Fire

Ship fire detection presents significant challenges in computer vision-based approaches due to factors such as the considerable distances from which ships must be detected and the unique conditions of the maritime environment. The presence of water vapor and high humidity further complicates the detection and classification tasks for deep learning models, as these factors can obscure visual clarity and introduce noise into the data. In this research, we explain the development of a custom ship fire dataset, a YOLO (You Only Look Once)-v10 model with a fine-tuning combination of dehazing algorithms. Our approach integrates the power of deep learning with sophisticated image processing to deliver comprehensive solutions for ship fire detection. The results demonstrate the efficacy of using YOLO-v10 in conjunction with a dehazing algorithm, highlighting significant improvements in detection accuracy and reliability. Experimental results show that the YOLO-v10-based developed ship fire detection model outperforms several YOLO and other detection models in precision (97.7%), recall (98%), and [email protected] score (89.7%) achievements. However, the model reached a relatively lower score in terms of F1 score in comparison with YOLO-v8 and ship-fire-net model performances. In addition, the dehazing approach significantly improves the model’s detection performance in a haze environment. Full article

The Pinus halepensis (Aleppo pine) forests prevailing in the western part of the Mediterranean Basin are amongst the most severely affected by fire due to their inherent flammability. Our understanding of the environmental factors driving post-fire community dynamics is currently limited by the lack of time-series data at temporal scales. In this present study, we analyzed a chronosequence of Greek Aleppo pine forests spanning a post-fire period of 65 years. Our goal is to explore the role of post-fire age, altitude, exposure, slope level, parent-rock material, rock cover, and cover of evergreen sclerophyllous shrubs (maquis) on plant assemblage diversity (species richness and Menhinick’s diversity index) and composition. Post-fire age had a significant effect on taxonomic distinctness and community turnover but not on species richness. Taxonomic distinctness increased with post-fire age due to a higher prevalence of the families Fabaceae, Asteraceae, and Poaceae during the early post-fire period. Maquis cover was significantly associated with Menhinick’s diversity index, taxonomic distinctness, and community turnover. Exposure and slope influenced only Menhinick’s diversity index. The turnover in species composition was primarily driven by the geographical proximity of the forests and secondarily by post-fire age and the maquis cover. This highlights the importance of the initial floristic composition in the process of autosuccession after a fire in Mediterranean-climate ecosystems. Full article

Prescribed burning is a cost-effective method for reducing hazardous fuels in pine- and oak-dominated forests, but smoke emissions contribute to atmospheric pollutant loads, and the potential exists for exceeding federal air quality standards designed to protect human health. Fire behavior during prescribed burns influences above-canopy sensible heat flux and turbulent kinetic energy (TKE) in buoyant plumes, affecting the lofting and dispersion of smoke. A more comprehensive understanding of how enhanced energy fluxes and turbulence are related during the passage of flame fronts could improve efforts to mitigate the impacts of smoke emissions. Pre- and post-fire fuel loading measurements taken during 48 operational prescribed burns were used to estimate the combustion completeness factors (CC) and emissions of fine particulates (PM_2.5), carbon dioxide (CO₂), and carbon monoxide (CO) in pine- and oak-dominated stands in the Pinelands National Reserve of southern New Jersey. During 11 of the prescribed burns, sensible heat flux and turbulence statistics were measured by tower networks above the forest canopy. Fire behavior when fire fronts passed the towers ranged from low-intensity backing fires to high-intensity head fires with some crown torching. Consumption of forest-floor and understory vegetation was a near-linear function of pre-burn loading, and combustion of fine litter on the forest floor was the predominant source of emissions, even during head fires with some crowning activity. Tower measurements indicated that above-canopy sensible heat flux and TKE calculated at 1 min intervals during the passage of fire fronts were strongly influenced by fire behavior. Low-intensity backing fires, regardless of forest type, had weaker enhancement of above-canopy air temperature, vertical and horizontal wind velocities, sensible heat fluxes, and TKE compared to higher-intensity head and flanking fires. Sensible heat flux and TKE in buoyant plumes were unrelated during low-intensity burns but more tightly coupled during higher-intensity burns. The weak coupling during low-intensity backing fires resulted in reduced rates of smoke transport and dispersion, and likely in more prolonged periods of elevated surface concentrations. This research facilitates more accurate estimates of PM_2.5, CO, and CO₂ emissions from prescribed burns in the Pinelands, and it provides a better understanding of the relationships among fire behavior, sensible heat fluxes and turbulence, and smoke dispersion in pine- and oak-dominated forests. Full article

Fire detection systems are critical for mitigating the damage caused by fires, which can result in significant annual property losses and fatalities. This paper presents a deep learning-based fire classification model for an intelligent multi-sensor system aimed at early and reliable fire detection. The model processes data from multiple sensors that detect various parameters, such as temperature, humidity, and gas concentrations. Several deep learning architectures were evaluated, including LSTM, GRU, Bi-LSTM, LSTM-FCN, InceptionTime, and Transformer. The models were trained on data collected from controlled fire scenarios and validated for classification accuracy, loss, and real-time performance. The results indicated that the LSTM-based models (particularly Bi-LSTM and LSTM) could achieve high classification accuracy and low false alarm rates, demonstrating their effectiveness for real-time fire detection. The findings highlight the potential of advanced deep-learning models to enhance the reliability of sensor-based fire detection systems. Full article

In order to reveal the deflagration mechanism of DME/H₂-blended gasses, the micro-mechanism was studied based on the constructed UC San Diego 2016 pyrolysis oxidation mechanism model. The results show that adiabatic flame temperature and laminar flame speed increase with the increase in the equivalence ratio (Φ); they first increase and then decrease with the increase in the hydrogen (H₂)-blended ratio (λ), and with the increase in λ, the Φ corresponding to the peak laminar flame speed of the blended gas increases. The addition of H₂ increases the consumption of O₂, and H₂ reacts with CO to form H₂O and CO₂, promoting complete combustion. When Φ = 1.0–1.2, the equilibrium mole fraction of H and OH-activated radicals reach the maximum, and with the addition of H₂, the concentration of activating radicals gradually increases, while the number of promoted elementary reactions increases by two, and the number of inhibited elementary reactions does not increase. Meanwhile, the addition of H₂ increases the reaction rate of most reactions on the main chemical reaction path CH₃OCH₃→CH₃OCH₂→CH₂O→HCO→CO→CO₂ of DME and increases the risk of the deflagration of DME/H₂-blended gas. Full article

This study carries out a comprehensive bibliometric analysis of scientific production on wildfires, soil erosion and land degradation, with the aim of understanding trends, critical gaps in scientific knowledge and research patterns. A total of 1400 articles published between 2001 and 2023 were analyzed with bibliometric tools (Bibliometrix and VOSviewer), revealing a steady growth in the number of publications over time. International collaboration between countries such as the United States, Spain, China and Portugal is evident, highlighting the global approach to tackling these issues, as well as the mobility and collaboration between scientists. Analyzing the conceptual structure through the co-occurrence of keywords reveals central themes such as “soil erosion” and “wildfire”, indicating areas of primary focus in research. This study highlights the continuing importance of these themes and the need for global collaboration to tackle the environmental challenges affecting forest ecosystems, and particularly the soil layer, caused by wildfires, which affect wildlands all over the world. Full article

The increased demand for contactless services has facilitated a rapid increase in logistics facilities. There are shorter distances between the shelf racks used in mezzansine racks in such facilities compared to standard racks and can store various items; however, research on fire safety related to this remains insufficient. In this study, we visited four logistics facilities with mezzanine racks and one logistics facility using shelf racks to investigate their fundamental characteristics. Considering the characteristics of logistics facilities that store various combustibles, a fire test was conducted using unit shelf racks with packaging materials, boxes, and expandable polystyrene (EPS). Shelf racks loaded with corrugated fiberboard, cardboard boxes, and EPS exhibited the highest fire risk and were set as combustibles inside the rack. Before the experiment, the radiative heat flux was measured by considering the spacing distances of mezzanine racks observed on-site. The most frequently measured range was 43.7–67.3 kW/m² at 1.0–1.5 m. After beginning the fire experiment, when simulating mezzanine racks with aisle widths of 1.2–2.0 m, fire owing to radiative heat occurred within 5 min in the separated shelf racks. Based on the results, we estimate that the minimum separation distance required to prevent radiant heat-based fires between shelving racks inside a mezzanine is 3.2 m. These findings are expected to be utilized in fire prevention by increasing the understanding of the spread of fire in shelf racks. Full article

Wood quality has been an ongoing concern for science, having become increasingly important in the current context, in which the demand for wood is increasing and forest fires are more frequent and violent. This study aims to evaluate the quality of wood in trees affected by fires and the negative impact of these phenomena on the speed of wood degradation, as a result of weakening the trees due to the action of stress factors. The study was carried out using modern techniques on beech trees (Fagus sylvatica L.) remaining in an area affected by a litter fire in 2017. Measurements were taken with the Arbotom Rinntech sound tomograph, the IML Resi F-500S resist graph, and the Pressler core sampler to observe the quality of the wood inside the trees. It was found that all the trees were in various stages of decay, the tomograms being able to characterize the severity of decay only in the case of fully decayed wood as a result of the action of xylophages fungi, whose harmful influence is more pronounced when the injuries sustained by the trees are higher. Although the trees attempted to close the fire wounds through their own defense mechanisms, the destructive action of the fungi intensified with time. After the forest fires, for an effective assessment of the wood’s internal quality, the resist graph can be used. For valuable trees, one could use the tomograph, but the measurements have to be taken only by qualified operators. Full article

Wildfires burn annually over 400,000 ha in Mediterranean countries. By the end of the 21st century, wildfire Burnt Area (BA) and associated Green House Gas (GHG) emissions may double to triple due to climate change. Regional projections of future BA are urgently required to update wildfire policies. We present a robust methodology for estimating regional wildfire BA and GHG emissions under future climate change scenarios in the Mediterranean. The Fire Weather Index, selected drought indices, and meteorological variables were correlated against BA/GHG emissions data to create area-specific statistical projection models. State-of-the-art regional climate models (horizontal resolution: 12 km), developed within the EURO-CORDEX initiative, simulated data under three climate change scenarios (RCP2.6, RCP4.5, and RCP8.5) up to 2070. These data drove the statistical models to estimate future wildfire BA and GHG emissions in three pilot areas in Greece, Montenegro, and France. Wildfire BA is projected to increase by 20% to 130% up to 2070, depending on the study area and climate scenario. The future expansion of fire-prone areas into the north Mediterranean and mountain environments is particularly alarming, given the large biomass present here. Fire-smart landscape management may, however, greatly reduce the projected future wildfire BA and GHG increases. Full article

Most fire spread is caused by the absence of suppression means at the beginning of the fire. This results in the missed golden time. There are various factors that cause initial fires, such as electrical outlets, general distribution circuits, and oil–vapor–gas cluster spaces. In most cases, these places are out of reach of human hands or they lose the initial suppression time when a fire occurs, causing the spread of fire. This study implements an intelligent fire suppression device that connects sensor IoT based on microcapsules to secure initial fire suppression and golden time in the event of a fire in blind spots that cannot be seen by humans or at a time when it is difficult to recognize a fire. The microcapsule is a micro-collection unit that collects Novec 1230 gas generated in the semiconductor production process. The microcapsule is molded into a form with a fire suppression function and, when a fire occurs, the molded body explodes and absorbs ambient oxygen to suppress the fire. The complex-sensor IoT executes smoke and heat detection generated when a fire is suppressed within 10 s, which ensures the reliability of the detector by notifying of the fire and detecting the ignition point through communication linkages such as Ieee 485 and WiFi or LoRa. Full article

Detecting wildfires presents significant challenges due to the presence of various potential targets in fire imagery, such as smoke, vehicles, and people. To address these challenges, we propose a novel multi-label classification model based on BiFormer’s feature extraction method, which constructs sparse region-indexing relations and performs feature extraction only in key regions, thereby facilitating more effective capture of flame characteristics. Additionally, we introduce a feature screening method based on a domain-adversarial neural network (DANN) to minimize misclassification by accurately determining feature domains. Furthermore, a feature discrimination method utilizing a Graph Convolutional Network (GCN) is proposed, enabling the model to capture label correlations more effectively and improve performance by constructing a label correlation matrix. This model enhances cross-domain generalization capability and improves recognition performance in fire scenarios. In the experimental phase, we developed a comprehensive dataset by integrating multiple fire-related public datasets, and conducted detailed comparison and ablation experiments. Results from the tenfold cross-validation demonstrate that the proposed model significantly improves recognition of multi-labeled images in fire scenarios. Compared with the baseline model, the mAP increased by 4.426%, CP by 4.14% and CF1 by 7.04%. Full article

Evidence has previously shown that outer tunics (turnout coats) worn by firefighters at structural fires are contaminated with harmful chemicals which subsequently off-gas from the material. However, there is limited research on whether this phenomenon extends to wildland firefighter uniforms. This pilot study aimed to explore if the tunics of volunteer bushfire and forestry firefighters in Western Australia off-gas any contaminants after exposure to prescribed burns or bushfires, and whether there is a need to explore this further. Nine tunics were collected from firefighters following nine bushfire and prescribed burn events, with a set of unused tunics serving as a control. Chemical analysis was performed on these tunics to assess levels of acrolein, benzene, formaldehyde, and sulphur dioxide contamination. The assessment involved measuring chemical off-gassing over a 12 h period using infrared spectrometry. Tunics worn by firefighters appear to adsorb acrolein, benzene, formaldehyde, and sulphur dioxide from bushfire smoke and these contaminants are emitted from firefighting tunics following contamination at elevated concentrations. Further investigation of this research with a larger study sample will be beneficial to understand this phenomenon better and to determine the full extent and range of chemical contaminants absorbed by all firefighter clothing. Full article

In this study, a 1/10 reduced-scale model tunnel with one end closed was constructed to investigate maximum temperature profiles beneath the tunnel ceiling during fire events. By varying the heat release rates (HRRs) and tunnel slopes (0%, 2%, 5%, and 6%) and measuring horizontal temperatures longitudinally along the tunnel ceiling, the effects of these parameters were systematically examined. The findings reveal that the distribution of maximum temperatures within a one-end-closed tunnel can be categorized into three distinct regions: far-field, transition, and near-field regions. Notably, milder tunnel slopes correspond to an elevated maximum temperature beneath the ceiling. By employing dimensional analysis, two prediction models were formulated to forecast maximum temperatures beneath the ceiling for fire sources located in the far-field and near-field regions, respectively. These predictive models were validated against experimental data, demonstrating favorable agreement. This study enhances our understanding of the impact of tunnel slope on temperature distribution during fire events in one-end-closed tunnels. Furthermore, the prediction models developed offer practical tools for assessing and mitigating fire risks in such tunnel configurations. Full article

Soil and water bioengineering (SWBE) measures in fire-prone areas are essential for erosion mitigation, revegetation, as well as protection of settlements against inundations and landslides. This study’s aim was to detect erosive areas at the basin scale for SWBE implementation in pre- and post-fire conditions based on a wildfire event in 2019 in southern Ecuador. The Revised Universal Soil Loss Equation (RUSLE) was used in combination with earth observation data to detect the fire-induced change in erosion behavior by adapting the cover management factor (C-factor). To understand the spatial accuracy of the predicted erosion-prone areas, high-resolution data from an Unmanned Aerial Vehicle (UAV) served for comparison and visual interpretation at the sub-basin level. As a result, the mean erosion at the basin was estimated to be 4.08 t ha⁻¹ yr⁻¹ in pre-fire conditions and 4.06 t ha⁻¹ yr⁻¹ in post-fire conditions. The decrease of 0.44% is due to the high autonomous vegetation recovery capacity of grassland in the first post-fire year. Extreme values increased by a factor of 4 in post-fire conditions, indicating the importance of post-fire erosion measures such as SWBE in vulnerable areas. The correct spatial location of highly erosive areas detected by the RUSLE was successfully verified by the UAV data. This confirms the effectivity of combining the RUSLE with very-high-resolution data in identifying areas of high erosion, suggesting potential scalability to other fire-prone regions. Full article

Cold-formed steel (CFS) sections, increasingly favored in the construction industry due to their numerous advantages over hot-rolled steel, have received limited attention in research concerning the flexural behavior of galvanized iron (GI)-based CFS at elevated temperatures. Understanding how these materials and structures behave under elevated temperatures is crucial for fire safety. The authors have performed experimental studies previously on GI-based CFS under elevated temperatures. In that study, CFS sections made of GI of grade E350 of 1.5 m long and 2 mm thickness were used. Built-up beam sections were tested under two-point loading after heating to 60 and 90 min durations and subsequently cooling them down using air and water. This study aims to uncover the influence of different stiffener configurations on the load carrying capacity of sections under elevated temperature parametrically. With the experimental study results from previous studies as a reference, authors used FEM analysis to comprehensively study the behavior of GI-based CFS sections under fire. Vertical, horizontal, and not providing a stiffener were the configurations selected to study the beams parametrically. Parametric analysis confirmed that different stiffener configurations did not alter the predominant failure mode, which remained distortional buckling across all specimens. Beams with vertical stiffeners demonstrated superior performance compared to those with horizontal stiffeners in parametric analysis. Lateral–torsional buckling was observed in the reference specimen, lacking stiffeners due to inadequate restraint at the supports. Full article

A fire in the cargo compartment has a major impact on civil aviation flight safety, and according to the airworthiness clause of the CCAR-25, the detector must sound an alarm within 1 min of a fire in the cargo compartment. As for the cargo compartment of large transport aircrafts, the internal space is high and open, and the smoke movement speed becomes slower with significant cooling in the process of diffusion. Hysteresis can occur in smoke detectors because of their internal labyrinth structure, which causes the detector’s internal and external response signals to be out of sync. This research employs a numerical simulation to examine the detector response parameters under an ambient wind speed of 0.1–0.2 m/s and fits a Cleary two-stage hysteresis model, where τ₁= 0.09u^−1.43 and τ₂= 0.67u^−1.59. Finally, multiple full-scale cargo cabin experiments were conducted to validate the prediction model. The results show that the model’s predicted alarm range is 43.1 s to 49.0 s, and the actual alarm time obtained by the experiment falls within this interval, confirming the model’s accuracy and providing theoretical support for the structural design and layout of the aircraft cargo cabin smoke detector. Full article

Early detection of cable trench fires by locating the fire source in a timely manner can reduce the risk of fire. However, existing fire warning methods have low accuracy, long calculation times and difficulty coping with sudden fire situations. We established experimental platforms for cable trenches with different structures and combined these with simulation analysis to investigate the relationship between the ignition point position and the temperature distribution at the ceiling. An exponential function for predicting the ignition point position and the maximum temperature rise of tunnels is proposed based on the extreme values of ceiling temperature. The results indicate that the vertical temperature of the ceiling exhibits an exponential function variation pattern. The maximum deviation for identifying the ignition point is 0.098 m, with an average deviation of 0.044 m and an average accuracy of 98.77%. The maximum temperature prediction error for the ceiling is 14 °C, with an average deviation of 12.33 °C and an average accuracy of 98.30%. Compared to traditional fire prediction methods, the method proposed here has higher accuracy and provides a theoretical basis for early prevention and control of cable trench fires. Full article

Background. Wildfires may cause serious injuries to the anatomical structure of trees that can lead to tree death or long-lasting injury recovery, limiting their growth and vitality for several years. Post-fire management involves a wide range of measures aimed at recovering and restoring burnt areas. Usually, the first step is “salvage logging”, i.e., the removal of irremediably injured trees. The burn severity depends on several parameters and is variable within the burnt area. For this reason, in some areas, the death of apparently healthy individuals has often been observed even after several years. This study aims to assess delayed/latent mortality by analyzing glucose like a tracer in wood by using a blood glucometer and HPLC. Results. The glucose in the phloem, cambium, and last xylem rings was measured using a glucometer developed for measuring glucose in the blood. The adopted approach detected glucose concentrations that were recognizable for different functional levels of the trees. Conclusions. The glucometer was suitable to detect the glucose in wood and phloem in order to define the death or health of the disturbed and undisturbed trees post-fire. Further investigations are required to find new solutions for a rapid evaluation of the abiotic and biotic factors that influence tree functionality in the forest. This approach will be used to predict the probability of the death of the individuals injured, which would improve the efficiency and the economy of recovery operations. Full article

High-speed microjet hydrogen–air diffusion flames are investigated computationally. The focus is on the prediction of the so-called bottleneck phenomenon. The latter has been previously observed as a specific feature of the present flame class and has not yet been investigated computationally. In the configuration under consideration, the nozzle diameter is 0.5 mm and six cases with mean nozzle injection velocities (U) between 306 m/s and 561 m/s are considered. The flow in the nozzle lance is analyzed separately to obtain detailed inlet boundary conditions for the flame calculations. It is confirmed by calculation that the phenomenon is mainly determined by the transition to turbulence in the initial parts of the free jet. The transitional turbulence proves to be the biggest challenge in predicting this class of flames, as the generally available turbulence and turbulent combustion models reach the limits of their validity in transitional flows. In a Reynolds-Averaged Numerical Simulation framework, the Shear Stress Transport model is found to perform better than alternative two-equation models and is used as the turbulence model. By neglecting the interactions between the turbulence and chemistry (no-model approach), it is possible to predict the morphology of the bottleneck flame and its dependence on U qualitatively. However, the position of the bottleneck is overpredicted for U < 561 m/s. The experimental flames in the considered U range are all attached to the nozzle. This is also predicted by the no-model approach. The Eddy Dissipation Concept (EDC) used as the turbulence combustion model predicts, however, lifted flames (with increasing lift-off height as U decreases). With the EDC, no bottleneck morphology is observed for U = 561 m/s. For lower U, the EDC results for the bottleneck position are generally closer to the measurements. It is demonstrated that accuracy in predicting the bottleneck position can be improved by ad hoc modifications of the turbulent viscosity. Full article