. Our results show that the most cost-effective combinations of treatment strategies vary with the soil loss reduction objective. Relevant treatment synergies were identified that can help land managers to maximize the attainment of soil loss mitigation goals ensuring the best use of resources. This work contributes to a better understanding of how post-fire soil loss can be mitigated, contributing for better resource allocation while maximizing specific management goals. Full article

Forest harvesting can alter sedimentary processes in catchments by reducing vegetation cover and exposing the soil surface. To mitigate these effects, post-harvest residue management is commonly used, though its effectiveness needs individual evaluation. This study assessed how windrowed harvest residues influence structural sediment connectivity in two forest catchments in south-central Chile with a Mediterranean climate. Using digital terrain models and the Index of Connectivity, scenarios with and without windrows were compared. Despite similar windrow characteristics, effectiveness varied between catchments. In catchment N01 (12.6 ha, average slope 0.28 m m⁻¹), with 13.6% windrow coverage, connectivity remained unchanged, but in contrast, catchment N02 (14 ha, average slope 0.27 m m⁻¹), with 21.9% coverage, showed a significant connectivity reduction. A key factor was windrows’ orientation: 83.9% aligned with contour lines in N02 versus 58.6% in N01. Distance to drainage channels also played a role, with the decreasing effect of connectivity at 50–60 m in N02. Bootstrap analysis confirmed significant differences between catchments. These results suggest that windrow configuration, particularly contour alignment, may be more critical than coverage percentage. For effective connectivity reduction, especially on moderate to steep slopes, forest managers should prioritize contour-aligned windrows. This study enhances our understanding of structural sediment connectivity and offers practical insights for sustainable post-harvest forest management. Full article

Typhoons are major climate disturbances that significantly impact coastal ecosystems, particularly mangrove forests. This study examines the effects of typhoons on mangrove communities at different stages of recovery, focusing on how environmental factors influence carbon storage and net ecosystem exchange (NEE). Three mangrove sites were selected based on their recovery age: young, moderately restored, and mature. The results revealed that typhoons had the most pronounced effect on young mangroves, resulting in significant reductions in both above-ground and soil carbon storage. In contrast, mid-aged and mature mangroves demonstrated greater resilience, with mature mangroves recovering most rapidly in terms of community structure and carbon storage. Key factors such as wind speed, heavy rainfall, and changes in photosynthetically active radiation (PAR) contributed to carbon storage losses, particularly in young mangrove forests. This study underscores the importance of recovery age in determining mangrove resilience to extreme weather events and offers insights for enhancing restoration and conservation strategies to mitigate the impacts of climate change on coastal carbon sequestration. Full article

Understanding and mapping forest fire vulnerability is essential for informed landscape management and disaster risk reduction, especially in the context of increasing anthropogenic and climatic pressures. This study aims to model and spatially predict forest fire vulnerability across Romania using two machine learning algorithms: MaxEnt and XGBoost. We integrated forest fire occurrence data from 2006 to 2024 with a suite of climatic, topographic, ecological, and anthropogenic predictors at a 250 m spatial resolution. MaxEnt, based on presence-only data, achieved moderate predictive performance (AUC = 0.758), while XGBoost, trained on presence–absence data, delivered higher classification accuracy (AUC = 0.988). Both models revealed that the impact of environmental variables on forest fire occurrence is complex and heterogeneous, with the most influential predictors being the Fire Weather Index, forest fuel type, elevation, and distance to human proximity features. The resulting vulnerability and uncertainty maps revealed hotspots in Sub-Carpathian and lowland regions, especially in Mehedinți, Gorj, Dolj, and Olt counties. These patterns reflect historical fire data and highlight the role of transitional agro-forested landscapes. This study delivers a replicable, data-driven approach to wildfire risk modelling, supporting proactive management and emphasising the importance of integrating vulnerability assessments into planning and climate adaptation strategies. Full article

Wildfires are becoming an increasingly severe threat to European forests, driven by climate change, land use changes, and socio-economic factors. Integrated solutions for wildfire prevention, early detection, emergency management, and ecological restoration are urgently needed to enhance forest resilience. The Horizon 2020 SILVANUS project developed a comprehensive multi-sectoral platform combining technological innovation, stakeholder engagement, and sustainable forest management strategies. This report analyses the Slovak Republic’s participation in SILVANUS, applying a seven-criterion fit–gap framework (governance, legal, interoperability, staff capacity, ecological suitability, financial feasibility, and stakeholder acceptance) to evaluate the platform’s alignment with national conditions. Notable contributions include stakeholder-supported functional requirements for wildfire prevention, climate-sensitive forest models for long-term adaptation planning, IoT- and UAV-based early fire detection technologies, and decision support systems (DSS) for emergency response and forest-restoration activities. The Slovak pilot sites, particularly in the Podpoľanie region, served as important testbeds for the validation of these tools under real-world conditions. All SILVANUS modules scored ≥12/14 in the fit–gap assessment; early deployment reduced high-risk fuel polygons by 23%, increased stand-level structural diversity by 12%, and raised the national Sustainable Forest Management index by four points. Integrating SILVANUS outcomes into national forestry practices would enable better wildfire risk assessment, improved resilience planning, and more effective public engagement in wildfire management. Opportunities for adoption include capacity-building initiatives, technological deployments in fire-prone areas, and the incorporation of DSS outputs into strategic forest planning. Potential challenges, such as technological investment costs, inter-agency coordination, and public acceptance, are also discussed. Overall, the Slovak Republic’s engagement with SILVANUS demonstrates the value of participatory, technology-driven approaches to sustainable wildfire management and offers a replicable model for other European regions facing similar challenges. Full article

This study used Jilin-1 satellite data and unmanned aerial vehicle (UAV)-collected visible-thermal infrared imagery to calculate twelve spectral indices and evaluate their effectiveness in distinguishing post-fire forest areas and identifying human-altered land-cover changes in Jinyun Mountain, Chongqing. The research goals included mapping wildfire impacts with M-statistic separability, measuring land-cover distinguishability through Jeffries–Matusita (JM) distance analysis, classifying land-cover types using the random forest (RF) algorithm, and verifying classification accuracy. Cumulative human disturbances—such as land clearing, replanting, and road construction—significantly blocked the natural recovery of burn scars, and during long-term human-assisted recovery periods over one year, the Red Green Blue Index (RGBI), Green Leaf Index (GLI), and Excess Green Index (EXG) showed high classification accuracy for six land-cover types: road, bare soil, deadwood, bamboo, broadleaf, and grass. Key accuracy measures showed producer accuracy (PA) > 0.8, user accuracy (UA) > 0.8, overall accuracy (OA) > 90%, and a kappa coefficient > 0.85. Validation results confirmed that visible-spectrum indices are good at distinguishing photosynthetic vegetation, thermal bands help identify artificial surfaces, and combined thermal-visible indices solve spectral confusion in deadwood recognition. Spectral indices provide high-precision quantitative evidence for monitoring post-fire land-cover changes, especially under human intervention, thus offering important data support for time-based modeling of post-fire forest recovery and improvement of ecological restoration plans. Full article

(1) Background: Changes in the spatial, temporal, and magnitude-related patterns of fires caused by humans are expected to exacerbate with climate change, significantly impacting ecosystems and societies worldwide. However, our understanding of fire regimes in many regions remains limited, largely due to the inherent complexity of fire as an ecological process. Pyrogeography, combined with unsupervised learning methods and the availability of long-term satellite data, offers a robust framework for approaching this problem. The purpose of the study is to identify the pyroregions of the Argentine Gran Chaco, the world’s largest continuous tropical dry forest region. (2) Methods: Using globally available fire occurrence datasets, we computed five fire metrics, related to the extent, frequency, intensity, size, and seasonality of fires at three spatial scales (5, 10, and 25 km). In addition, we tested two widely used cluster algorithms, the K-means algorithm and the Gaussian Mixture Model (GMM). (3) Results and Discussion: The identification of pyroregions was dependent on the clustering algorithm and scale of analysis. The GMM algorithm at a 25 km scale ultimately demonstrated more coherent ecological and spatial distributions. GMM identified six pyroregions, which were labeled based on three metrics in the following order: annual burned area (categorized in low, regular or high), interannual variability of fire (rare, occasional, frequent), and fire intensity (low, moderate, intense). The values were as follows: LRM (22% of study area), ROI (19%), ROM (14%), LOM (10%), ROL (9%), and HFL (4%). (4) Conclusions: Our study provides the most comprehensive delineation of the Argentine Gran Chaco’s Dry Forest pyroregions to date, and highlights both the importance of determining the optimal scale of analysis and the critical role of clustering algorithms in efforts to accurately characterize the diverse attributes of fire regimes. Furthermore, it emphasizes the importance of integrating fire ecology principles and fire management perspectives into pyrogeographic studies to ensure a more comprehensive and meaningful characterization of fire regimes. Full article

Accurate real-time tracking of forest fires using UAV platforms is crucial for timely early warning, reliable spread prediction, and effective autonomous suppression. Existing detection-based multi-object tracking methods face challenges in accurately associating targets and maintaining smooth tracking trajectories in complex forest environments. These difficulties stem from the highly nonlinear movement of flames relative to the observing UAV and the lack of robust fire-specific feature modeling. To address these challenges, we introduce AO-OCSORT, an association-optimized observation-centric tracking framework designed to enhance robustness in dynamic fire scenarios. AO-OCSORT builds on the YOLOX detector. To associate detection results across frames and form smooth trajectories, we propose a temporal–physical similarity metric that utilizes temporal information from the short-term motion of targets and incorporates physical flame characteristics derived from optical flow and contours. Subsequently, scene classification and low-score filtering are employed to develop a hierarchical association strategy, reducing the impact of false detections and interfering objects. Additionally, a virtual trajectory generation module is proposed, employing a kinematic model to maintain trajectory continuity during flame occlusion. Locally evaluated on the 1080P-resolution FireMOT UAV wildfire dataset, AO-OCSORT achieves a 5.4% improvement in MOTA over advanced baselines at 28.1 FPS, meeting real-time requirements. This improvement enhances the reliability of fire front localization, which is crucial for forest fire management. Furthermore, AO-OCSORT demonstrates strong generalization, achieving 41.4% MOTA on VisDrone, 80.9% on MOT17, and 92.2% MOTA on DanceTrack. Full article

Wildfires, whether natural or human-caused, significantly alter soil properties and increase soil erosion susceptibility, particularly through changes in rill detachment capacity (Dc). This study aimed to evaluate the influence of fire intensity on key soil properties and to recognize their relationships with Dc under controlled laboratory conditions. The research was conducted in the Darestan Forest, Guilan Province, northern Iran, a region characterized by a Mediterranean semi-arid climate. Soil samples were collected from three fire-affected conditions: unburned (NF), low-intensity fire (LF), and high-intensity fire (HF) zones. A total of 225 soil samples were analyzed using flume experiments at five slope gradients and five flow discharges, simulating rill erosion. Soil physical and chemical characteristics were measured, including hydraulic conductivity, organic carbon, sodium content, bulk density, and water repellency. The results showed that HF soils significantly exhibited higher rill detachment capacity (1.43 and 2.26 times the values compared to the LF and NF soils, respectively) and sodium content and lower organic carbon, hydraulic conductivity, and aggregate stability (p < 0.01). Strong correlations were found between Dc and various soil properties, particularly a negative relationship with organic carbon. The multiple linear equation had good accuracy (R² > 0.78) in predicting rill detachment capacity. The findings of the current study show the significant impact of fire on soil degradation and rill erosion potential. The study advocates an urgent need for effective post-fire land management, erosion control, and the development of sustainable soil restoration strategies. Full article

Timely and accurate detection of forest fires is crucial for protecting forest ecosystems. However, traditional monitoring methods face significant challenges in effectively detecting forest fires, primarily due to the dynamic spread of flames and smoke, irregular morphologies, and the semi-transparent nature of smoke, which make it extremely difficult to extract key visual features. Additionally, deploying these detection systems to edge devices with limited computational resources remains challenging. To address these issues, this paper proposes a lightweight hybrid receptive field model (LHRF-YOLO), which leverages deep learning to overcome the shortcomings of traditional monitoring methods for fire detection on edge devices. Firstly, a hybrid receptive field extraction module is designed by integrating the 2D selective scan mechanism with a residual multi-branch structure. This significantly enhances the model’s contextual understanding of the entire image scene while maintaining low computational complexity. Second, a dynamic enhanced downsampling module is proposed, which employs feature reorganization and channel-wise dynamic weighting strategies to minimize the loss of critical details, such as fine smoke textures, while reducing image resolution. Furthermore, a scale weighted Fusion module is introduced to optimize multi-scale feature fusion through adaptive weight allocation, addressing the issues of information dilution and imbalance caused by traditional fusion methods. Finally, the Mish activation function replaces the SiLU activation function to improve the model’s ability to capture flame edges and faint smoke textures. Experimental results on the self-constructed Fire-SmokeDataset demonstrate that LHRF-YOLO achieves significant model compression while further improving accuracy compared to the baseline model YOLOv11. The parameter count is reduced to only 2.25M (a 12.8% reduction), computational complexity to 5.4 GFLOPs (a 14.3% decrease), and mAP50 is increased to 87.6%, surpassing the baseline model. Additionally, LHRF-YOLO exhibits leading generalization performance on the cross-scenario M4SFWD dataset. The proposed method balances performance and resource efficiency, providing a feasible solution for real-time and efficient fire detection on resource-constrained edge devices with significant research value. Full article

Extreme wildfire events (EWEs) are becoming increasingly frequent in Mediterranean regions, posing significant threats to ecosystems. This study aimed to support post-fire restoration planning by developing a prioritization framework that categorizes areas according to different levels of vulnerability to the adverse impacts of EWEs. We developed a multi-criteria decision analysis (MCDA) approach to classify these areas within a fire perimeter. The process begins with the collection of available spatial data to assess the pre- and post-fire conditions. Following this, a set of criteria and sub-criteria was established through a participatory approach with local stakeholders. The analytic hierarchy process (AHP) was used to determine stakeholders’ preferences, which were then processed using the Criterium Decision Plus (CDP) version 4 software to support problem modeling. A combined consistency check was applied to ensure both individual coherence and group agreement. Finally, the methodology was integrated using the Ecosystem Management Decision Support (EMDS) software version 9, resulting in a spatial prioritization map that visually represents the levels of restoration priority and serves as a decision-support tool for post-fire restoration planning. Both the process and its results are discussed for an application to a large fire perimeter in the Vale do Sousa forested landscape. Full article

Forest fire detection is vital for ecological conservation and disaster management. Existing visual detection methods exhibit instability in smoke-obscured or illumination-variable environments. Although multimodal fusion has demonstrated potential, effectively resolving inconsistencies in smoke features across diverse modalities remains a significant challenge. This issue stems from the inherent ambiguity between regions characterized by high temperatures in infrared imagery and those with elevated brightness levels in visible-light imaging systems. In this paper, we propose MCDet, an RGB-T forest fire detection framework incorporating target-aware fusion. To alleviate feature cross-modal ambiguity, we design a Multidimensional Representation Collaborative Fusion module (MRCF), which constructs global feature interactions via a state-space model and enhances local detail perception through deformable convolution. Then, a content-guided attention network (CGAN) is introduced to aggregate multidimensional features by dynamic gating mechanism. Building upon this foundation, the integration of WIoU further suppresses vegetation occlusion and illumination interference on a holistic level, thereby reducing the false detection rate. Evaluated on three forest fire datasets and one pedestrian dataset, MCDet achieves a mean detection accuracy of 77.5%, surpassing advanced methods. This performance makes MCDet a practical solution to enhance early warning system reliability. Full article

Our research examines the dynamics of policy implementation in forest fire management and how local governments in Indonesia can successfully implement these policies. There are two main issues: first, the extent to which forest fire management practices are collaborative, which we assess by examining whether government implementation has focused on developing integrated forest fire management policies represented through collaborative networks. Second, we consider whether and how governments and other competing stakeholders move from conflict to collaboration to enable policy implementation. This research explores whether and how collaborative management can provide a foundation for successful forest fire management, particularly in Riau Province, Sumatra, Indonesia, an area that has experienced significant forest fires and expansion of plantations and oil palm industries. Data were collected through in-depth interviews and observations. We revealed a lack of coordination among local, central, and other stakeholders, which might result in policy “tyranny”. In order to effectively reduce the number of fires, the government needs to empower those responsible for fire prevention through law and policy. However, because forest fire management is inherently top-down and often excludes lower levels of bureaucracy, collaborative management remains challenging. Full article