Search Results (228)

Machine learning approaches to wildfire spread prediction are constrained by the lack of standardized, multi-source, spatiotemporal datasets that fuse terrain, weather, and fire-state information into a single ML-ready format. We present WildfireCube, a reproducible event-centric pipeline and methodology for constructing dense fourth-order spatiotemporal tensors of shape (T, C, H, W) at 30 m spatial and 3 h temporal resolution. Following the analysis-ready data convention established in the Earth Observation community, the pipeline fuses four open data sources: the Copernicus GLO-30 Digital Elevation Model for static terrain derivatives, ERA5-Land reanalysis for hourly weather forcing, Sentinel-2 Level-2A imagery for spectral vegetation and burn-severity indices, and NASA FIRMS active-fire hotspot detections for fire-state reconstruction via ordinary kriging. The resulting 13-channel normalized tensor separates causal drivers into three physically motivated groups: static landscape controls (elevation, slope, aspect, fuel load), dynamic atmospheric forcings (wind components, temperature, precipitation), and evolving fire state (fire-front mask, burn severity, fractional burn, observation confidence). A physics-informed normalization framework maps all channels to bounded ranges using fixed physical constants rather than sample statistics, ensuring cross-event comparability and exact invertibility. We demonstrate the pipeline on 13 wildfire events across the United States, Canada, and Greece (2017–2023), producing a processed catalog exceeding 300 GB compressed and spanning a 14-fold range in burned area, a 27 °C range in mean temperature, and different fire regimes. Event tensors are stored in chunked Zarr archives with Zstandard compression, achieving a 2.58× compression ratio. As future work, the pipeline will be applied to a 40-event target catalog projected to exceed 2 TB of raw data, providing the multi-regime diversity and scale required for training robust deep learning models for spatiotemporal wildfire prediction. Full article

The increasing severity of global wildfires requires advanced suppression strategies to mitigate impacts on the environment and human life. This work investigates the applicability of Multi-Agent Reinforcement Learning (MARL) to aerial wildfire suppression using the SoSID Toolkit, an agent-based grid simulation grounded in cellular-automata-based fire propagation. To enhance interpretability and support the reconstruction of learned tactics, this work introduces the Dual Decomposition Framework, providing a modular structure for both the reward function and the observation space. This design enables the systematic evaluation of individual components, allowing the identification of the elements most relevant to effective wildfire suppression. The learned MARL policy is compared against a heuristic strategy inspired by real-world firefighting practice. The reward analysis confirms that the Dual Decomposition Framework enhances transparency in agent behavior by analyzing the contribution of individual components. The experiments further show that the learned policy can outperform the heuristic approach in terms of burned-area reduction when fire spread sensitivity is low, demonstrating the potential of MARL for effective suppression strategies. However, performance declines as spread sensitivity increases, indicating limited generalization and signs of overfitting to training conditions. The findings suggest that approaches such as curriculum learning may improve robustness under faster-spreading fire dynamics. Full article

Grassland fire is one of the major disasters threatening regional ecological security. Its occurrence, development, and spread are closely related to the spatial distribution and coverage of surface vegetation and snow cover across grassland areas. As the primary combustible fuel source, higher vegetation coverage increases fuel load and continuity, thereby directly determining grassland fire danger levels and accelerating fire spread velocity. In contrast, snow cover imposes an indirect regulatory effect on the spatiotemporal pattern of fire danger factors: it lowers surface temperature, raises near-surface humidity, and restricts the germination and growth of herbaceous vegetation in cold seasons, which effectively reduces available combustible materials and weakens regional fire hazard conditions. Therefore, accurately obtaining the coverage status of vegetation (direct combustible fuel factor) and snow cover (indirect fire-regulating factor) in complex grassland scenarios is the essential premise for reliable grassland fire danger monitoring, early warning, disaster prevention and control, and regional ecological management. Aiming at the practical problems in complex grassland scenarios (such as undulating terrain, uneven vegetation growth, large differences in snow depth, and complex lighting conditions), including difficulty in extracting vegetation and snow-covered areas, blurred and confusing boundaries, and low accuracy in coverage calculation, which seriously restrict the technical bottleneck of precise monitoring of grassland fire danger factors, this study takes near-ground images collected by grassland fire danger factor monitoring stations as the core data source, and proposes an improved UNet image segmentation model combined with image segmentation technology and deep learning methods to realize precise extraction of vegetation and snow-covered areas and efficient calculation of coverage in complex scenarios. To improve the model’s feature extraction ability, boundary localization accuracy, and reduce model parameters and computational overhead, the CBAM-ASPP (Convolutional Block Attention Module—Atrous Spatial Pyramid Pooling) module is integrated at the end of the encoding path. The attention mechanism is used to enhance the weight of key features, and the multi-scale receptive field of atrous spatial pyramid pooling is utilized to strengthen the model’s ability to fuse features of vegetation and snow areas of different scales. The residual attention mechanism is introduced in the upsampling stage to effectively alleviate the gradient disappearance problem, improve the model’s ability to accurately locate the boundaries of vegetation and snow areas, and reduce segmentation errors. In the training process, a dynamically weighted hybrid loss function is adopted to dynamically adjust the weights according to the segmentation difficulty of different types of samples during training, optimize the model training effect, and improve the segmentation accuracy and generalization ability. Experiments were conducted using near-ground images of typical complex grassland scenarios as the dataset, and the performance of the proposed model was verified through comparative experiments. The results show that in the vegetation segmentation task, the mean Intersection over Union (mIoU) of the model reaches 84.70%, and the accuracy rate is 91.28%, which are 1.48 and 1.58 percentage points higher than those of the standard UNet model, respectively. In the snow segmentation task, the mIoU of the model reaches 92.74%, and the accuracy rate is 94.19%, which are 2.39 and 2.36 percentage points higher than those of the standard UNet model, respectively. At the same time, the number of parameters of the model is reduced by 12.85% compared with the standard UNet. Also, its comprehensive performance is significantly better than that of mainstream image segmentation models such as FCN, SegNet, and DeepLabv3+. Based on the standardized time-series data retrieved by the optimized segmentation model, this study further constructs a Grassland Fire Risk Index (GFRI) using the Analytic Hierarchy Process (AHP). Pearson correlation verification confirms that the GFRI has an extremely significant positive correlation with historical fire frequency, accurately capturing the seasonal dynamic rhythm of regional grassland fire occurrence. This integrated framework of intelligent segmentation and fire risk quantification provides a reliable technical solution for grassland fire factor monitoring, dynamic fire risk assessment, early warning systems, and refined regional ecological management. Full article

Firefighters are regularly exposed to occupational stress and potentially traumatic events. However, few evidence-based, fire service-specific interventions exist. Brief, mindfulness-based interventions may help address these challenges by improving regulation skills and reducing psychological distress. This pilot randomized controlled trial primarily evaluated the feasibility and acceptability of a one-session, group-based, virtual mindful attention training workshop developed specifically for firefighters, with secondary evaluation of preliminary efficacy. Firefighters (N = 82) were recruited from multiple fire departments across a large U.S. Southwestern metropolitan area and randomized to the mindful attention workshop (n = 45) or a waitlist control condition (n = 37). Feasibility outcomes were mixed, with strong enrollment among eligible participants (74.5%) but relatively low workshop attendance among those randomized to the intervention (53.3%). A total of 24 firefighters completed the workshop and found it to be helpful, informative, and relevant to the challenges faced in the fire service, with group processes characterized by high comfort, understanding, and low conflict. However, no significant between-group differences were observed in reductions in symptom severity or increases in mindfulness-based outcomes. Post hoc descriptive analyses revealed that most firefighters expressed strong interest in digitally delivered mental health content and the vast majority perceived online or app-based firefighter-specific mental health resources as helpful. Findings indicate mixed feasibility, strong acceptability among attendees, and a lack of preliminary efficacy, and highlight directions for refining intervention delivery of this pilot workshop and evaluating clinical impact in future trials. 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

Precise Estimated Time of Arrival (ETA) prediction in Terminal Maneuvering Areas (TMA) constitutes a prerequisite for efficient arrival sequencing and airspace capacity management. While data-driven approaches outperform kinematic models, conventional Recurrent Neural Networks (RNNs) exhibit limitations in modeling complex multi-aircraft spatial interactions and lack the capability to quantify predictive uncertainty. Conversely, Spiking Neural Networks (SNNs) enable energy-efficient event-driven computation, yet their applicability to continuous trajectory regression is hindered by “input starvation,” where normalized state vectors fail to induce sufficient neural firing rates. This study proposes a Probabilistic Spiking Transformer (PST) architecture to integrate neuromorphic sparsity with global attention mechanisms. An Adaptive Spiking Temporal Encoding mechanism incorporating learnable linear projections is introduced to resolve the regression-spiking incompatibility, facilitating the autonomous mapping of continuous trajectory dynamics into sparse spike trains without heuristic scaling. Concurrently, a Distance-Biased Multi-Aircraft Cross-Attention (MACA) module models air traffic conflicts by weighting spatial interactions according to physical proximity, thereby embedding separation constraints into the feature extraction process. Evaluation on large-scale real-world ADS-B datasets demonstrates that the PST yields a Mean Absolute Error (MAE) of 49.27 s, representing a 60% error reduction relative to standard LSTM baselines. Furthermore, the model generates well-calibrated probabilistic distributions (Prediction Interval Coverage Probability > 94%), offering quantifiable uncertainty metrics for risk-based decision support while ensuring real-time inference suitable for operational deployment. Full article

Forest fire occurrence prediction remains challenging despite advances in operational fire danger rating systems. In South Korea, the Korea Forest Fire Danger Rating Index (KFDRI) incorporates meteorological conditions, terrain (elevation, aspect), and forest type to assess regional fire danger. While KFDRI successfully assesses environmental fire danger at the pixel level, it does not explicitly account for human activity patterns that create substantial occurrence variability among locations with similar environmental conditions. This limitation is critical in human-dominated landscapes where where the main source of fire occurrence is anthropogenic. This study developed a Random Forest (RF) model to predict forest fire occurrence probability and propose management priorities during the forest fire prevention season (November–May) along the eastern coast of Korea, explicitly integrating human proximity variables (distance to agricultural areas and roads) with topographical (elevation, slope, aspect), surface fuel load, and meteorological variables (SMAP soil moisture, cumulative precipitation). Using forest fire occurrence records (1112 fire occurrence records) and background samples from 2015 to 2024, the model was trained with monthly stratified sampling and 10-fold cross-validation. The model achieved stable classification performance, with an overall F1-score of 0.515 and accuracy of 0.733. According to the SHAP (SHapley Additive exPlanations) analysis, distance to agricultural areas, elevation, slope, aspect, 5-day cumulative precipitation, and forest type were the most influential predictors. In particular, occurrence probability tended to increase in areas close to agricultural land (<180 m), at low elevations (≤200 m), on moderately steep slopes (≥8°), on south- and west-facing aspects, and under dried conditions. These results emphasize that fire occurrence risk is primarily structured by human proximity within areas of similar environmental danger. We propose an operational integration in which the RF model provides a 30 m “where-to-focus” occurrence layer that is used alongside KFDRI’s daily danger rating to prioritize prevention and patrol efforts. Full article

Most machine learning (ML)-based facility location studies utilize uniform grid partitioning, often overlooking spatial heterogeneity. This limitation can compromise the validity and practical applicability of the resulting site selections. In response to this issue, this paper uses fire stations as the research subject and proposes a location prediction method that considers the heterogeneous characteristics within cities. Firstly, the Gaussian Mixture Model (GMM) is adopted based on the Point of Interest (POI) data to determine the clustering centres of the study area. Secondly, a Voronoi diagram is constructed to divide the study area reasonably. Then, a comprehensive feature matrix is constructed by integrating multi-source spatial data and five machine learning models: Random Forest (RF), Gradient Boosting Decision Tree (GBDT), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost) and Logistic Regression (LR). These are then used for training and evaluation. Finally, the GBDT model with the best performance in terms of both the F1 score and the AUC value was selected to predict the location of fire stations in Chengguan District, Lanzhou City. The results demonstrate the GBDT model’s effectiveness in identifying the rationale behind existing fire station locations and predicting potential new locations. It predicts 12 suitable locations for new fire stations, and the suitability of these predicted locations is validated by comparing them with the existing fire station locations, 8 of which are in the same block as existing fire stations in Chengguan District. Adding micro fire stations at four new predicted locations would improve response efficiency. The results of the feature importance analysis show that road accessibility is the primary factor affecting fire station location selection. This study’s proposed method effectively enhances the reasonableness of fire station site selection and provides a basis for planning fire stations in new urban areas in the future. Full article

Traditional burn severity assessment methods have predominantly leveraged optical remote sensing data, yet such methods often overlook critical vegetation structural information inherent to post-fire ecosystems. Synthetic Aperture Radar (SAR) data offer structural information but are hindered by non-uniform scattering in fire-affected areas, limiting the utility of conventional decomposition techniques. Here, we introduced a metric that quantifies scattering non-uniformity by jointly considering canopy burn and ground condition non-uniformity. From this metric, we derived quantitative polarimetric features that enhance SAR-based severity estimation and demonstrated the potential to assess burn severity, with an R of 0.77 and a RMSE of 0.58. Initially, six decomposition features were extracted with the covariance matrix and then 14 feature groups were formed through metric and combination. Subsequently, sensitivity analyses were conducted for the first nine feature groups with the Composite Burn Index (CBI) values. Following this, the 14 feature groups were employed as inputs and the CBI values as outputs for random forest learning at a 7:3 training ratio to assess burn severity and generate burn severity maps. This study used the Jinyun Mountain fire in Chongqing as the primary case and eight fires in the United States as supplemental data to discuss the general applicability of the quantitative polarimetric features in assessing burn severity. Notably, the developed methodology showcased superior results within all wildfires, offering a new outlook for future burn severity assessments utilizing vegetation structure information. Full article

Effective command-and-control (C2) decision-making during emergency response relies on timely access to spatially accurate information. It also requires a clear understanding of evolving incident conditions. Traditional fire-service training methods provide limited opportunities to rehearse complex, high-risk, and large-scale incidents under realistic yet safe conditions. This exploratory pilot study presents the design and experimental evaluation of an integrated training environment that combines geographic information system (GIS) data, unmanned aerial vehicle (UAV) imagery, and immersive virtual reality (VR) simulations to support C2 training for fire-service incident commanders. The system was assessed through scenario-based exercises involving 23 active incident commanders across three representative emergency scenarios: wildland fire, hazardous materials transport accident, and flood response. The training scenarios were based on real geographic areas in central Slovakia, using authentic terrain, land-cover, infrastructure, and hydrological GIS layers to ensure spatial realism of the simulated emergency environments. Pre-training and post-training questionnaires were used to evaluate perceived training realism, preparedness for command tasks, decision-making confidence, and the perceived usefulness of digital spatial information tools. Results indicate a substantial post-training increase in perceived realism and preparedness, with strong positive correlation between these variables (Spearman ρ = 0.71, p < 0.001). Participants reported improved confidence in assessing incident conditions, prioritizing operational tasks, and allocating resources under dynamically evolving scenarios. The study evaluates perceived spatial situational understanding derived from multi-source spatial information integration rather than directly measured situational awareness using standardized psychometric instruments. UAV imagery was found to be particularly valuable for rapid incident size-up, while GIS layers primarily supported spatial planning, hazard delineation, and resource coordination; VR served as a unifying platform for fusing these information sources into a coherent operational picture. Scenario-specific differences in tool usefulness were observed, reflecting the spatial and risk characteristics of each incident type. Overall, the findings indicate that integrated GIS–UAV–VR environments provide a realistic and scalable complement to traditional fire-service command training, enhancing spatially supported decision-making and preparedness for complex emergency response. Given the single-group pretest–posttest design, limited sample size, absence of a control group, and reliance on perceived evaluation measures, the results should be interpreted as indicative rather than as generalizable evidence of training effectiveness. Full article

Forest management interventions in fire-prone western U.S. forests aim to restore structural heterogeneity, yet tracking treatment efficacy at landscape scales remains a persistent challenge. Traditional monitoring tools often lack the spatial resolution or temporal frequency needed to assess fine-scale structural outcomes. While deep learning approaches for mapping canopy structure from high-resolution satellite imagery have advanced rapidly, their application to operational monitoring of restoration outcomes with independent validation remains limited. This study demonstrates and validates a scalable monitoring workflow that integrates high-resolution PlanetScope multispectral imagery (~4.77 m) with a residual U-Net convolutional neural network (CNN) to quantify canopy structure dynamics in support of forest restoration programs. Trained using 3 m canopy cover data from the California Forest Observatory (CFO) as a reference, the model accurately segmented forest canopy from openings across a large, independent test area of ~1761 km², with an overall accuracy of 92.2%, and an F1-score of 95.1%. Independent validation against airborne LiDAR across 140 km² of heterogeneous terrain confirmed operational performance (overall accuracy 85.9%, F1-score 0.77 for canopy gaps). We applied this framework to quantify structural changes within the North Yuba Collaborative Forest Landscape Restoration Program from 2020 to 2024, providing managers with actionable metrics to evaluate treatment effectiveness against historical reference conditions. The treatments created 564 acres of new openings, significantly increasing structural heterogeneity, with 56% of new open area located within 12 m of residual canopy. While treatment outcomes aligned with the goal of fragmenting dense canopy, the resulting large openings (>5 acres) slightly exceeded historical reference conditions for the area. This validated workflow translates high-resolution satellite imagery into timely, actionable metrics of forest structure, enabling managers to rapidly evaluate treatment impacts and refine restoration strategies in fire-prone ecosystems. Full article

Accurate mapping of wetland vegetation is essential for ecosystem monitoring and conservation planning. Traditional workflows combining Sentinel-1 SAR, Sentinel-2 optical imagery, and topographic data have advanced vegetation classification but require extensive preprocessing and often yield fragmented boundaries and “salt-and-pepper” noise. In this study, we compare a conventional multi-sensor classification framework with a novel embedding-based approach derived from the AlphaEarth foundation model, using a cluster-guided Random Forest classifier applied to the dynamic wetland system of Narran Lake, New South Wales. Both approaches achieved high accuracy ac with test performance typically in the ranges: OA = 0.985–0.991, Cohen’s κ = 0.977–0.990, weighted F1 = 0.986–0.991, and MCC = 0.977–0.990. Embedding based maps showed markedly improved spatial coherence (lower edge density, local entropy, and patch fragmentation), producing smoother, ecologically consistent boundaries while requiring minimal preprocessing. Differences in class delineation were most evident in fire-affected and agricultural areas, where embeddings demonstrated greater resilience to spectral disturbance and post-fire variability. Although overall accuracies exceeded 0.98, these high values reflect the use of spectrally pure, homogeneous training samples rather than overfitting. The results highlight that embedding-driven methods can deliver cleaner, more interpretable vegetation maps with far less data preparation, underscoring their potential to streamline large-scale ecological monitoring and enhance the spatial realism of wetland mapping. Full article

The escalating threat of wildfires under global climate change necessitates rigorous monitoring to mitigate environmental and socio-economic risks. Burned area (BA) mapping is crucial for understanding fire dynamics, assessing ecosystem impacts, and supporting sustainable land management under increasing fire frequency. This study aims to develop a high-resolution detection framework specifically calibrated for Mediterranean environmental conditions, ensuring the production of consistent and accurate annual BA maps. Using Sentinel-2 MSI time series over Sardinia (Italy), the research objectives were to: (i) integrate field surveys with high-resolution photointerpretation to build a robust, locally tuned training dataset; (ii) evaluate the discriminative power of multi-temporal spectral indices; and (iii) implement a Random Forest classifier capable of providing higher spatial precision than current operational products. Validation results show a Dice Coefficient (DC) of 91.8%, significantly outperforming the EFFIS Burnt Area product (DC = 79.9%). The approach proved particularly effective in detecting small and rapidly recovering fires, often underrepresented in existing datasets. While inaccuracies persist due to cloud cover and landscape heterogeneity, this study demonstrates the effectiveness of a machine learning approach for long-term monitoring, for generating multi-year wildfire inventories, offering a vital tool for data-driven forest policy, vegetation recovery assessment and land-use change analysis in fire-prone regions. Full article

Forest fire susceptibility prediction is essential for effective management, yet considerable uncertainty persists under future climate change, especially in climate-sensitive plateau regions. This study integrated MODIS fire data with climatic, topographic, vegetation, and anthropogenic variables to construct an Extreme Gradient Boosting (XGBoost) model for the Yunnan Plateau, a region highly prone to forest fires. Compared with Support Vector Machine and Random Forest models, XGBoost showed superior ability to capture nonlinear relationships and delivered the best performance, achieving an AUC of 0.907 and an overall accuracy of 0.831. The trained model was applied to climate projections under SSP1-2.6, SSP2-4.5, and SSP5-8.5 to assess future fire susceptibility. Results indicated that high-susceptibility periods primarily occur in winter and spring, driven by minimum temperature, average temperature, and precipitation. High-susceptibility areas are concentrated in dry-hot valleys and mountain basins with elevated temperatures and dense human activity. Under future climate scenarios, both the probability and spatial extent of forest fires are projected to increase, with a marked expansion after 2050, especially under SSP5-8.5. Although the XGBoost model demonstrates strong generalizability for plateau regions, uncertainties remain due to static vegetation, coarse anthropogenic data, and differences among climate models. Full article

This article presents a methodology for real-time forecasting of a fire-extinguishing agent jet trajectory from a robotic fire monitor under wind influence, which can significantly displace the impact area position and complicate targeting. The proposed methodology is designed for controlling firefighting robots in conditions where visual monitoring of the impact area is impeded by factors such as: obscuration of the fire-extinguishing agent flow by smoke, low visibility of its fragmented particles against the background environment, and long-range jet discharge. Trajectory forecasting is implemented using a neural network model. The training and verification of this model are performed with datasets constructed from the results of numerical simulations of fire-extinguishing agent motion under wind influence, based on Computational Fluid Dynamics (CFD) methods. Experimentally obtained data are used for the validation of the trained neural network model and the selected CFD models. The paper describes the methodology for conducting full-scale tests of fire monitors; a photogrammetric algorithm for generating validation datasets from the test results; an algorithm for calculating target characteristics, which describe the jet trajectory and are consistent with experimental data, used for forming training and verification datasets based on simulation; and a procedure for selecting Computational Fluid Dynamics models and their parameters to ensure the required accuracy. The article also presents the results of an experimental evaluation of the developed methodology’s effectiveness for real-time prediction of the water jet trajectory from a fire monitor under various control and disturbance parameters. Full article