Search Results (3,154)

Monitoring forest density is essential for understanding ecosystem health, wildfire risk, and post-disturbance recovery. This study proposes a robust methodology to extract forest density classes exclusively using Sentinel-2 multispectral imagery combined with vegetation indices (VIs), textural parameters, and spatial clustering metrics. The approach was applied to the northern part of Euboea Island, Greece, as a pilot area severely affected by a wildfire in August 2021. Four cloud-free Sentinel-2 images (2017–2024) were selected to capture pre- and post-fire conditions. A set of nine VIs—representing vegetation vigor, chlorophyll content, soil exposure, and canopy moisture—were calculated and statistically assessed for independence. To enhance classification accuracy, texture measures (homogeneity, correlation, and entropy) and spatial autocorrelation metrics (Moran’s I, Getis-Ord Gi) were derived for selected VIs. Supervised classification was performed using the Maximum Likelihood algorithm, yielding overall accuracies up to 89.4% and kappa coefficients above 0.85 when combining VIs with texture and spatial metrics. Results revealed a dramatic 49.3% reduction in forest cover immediately after the wildfire, with partial recovery (to 77.9% of pre-fire levels) three years later, mainly as a low-density forest. Approximately 12.1% of forest cover failed to regenerate, indicating potential long-term ecosystem degradation. The proposed approach provides a computationally efficient, high-accuracy alternative to data-fusion methods involving (Light Detection and Ranging) LiDAR or (Synthetic Aperture Radar) SAR datasets, making it suitable for operational forest monitoring and fire-risk management. Full article

Wildfires are a major natural hazard causing extensive ecological damage and endangering human survival. Previous studies on wildfires in China have mostly focused on specific regions or individual drivers, with limited systematic assessments at the long-term and national scales. The spatiotemporal patterns of wildfires and their multiple driving mechanisms under China’s diverse climatic regimes remain insufficiently understood. To bridge this gap, we combined MCD64A1 burned area data (2001–2023) with multi-source natural (meteorological, vegetation, and topographic) and anthropogenic factors, using random forest models at both the national and regional scales to examine the spatiotemporal patterns, dominant drivers, and response mechanisms of wildfires in China. The results revealed that: (1) Spatially, wildfires were concentrated in northeastern and southern China, which accounted for 86.20% of the total burned area. Temporally, northern wildfires were primarily a spring-dominated fire regime, with peak activity in March and April, whereas southern wildfires were winter-dominated, peaking in February. (2) At the national scale, elevation was the key topographic factor influencing wildfire occurrence (relative importance = 0.49), with low-elevation and gentle-slope areas being more fire-prone. At the regional scale, the driving factors exhibit spatial differentiation, forming a spatial pattern of topography-dominated and climate-dominated. (3) Partial dependence plot analysis revealed nonlinear and threshold responses. Fire probability increases rapidly when the soil moisture is below 20 mm, while extremely high land surface temperatures in arid regions suppress fire occurrence due to fuel limitations. This study enhances the understanding of spatially heterogeneous wildfire drivers in China and provides a scientific basis for region-specific wildfire prevention and management strategies. Full article

Forest fires occur frequently in China; however, the complex terrain and incomplete road networks severely constrain ground rescue efficiency. Accurate forest road information is essential for the optimization of emergency response and rescue force deployment. Existing road extraction algorithms are primarily designed for urban environments and exhibit limited efficacy in forest scenarios due to dense canopy, complex background interference and specific forest road features. To address this gap, this study proposes a forest road extraction method based on an enhanced DeepLabv3+ model using multi-temporal, high-resolution satellite imagery. Specifically, a Multi-Scale Channel Attention (MCSA) mechanism is embedded in skip connections to suppress background interference, while strip pooling is integrated into the Atrous Spatial Pyramid Pooling (ASPP) module to better capture slender road features. A composite Focal-Dice loss function is also constructed to mitigate sample imbalance. Finally, by applying the model in multi-temporal remote sensing images, a fusion strategy is introduced to integrate multi-seasonal road masks to enhance overall accuracy and topological integrity. Experimental results show that the proposed method achieves a precision of 54.1%, an F1-Score of 59.3%, and an IoU of 41.8%, effectively enhancing road continuity and providing robust technical support for fire-rescue decision-making. Full article

We revisit a hyperbolic wildfire model based on reaction–diffusion dynamics with relaxation effects and extend it by incorporating an advection transport term that accounts for wind-driven fire spread. After a planar two-dimensional reformulation and non-dimensionalization of the model, the analysis is restricted to the minimal ignition regime characterized by the presence of a logistic reaction term governing the evolution of the fire-affected tree fraction. The focus of the study is to assess the influence of the effective wind velocity on the propagation dynamics of the fire-affected tree fraction. For this purpose, analytical solutions of the extended wildfire model are derived by applying the Simple Equations Method (SEsM) in its (1,1) variant using a Riccati-type ordinary differential equation as a simple equation. The obtained families of exact solutions describe physically relevant transition fronts connecting fire-unaffected and fully fire-affected states, or vice versa. Numerical simulations of the derived analytical solutions are performed to demonstrate how the internal front thickness and the profile morphology depend on the specific variant of the Riccati-type solution and on the magnitude of the effective wind velocity. A phase-plane stability and bifurcation analysis of the reduced traveling wave system is carried out. Hopf bifurcation thresholds with respect to the effective wind velocity parameter are identified, revealing transitions between monotone front propagation and oscillatory regimes. A regime map is constructed in the parameter plane spanned by the effective wind velocity and the traveling wave speed. This regime diagram delineates regions of qualitatively different propagation behavior, including monotone advancing fronts, possible oscillatory regimes, and regimes in which traveling wave fronts cease to exist. Full article

Against the backdrop of climate change, forest fires increasingly undermine ecosystem stability and reshape species distributions in Heilongjiang Province. Therefore, quantifying the drivers of fire occurrence and conducting long-term fire risk forecasting holds critical value for regional ecological security. Centered on the forested regions of Heilongjiang Province, this study systematically assessed the relative contributions of multi-source factors—including topography, vegetation, and meteorological conditions—to fire occurrence and compared the predictive performance of three models: Deep Neural Network with Residual Connections (ResDNN), Artificial Neural Network (ANN), and Support Vector Machine (SVM). Modeling results based on historical fire records indicated that the ResDNN model achieved the highest accuracy (85.6%). Owing to its robust nonlinear mapping capability, it performed better in capturing complex feature interactions than ANN and SVM. These results demonstrate its strong applicability to forest fire prediction in Heilongjiang Province. Building on these findings, the study employed the best-performing ResDNN model in conjunction with CMIP6 multi-model climate projections to simulate and map the spatiotemporal probability of forest fire occurrence from 2030 to 2070. The results provide an intuitive representation of long-term fire-risk trajectories under future climate scenarios and offer scientific support for regional fire prevention, monitoring, early-warning systems, and forest management under climate change. Full article

The 2022 Chongqing wildfires, occurring during an unprecedented heatwave, severely degraded subtropical forest ecosystems and disrupted hydrological cycling. We developed an integrated artificial intelligence framework combining Long Short-Term Memory and Transformer architectures to simulate post-fire evapotranspiration (ET) dynamics using 37 months of field observations (2022–2025) across 24 plots with four burn severities. The Penman–Monteith–Leuning model provided physically based benchmarks. Results revealed three distinct recovery phases: destruction/stagnation (0–7 months, ET at 6%–10% of pre-fire levels), rapid recovery (8–19 months), and stabilization (20–37 months, reaching 100% ET recovery). The coupled LSTM–Transformer ensemble achieved superior performance (RMSE = 0.10 mm·day⁻¹, NSE = 0.98), outperforming single models by 31% in uncertainty reduction. SHAP analysis identified phase-dependent factor shifts: soil water content dominated Stage I (42.5%), while leaf area index (LAI) controlled Stages II–III (>48%). A bimodal LAI time-lag effect emerged: 4–7 days (leaf water potential equilibrium, 27.7% contribution) and 8–14 days (root uptake compensation, 21.7%). Burn severity significantly extended time-lags (severe burns: 12/21 days vs. unburned: 5/12 days), indicating hydraulic system reconstruction requirements. Despite equivalent LAI recovery, severe burns maintained 12%–15% ET reduction, suggesting lasting hydraulic limitations. This study demonstrates that physics-constrained AI models effectively capture complex post-fire ecohydrological dynamics while providing mechanistic interpretability, advancing understanding of vegetation–water coupling reconstruction under increasing fire frequency. Full article

Wildfires at the wildland–urban interface (WUI) have increased in frequency and severity under global warming and intensified human activities. As a representative high-altitude mountainous region in southwestern China, Yunnan features complex topography, steep climatic gradients, and dispersed settlements interwoven with wildlands, making it a fire-prone area where wildfire management is particularly challenging. However, a fine-scale WUI dataset is currently lacking for this region. To address this gap, we refined WUI classification thresholds using a one-factor-at-a-time (OFAT) method and generated the first fine-resolution WUI map of Yunnan. Seasonal wildfire driving factors from 2004 to 2023 were quantified, and machine learning models were applied to produce seasonal susceptibility maps. SHapley Additive exPlanations (SHAP) were employed to interpret the dominant contributing factors. The resulting WUI covers 25,730.67 km², accounting for 6.5% of Yunnan’s land area. Random forest models effectively captured seasonal wildfire susceptibility patterns, with AUC values exceeding 0.83 across all seasons. High susceptibility zones (>0.5) comprised 30.09% of the WUI in spring, 25.74% in winter, 22.61% in autumn, and 13.74% in summer. SHAP analysis revealed that anthropogenic factors consistently drive wildfire occurrence, while climatic conditions in the preceding season influence vegetation status and subsequently affect wildfire likelihood in the current season. By integrating static “where” mapping with dynamic “when” susceptibility analysis, this study establishes a comprehensive “When–Where” framework that supports both long-term WUI planning and short-term seasonal early warning. The integration of fine scale WUI mapping with seasonal susceptibility modeling enhances wildfire risk management in complex high-altitude regions. These findings provide a scientific basis for location-specific, time-sensitive, and full-chain wildfire management in mountainous landscapes and contribute to cross-border ecological security governance in the Indo-China Peninsula. Full article

The increasing frequency of global forest fires necessitates rapid and accurate detection methods. This study proposes a forest fire detection and segmentation framework based on the MST++ hyperspectral reconstruction model to improve the accuracy and robustness of wildfire monitoring under complex environmental conditions. The proposed method first reconstructs hyperspectral images from RGB inputs using an MST++ model trained on the NTIRE 2022 RGB-to-hyperspectral dataset (950 paired samples), followed by fire and smoke segmentation based on spectrally sensitive bands. For segmentation experiments, 118 flame images from the BoWFire dataset and 100 manually annotated smoke images from public datasets (D-Fire and DFS) were used. Quantitative results demonstrate that the proposed MST++-based method significantly outperforms the conventional U-Net baseline. In flame segmentation, MST++ achieved an IoU of 76.90%, an F1 score of 86.81%, and a Kappa coefficient of 0.8603, compared to 44.42%, 58.15%, and 0.5625 for U-Net, respectively. For smoke segmentation, MST++ achieved an IoU of 91.76% and an F1 score of 95.66%, surpassing U-Net by 17.08% and 10.32%, respectively. In fire–smoke overlapping scenarios, MST++ maintained strong robustness, achieving an IoU of 89.64% for smoke detection. These results indicate that hyperspectral reconstruction enhances discrimination capability among flame, smoke, and complex backgrounds, particularly under low-light and overlapping conditions. The proposed framework provides a reliable and efficient solution for early forest fire detection and demonstrates the potential of hyperspectral reconstruction approaches in disaster monitoring applications. Full article

High-precision and real-time monitoring of forest fires is a critical requirement in disaster prevention and mitigation. During fire evolution, significant stage-wise variations occur, which make it difficult for conventional semantic segmentation models to simultaneously achieve robust multi-scale feature extraction and strong interference resistance. To address this issue, this paper proposes a stage-aware multi-head segmentation network, termed SAMS-Net. The proposed network decouples fire-stage recognition from pixel-level segmentation and employs a Hard-Switch Routing mechanism to dynamically activate the stage-specific decoder that matches the current fire phase during inference, while pruning irrelevant branches to reduce computational redundancy. Experimental results show that SAMS-Net achieves 76.16% mIoU, 81.30% Dice, and 90.31% PA, outperforming mainstream segmentation models such as FCN, U-Net++, DeepLabV3, and YOLOv9-Seg. In challenging stages, particularly the early and recession phases, the segmentation performance improves by more than 10% compared with the second-best model. Meanwhile, the proposed method maintains high accuracy with a real-time inference speed of 75.8 FPS. These results support the effectiveness of SAMS-Net for flame-and-ember foreground segmentation on the constructed multi-stage forest-fire benchmark dataset. Broader generalization across independent datasets and real-world deployment scenarios will be further investigated in future work. Full article

A substantial proportion of wildfires in Mediterranean regions continue to be recorded without information about the cause or source of ignition, limiting our ability to understand ignition drivers and design effective prevention strategies. In this study, we develop a spatially harmonised wildfire database for mainland Spain by integrating ignition records from the Spanish General Fire Statistics (EGIF) with fire perimeters generated from satellite images. We then apply a Random Forest classifier to infer ignition causes for events lacking cause attribution. To interpret model behaviour, we use Shapley Additive Explanation (SHAP) values at both global and local scales. Results indicate that human-caused ignitions are dominant, with intentional and negligence-related fires accounting for 52.13% of all known events, although they are associated with contrasting climatic and land-use settings. Negligence-related fires tend to occur under hot, dry and windy conditions, often in agricultural interfaces, whereas intentional fires are more frequent under cooler and wetter conditions and in areas with higher population density and land-use change. Lightning-caused fires represent a small fraction of total ignitions (3%) but exhibit a distinct climatic signature, occurring primarily in sparsely populated areas, under intermediate moisture conditions, and often leading to larger burned areas. Despite strong overall model performance (F1-score = 0.82), minority classes (e.g., lightning and fire rekindling, 0.17%) remain challenging to classify, reflecting both data imbalance and uncertainty in causal attribution. Overall, the combined use of machine learning and explainable AI provides a coherent spatial characterisation of wildfire ignition drivers across mainland Spain, highlights systematic differences among ignition causes, and identifies key limitations in existing fire cause records. This framework represents a practical step towards improving fire cause information by integrating remote sensing products with field-based fire reports, thereby supporting more targeted and evidence-based fire risk management. Full article

Community land management plays an important role in wildfire-prone landscapes in Mediterranean Europe. However, in Portugal, information on the spatial extent and boundaries of community land remains fragmented across multiple institutions. This study addresses a critical but often overlooked issue in wildfire management: the fragmentation of institutional data on community land boundaries in mainland Portugal and its direct implications for forest fire risk management, planning, and accountability. We harmonized georeferenced datasets from various government and public institutions, applying multi-institutional spatial integration supported by legal land use criteria using the Land Use Land Cover map 2018 (LULC2018). The resulting national map represents the first fully harmonized spatial assessment of community land (baldios) in mainland Portugal. Our results show that baldios currently occupy approximately 595 thousand hectares, significantly exceeding official estimates. Of this total, around 74% are under partial forest regime law, and approximately 76% are classified as having a high or very high wildfire hazard. This means that three out of every four hectares of baldios in mainland Portugal are structurally susceptible to extreme wildfire conditions. Beyond improving cartographic data, the study’s findings demonstrate how the lack of land registry weakens the institutional foundations for community-based wildfire management. Without a functional, legally validated national map of community land boundaries, responsibilities, co-management mechanisms, and prevention measures remain spatially inconsistent. Full article

Fire detection is a critical task for early warning systems, particularly in environments where visual sensing is unreliable. While most existing approaches rely on image-based or smoke-based detection, acoustic signals provide complementary information capable of capturing early combustion-related events. This study investigates deep learning models for sound-based fire detection, focusing on convolutional and Transformer-based architectures. VGG16 and VGG19 convolutional neural networks are adapted to process time-frequency audio representations for binary classification into Fire and No-Fire classes. An Audio Spectrogram Transformer (AST) is further employed to model long-range temporal dependencies in acoustic data. Finally, a hybrid VGG19-AST architecture is proposed, in which convolutional layers extract local spectral–temporal features, and Transformer-based self-attention performs global sequence modeling. The models are evaluated on a curated dataset containing fire sounds and diverse environmental background noises under multiple noise conditions. Experimental results demonstrate competitive performance across convolutional and Transformer-based models, while the proposed hybrid VGG19-AST architecture achieves the most consistent overall results. The findings suggest that integrating convolutional feature extraction with self-attention-based global modeling enhances robustness under complex acoustic variability. The proposed hybrid framework provides a scalable and cost-effective solution for sound-based fire detection, particularly in scenarios where visual monitoring may be obstructed or ineffective. Full article

This study presents a comprehensive wildfire risk assessment framework for Rhodes Island, Greece, aimed at quantifying the impacts of climate change on hazard levels and vulnerability in a typical Mediterranean environment. The approach integrates Fire Weather Index (FWI) data, detailed fuel-type mapping, and multiple vulnerability indicators covering ecological, socioeconomic, and population factors, enabling spatially explicit estimates of current and future wildfire risk. Historically, Rhodes mostly faces moderate wildfire risk, mainly in central and northeastern regions, with localised areas of higher risk near settlements and key economic sites. Climate forecasts for 2025–2049 predict a notable increase in hazard, with areas experiencing extreme fire weather (FWI > 50) increasing from 15.19% to 66–72%, across all emission scenarios. Ecological vulnerability is particularly alarming, as 93% of the island is already highly susceptible; fire-prone forest and agricultural zones are expected to move into the highest ecological risk categories, especially in the central mountain areas. The devastating 2023 wildfire, which burned over 17,600 hectares, caused more than €5.8 million in direct damages and led to the largest evacuation in the island’s history, closely aligning with high-risk zones modelled in the framework. An important insight is the limited spatial variation in near-future risk between RCP 4.5 and RCP 8.5, indicating that significant wildfire intensification is largely unavoidable by mid-century, emphasising the urgent need for quick adaptation and risk mitigation efforts for Mediterranean critical infrastructure and communities. Full article

Wildfires have become more frequent and intense worldwide due to climate change and anthropogenic activities, which is why accurate and timely burned area mapping is essential for estimating damage and effective post-fire recovery planning. Synthetic Aperture Radar (SAR) data, which operates under all weather conditions and day-night cycles, offers a reliable source for burned area mapping. In this context, several studies have explored the use of dual-polarization SAR imagery and machine learning, yet the influence of multi-date, dual-orbit pass data and texture features remained unexplored. Therefore, this study aims to assess the Sentinel-1 acquisition configurations, varying in temporal depth and orbital direction, for wildfire burned area mapping, considering the recent Palisades wildfire event as a study area. A comparative study was conducted across different scenarios to evaluate the effectiveness of using single-date versus multi-date SAR imagery, the integration of ascending and descending orbit passes, and the contribution of Grey-Level Co-occurrence Matrix texture features. The performance of Random Forest (RF) and Extreme Gradient Boosting classifiers was analyzed through the scenarios mentioned above. The single-date configuration using RF achieved an accuracy of 82.34%, F1-score of 81.43%, precision of 83.07%, recall of 80.84%, and ROC-AUC of 90.88%, whereas the multi-date approach reached 85.78%, 85.15%, 86.45%, 84.56%, and 93.28%, respectively. Our study highlights the importance of acquisition configuration and texture information for reliable SAR-based wildfire burned area assessment. Full article

Anthropogenic wildfires account for the majority of wildfire ignitions in human-dominated landscapes, yet their spatial drivers remain insufficiently understood at national scales. This study aims to identify key factors influencing anthropogenic wildfire occurrence and to develop a robust and interpretable prediction framework using nationwide data from South Korea. Wildfire occurrence records from 2011–2021 were integrated with daily meteorological, environmental, and socio-economic variables at a 1 km grid resolution. A stacking ensemble model combining Random Forest, XGBoost, LightGBM, Extra Trees, and logistic regression was implemented to improve predictive robustness under rare-event conditions. Model performance was evaluated using ROC–AUC, PR–AUC, and threshold-optimized F1-scores, and variable contributions were interpreted using feature importance and SHAP analyses. The ensemble model achieved a PR–AUC of 0.934 and an ROC–AUC of 0.941. Relative humidity and maximum temperature were identified as influential meteorological variables, while human-accessibility-related variables, particularly distance to roads and agricultural land, showed consistently high contributions to spatial ignition probability. These findings indicate that anthropogenic wildfire occurrence is shaped by interactions between fire-weather conditions and spatial patterns of human accessibility. The proposed framework provides a scalable approach for understanding anthropogenic wildfire mechanisms and supporting prevention strategies in forested landscapes. Full article