Search Results (1,956)

This manuscript introduces a new class of count time series models, referred to as the minification integer-valued Split-BREAK (MIN–SB) process. The proposed framework extends the Split-BREAK modeling philosophy to the integer-valued setting and provides a flexible mechanism for capturing rare events, zero inflation, and structural regime changes frequently observed in safety-related data. The main stochastic properties of the MIN–SB process are derived, including stationarity conditions, explicit moment structure, and correlation dynamics. A key theoretical result reveals an implicit hidden Markov structure underlying the observable process, providing a structural explanation for zero clustering observed in rare-event count processes. Parameter estimation is developed using a simulated method of moments (SMM) approach based on zero-related statistics, and the asymptotic properties of the resulting estimators are established. A Monte Carlo simulation study demonstrates favorable finite-sample performance of the proposed estimation procedure. The practical usefulness of the model is illustrated through an empirical application to time series of injuries and fatalities caused by fire accidents in Serbia. The results show that the MIN–SB specification provides a flexible and accurate framework for modeling zero-inflated count processes arising in fire safety dynamics. Full article

Lithium-ion battery (LIB) cells are available in various sizes, formats, and chemistries. Should a LIB be exposed to conditions outside its operating parameters, each variation affects the cell failure mechanisms and any resultant fire dynamic. Battery fires can be dynamic events that differ significantly from those solid-, liquid- or gas-based fire curves often used in standard building material fire resistance tests. This preliminary research aimed to investigate how standard building materials, sometimes used as a compartment fire envelope, such as gypsum plasterboard, react when exposed to a dynamic battery fire. The research explored batteries that produced jet fires, could act as projectiles, or produced overpressures when they failed. The results showed that cylindrical cells can travel at significant speeds and distances due to expulsing the cell’s contents through the cell’s vent or ejected end cap. These cells were shown to be capable of piercing plasterboard and remain hot enough to present a fire risk where they fall on the far side of the plasterboard. It was also found that the overpressures produced by failing prismatic cells affected the structural integrity of some building materials. The results show a need for further research into the effectiveness of standard building fire controls when exposed to LIB fires. Full article

Forest fires are an increasing environmental challenge in Southern Europe, requiring reliable tools for assessing both fire-induced disturbances and subsequent ecosystem recovery. This study presents an integrated satellite-based system for automated monitoring of post-fire forest dynamics. The system combines multispectral data from Sentinel-2 and Landsat (TM, ETM+, OLI, OLI-2) with thermal anomaly information from MODIS and VIIRS within a unified processing framework. It is structured into two modules: Post-Fire Disturbance (PFDMO) and Post-Fire Recovery (PFRMO). The methodology builds on a validated algorithm integrating the Disturbance Index (DI), Vector of Instantaneous Condition (VIC), and Direction Angle (DA), enabling automated multi-temporal analysis from fire detection to recovery assessment. The system was applied to three wildfire-affected areas in Bulgaria under different environmental conditions. Results reveal substantial spatial variability in disturbance and recovery, with PFDMO values ranging from −5.17 to +10.16 and PFRMO values from −2.25 to +7.40. The results demonstrate the applicability of the proposed system for monitoring post-fire forest dynamics and illustrate its potential to support informed decision-making in forest management, biodiversity conservation, and sustainable resource use. The main contribution of the system lies in the integration of disturbance and recovery assessment within a single automated and scalable workflow based on freely available satellite data. Full article

Spiking neural networks (SNNs) have emerged as a promising paradigm for energy-efficient neuromorphic computing, particularly when processing asynchronous event streams from dynamic vision sensors (DVSs). However, SNNs often suffer from limited representational capacity and suboptimal feature recalibration compared to their artificial counterparts. To address these challenges, we propose SE-SNN, a novel architecture that integrates Squeeze-and-Excitation (SE) blocks into deep residual SNNs, enabling channel-wise attention without spike generation. Furthermore, we introduce a Robust Parametric Leaky Integrate-and-Fire (RobustPLIF) neuron model with learnable membrane time constant ($\tau$) and firing threshold ($v_{\mathrm{th}}$), allowing adaptive temporal dynamics in each layer. Our model is trained on the CIFAR10-DVS dataset.The experimental results demonstrate that SE-SNN achieves an accuracy of $78.8$% on CIFAR10-DVS with 16 time steps, outperforming baseline SNNs while maintaining biological plausibility and hardware efficiency. Ablation studies confirm the individual contributions of the SE blocks and learnable neuron parameters to the performance gains. Full article

Urban fire incidents in complex built environments pose severe threats to public safety. However, the unstructured nature of urban scenes presents substantial challenges for existing detection algorithms in reliably identifying incipient flames and diffuse smoke under dynamic visual interference. To address this issue, we propose YOLO-Fire, a lightweight and high-precision detection algorithm based on YOLOv11. Specifically, a Hybrid Feature Fusion Module (HFFM) adopts a parallel dual-stream architecture to structurally decouple high-frequency flame boundaries from low-frequency smoke textures. A Dual-Scale Contextual Diffusion (DCD) mechanism establishes global contextual constraints through an additive diffusion strategy, effectively suppressing fire-like background interference while enhancing semi-transparent smoke features. In addition, a Gaussian Spatial Pyramid Pooling Fast (GSPPF) module further improves multi-scale receptive field aggregation. Evaluated on a self-constructed large-scale urban fire dataset, YOLO-Fire achieves an mAP50 of 75.7%, mAP50-95 of 53.3%, and an F1-score of 73.7%, with only 10.02 M parameters, surpassing the YOLOv11 baseline by 2.4%, 4.5%, and 2.9%, respectively. Ablation studies confirm that each proposed module contributes both independently and synergistically to the overall performance gains. Comprehensive comparisons with mainstream detectors and specialized fire detection models further demonstrate that YOLO-Fire achieves superior overall performance, outperforming YOLO-FireAD and FireSmoke-YOLO by 2.7% and 2.4% in mAP50, respectively, while maintaining lower computational complexity. Furthermore, inference evaluation on a single-core CPU achieves 17.28 FPS, validating the practical deployment potential of YOLO-Fire in resource-constrained environments and offering an efficient, lightweight solution for real-time urban fire surveillance and early warning. Full article

Wildfires are an increasingly recurrent disturbance in Mediterranean forest landscapes, yet fire severity assessment remains limited in data-scarce regions such as Lebanon. This study aims to assess wildfire severity patterns and identify the main environmental drivers influencing fire severity across the forests of Akkar, northern Lebanon, within a Digital Landscapes framework. Fire severity was mapped using the Differenced Normalized Burn Ratio (dNBR) derived from multi-temporal Landsat-8 imagery (2013–2024) processed in Google Earth Engine. Vegetation productivity was assessed through annual Net Primary Productivity (NPP), while topographic variables (elevation, slope, and aspect) were derived from a Digital Elevation Model. The results reveal heterogeneous fire severity patterns over the study period and pronounced spatial variability in NPP, with no consistent linear relationship between productivity and fire severity. Principal Component Analysis (PCA) was applied to explore multivariate relationships between fire severity, productivity, and terrain. PCA results show that the first two components explain 77.4% of the total variance, indicating that fire severity is primarily structured by topographic factors, particularly elevation and solar exposure, while vegetation productivity plays a secondary role. These findings highlight the dominant influence of terrain on wildfire severity in Mediterranean mountainous landscapes, and demonstrate the value of integrating remote sensing, cloud-based platforms, and multivariate analysis for fire assessment in data-scarce regions. The study contributes to the advancement of Digital Landscapes approaches by providing a scalable and data-driven framework for understanding fire dynamics and supporting future landscape management and risk assessment strategies. 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

To address the challenges of low diagnostic accuracy of constrained primary frequency regulating (PFR) capacity for coal-fired units due to complex and strongly coupled restricting factors, an intelligent diagnosis method based on an improved snake optimizer-based multi-label random forest classification algorithm is proposed. By analyzing the factors restricting PFR capability, a set of characterization parameters and constraint factors for unit regulating capacity is established. The snake optimizer is enhanced by introducing dynamic update mechanisms and novel search strategies to improve its convergence speed and accuracy. The improved algorithm is then applied to optimize the hyperparameters of the multi-label random forest algorithm, enabling online diagnosis of PFR capacity limitations. Simulation results demonstrate that the proposed algorithm exhibits superior convergence performance, with lower medians of false alarm rate and missing alarm rate across all labels, coupled with reduced result dispersion compared to alternative algorithms. Tests on real operational data show an average false alarm rate of 0.029% and an average missing alarm rate of 0.053 for all labels. The results indicate that the proposed method is feasible and effective, enabling accurate online diagnosis of constrained PFR capacity of coal-fired units. Full article

Conventional high-voltage direct current (HVDC) systems based on line-commutated converters (LCC) are prone to commutation failures and consume excessive reactive power during AC grid faults. The controllable line-commutated converter (CLCC) was developed to solve these problems. To further investigate CLCC’s practical application in the AC system, this paper proposes a fixed AC voltage control strategy for the inverter-side CLCC. A hybrid LCC-CLCC HVDC transmission system model is built in PSCAD. Simulations are performed under three-phase short-circuit faults and wind power fluctuation scenarios. The results show that, unlike traditional LCC, the CLCC under the proposed control can actively increase its firing angle over 160 degrees during disturbances. This action injects dynamic reactive power into the grid and significantly reduces the AC bus voltage drop. Especially in weak grid conditions, CLCC can greatly reduce reactive power consumption through wide-range active adjustment of the firing angle, thereby improving voltage stability. Full article

In this work, we explore a piezoelectric neuron model in deterministic perturbations and stochastic forcing due to its use in mechanically driven sensing systems and neuromorphic sensor design. The model comprises of fast activation and slow recovery behaviors and constitutes a multiscale excitable system, converting external mechanical perturbations into nonlinear electrical responses. We initially examine the deterministic dynamics with phase-space reconstruction, basin of attraction mapping, return map analysis and sensitivity to initial conditions. These findings demonstrate stable limit-cycle oscillations and high nonlinear sensitivity that are crucial to high-resolution sensing and signal amplification. Stochastic forcing is added in order to include realistic environmental effects, and solved numerically with the Euler-Maruyama scheme. Time-series statistics, phase portraits, and recurrence quantification analysis are used to analyze the resulting ensemble dynamics, making it possible to characterize the variability and loss of predictability caused by noise. Comparison of deterministic and stochastic regimes indicates that the intensity of noise can considerably alter the firing patterns and recurrence structures. Full article

The analysis of dynamic causal mechanisms underlying shipboard fires and explosions is often restricted by the unstructured and fragmented nature of accident investigation reports. This study proposes a framework integrating ontology-driven information extraction with Dynamic Bayesian Networks (DBNs) to model temporal accident evolution. An ontology comprising 41 nodes was constructed through a structured expert elicitation process to formalize the domain knowledge. To process 198 bilingual accident reports, an extraction pipeline was deployed, incorporating XLM-RoBERTa, BiLSTM-CRF, and an entity-marker relation classifier. Large language model (LLM)-directed weak supervision, constrained by token-level information entropy filtering, was employed to expand the training corpus, necessitating only 2.5% manual verification. The extracted semantic dependencies were utilized to initialize a three-slice DBN (precursor, initial fire, and escalation/explosion). The network structure was jointly optimized through ontology constraints (112 forbidden and 4 mandatory edges), the Hill-Climbing algorithm, and BDeu scoring. The proposed DBN achieved an AUC of 0.759 ± 0.086 and a Brier Score of 0.192 ± 0.021 (1000 bootstrap iterations), demonstrating superior predictive performance over traditional interpretable models (Static BN, HMM, ETA) with large effect sizes (Cohen’s d > 1.0), while maintaining competitive accuracy and enhanced causal interpretability relative to XGBoost. This framework offers a scalable, data-driven methodology for dynamic probabilistic risk assessment in maritime safety. Full article

Series arc faults on the DC side of photovoltaic (PV) systems are a critical hazard that can trigger system fires. Conventional contact-based detection methods suffer from cumbersome installation and high retrofit cost, whereas existing non-contact approaches mostly rely on megahertz-level high-frequency sampling and therefore require expensive radio-frequency instrumentation or high-performance computing platforms. As a result, it remains difficult to simultaneously achieve strong interference immunity and real-time performance on low-cost embedded devices with limited resources. To address this engineering paradox between high-frequency sampling and constrained computational capability, this paper proposes a fully embedded, non-contact arc fault detection system based on a 12–80 kHz low-frequency sub-band selection strategy. By exploiting the physical characteristic of broadband energy elevation induced by arc faults, the proposed strategy avoids dependence on high-bandwidth hardware. Guided by this strategy, a Moebius-topology coaxial shielded loop antenna is employed as the near-field sensor, while an ultra-simplified passive analog front end is constructed directly by using the on-chip programmable gain amplifier and analog-to-digital converter of the microcontroller unit, enabling efficient signal acquisition and fast Fourier transform processing within the target sub-band. To cope with complex background noise in the low-frequency range, an environment-adaptive baseline mechanism based on exponential moving average and exponential absolute deviation is developed for dynamic decoupling. In addition, a lightweight INT8-quantized multilayer perceptron is introduced as a nonlinear auxiliary module, thereby forming a robust hybrid decision architecture with complementary rule-based and artificial intelligence components. Experimental results show that, under the tested household, laboratory, and PV-site conditions, the proposed system achieved an overall detection rate of 97%, while the remaining 3% mainly corresponded to failed ignition or non-sustained arc attempts rather than persistent false triggering during normal monitoring. Full article

Uncontrolled scrap tire fires represent high-intensity episodic emission events that pose severe toxicological threats to urban environments. This study employs atmospheric dispersion modelling to quantify the impact of a tire stockpile fire on a distal educational receptor, evaluating two distinct dynamic stages of the event: an initial high-intensity open flame scenario (E1, 4 h) and a prolonged smouldering/suppression scenario (E2, 6 h), induced by firefighting interventions. Results reveal extreme pollutant loading at the receptor site during E1, with PM₁₀ and SO₂ concentrations peaking at 23,766 ${\displaystyle \frac{\mathsf{\mu }\mathrm{g}}{{\mathrm{m}}^3}}$ and 7821 ${\displaystyle \frac{\mathsf{\mu }\mathrm{g}}{{\mathrm{m}}^3}}$ respectively, indicating an immediate risk of acute respiratory distress. The organic fraction was dominated by volatile organic compounds (VOCs) (8691 ${\displaystyle \frac{\mathsf{\mu }\mathrm{g}}{{\mathrm{m}}^3}}$) and a ∑16 PAHs flux of 313.9 ${\displaystyle \frac{\mathsf{\mu }\mathrm{g}}{{\mathrm{m}}^3}}$. Toxicological assessment identified Benzo[a]pyrene (BaP) as the primary driver of health hazards, contributing approximately 70% to the carcinogenic risk profile. A critical disparity was observed between Mutagenic Equivalency (MEQ) of 18.32 and Toxic Equivalency (TEQ) of 15.37, suggesting that standard monitoring significantly underestimates the biological threat to sensitive paediatric populations. These findings demonstrate that acute, oxygen-limited tire combustion creates a concentrated toxic slug of high-molecular-weight PAHs. The study underscores the necessity of integrating mutagenicity-based models into emergency response protocols to accurately safeguard vulnerable communities against the long-term toxicological legacy of elastomer thermolysis. Full article

Wildfires severely disrupt soil nitrogen (N) cycling, yet the mechanisms driving this disruption in fragile karst forest ecosystems remain poorly understood. We investigated how wildfires affect soil N transformation dynamics and the microclimatic drivers of these dynamics in a karst forest. Using an in situ paired burned versus unburned plot design, we evaluated post-fire soil physicochemical properties, N fractions, and N-acquiring enzyme activities in the 0–10 cm soil layer. Wildfires significantly deteriorated the soil microenvironment, increasing mean soil temperature by 9.93% and bulk density by 36.66%, while sharply reducing soil water content, porosity, and saturated hydraulic conductivity. Consequently, the fires severely depleted total and organic soil N pools. Furthermore, N-acquiring enzymes (urease, protease, nitrate reductase, and nitrite reductase) initially declined in activity before gradually recovering. Notably, partial least squares structural equation modeling (PLS-SEM) revealed a fundamental shift in the drivers of nitrogen transformation. In unburned soil, abiotic climatic factors regulated N dynamics. After wildfire, enzyme-mediated biological processes controlled N dynamics, and these processes were constrained by altered soil physics. Restoring soil physical structure and stimulating enzymatic mineralization are therefore critical, rate-limiting steps for the recovery of soil N reservoirs in fire-prone karst landscapes. Full article

Conventional structural design frameworks assess natural hazards as statistically independent phenomena, a practice that can lead to significant underestimation of risk for structures subjected to sequential or concurrent hazards. The generation of probabilistic fragility functions under such cascading loads, particularly for post-fire seismic events, presents a computational barrier for standard non-linear dynamic analysis. To address this barrier, this study introduces a comprehensive computational framework centered on a physics-constrained neural network (PCNN) to serve as a high-fidelity surrogate model. The framework first uses a non-linear 12-degree-of-freedom structural model to generate a baseline dataset of collapse times under post-fire, concurrent wind-earthquake loading via the computationally efficient endurance time (ET) method, confirming that wind effects are negligible under ambient conditions and that the framework correctly identifies this hazard hierarchy without prior labeling, while fire and seismic parameters dominate. This dataset is subsequently used to train the PCNN, which is validated to achieve exceptional predictive accuracy ($R^2=$ 0.991), performing on par with a state-of-the-art Random Forest model while enforcing physical constraints. A feature importance analysis confirmed that structural collapse is dominated by fire intensity (≈55%) and initial structural period (≈45%). The validated PCNN is then applied to demonstrate the framework’s capability, rapidly generating fragility curves that quantify the catastrophic effect of fire on seismic resilience. This analysis reveals that a severe 800 °C localized fire reduces the structure’s median collapse capacity by 94.7%, thereby establishing the proposed framework as a successful template for tackling complex, non-linear problems in multi-hazard engineering. Full article