Search Results (17)

Early warning systems on edge devices such as satellites and unmanned aerial vehicles (UAVs) are essential for effective forest fire prevention. Edge Intelligence (EI) enables deploying deep learning models on edge devices; however, traditional convolutional neural networks (CNNs)/Transformer-based models struggle to balance local-global context integration and computational efficiency in such constrained environments. To address these challenges, this paper proposes HybriDet, a novel hybrid-architecture neural network for wildfire detection. This architecture integrates the strengths of both CNNs and Transformers to effectively capture both local and global contextual information. Furthermore, we introduce efficient attention mechanisms—Windowed Attention and Coordinate-Spatial (CS) Attention—to simultaneously enhance channel-wise and spatial-wise features in high-resolution imagery, enabling long-range dependency modeling and discriminative feature extraction. Additionally, to optimize deployment efficiency, we also apply model pruning techniques to improve generalization performance and inference speed. Extensive experimental evaluations demonstrate that HybriDet achieves superior feature extraction capabilities while maintaining high computational efficiency. The optimized lightweight variant of HybriDet has a compact model size of merely 6.45 M parameters, facilitating seamless deployment on resource-constrained edge devices. Comparative evaluations on the FASDD-UAV, FASDD-RS, and VOC datasets demonstrate that HybriDet achieves superior performance over state-of-the-art models, particularly in processing highly heterogeneous remote sensing (RS) imagery. When benchmarked against YOLOv8, HybriDet demonstrates a 6.4% enhancement in mAP50 on the FASDD-RS dataset while maintaining comparable computational complexity. Meanwhile, on the VOC dataset and the FASDD-UAV dataset, our model improved by 3.6% and 0.2%, respectively, compared to the baseline model YOLOv8. These advancements highlight HybriDet’s theoretical significance as a novel hybrid EI framework for wildfire detection, with practical implications for disaster emergency response, socioeconomic security, and ecological conservation. Full article

To address the difficulty frontline commanders face in accurately perceiving fireground risks during the early stages of oil storage tank fires, in this study, we propose a method that integrates complex network theory with a multi-source information fusion approach based on cloud models and Dempster-Shafer (D-S) evidence theory for situational analysis and dynamic perception. Initially, the internal evolution of accident scenarios within individual tanks is modeled as a single-layer network, while scenario propagation between tanks is represented through inter-layer connections, forming a multi-layer complex network for the storage area. The importance of each node is evaluated to assess the risk level of scenario nodes, enabling preliminary situational awareness, with limited reconnaissance information. Subsequently, the cloud model’s capability to handle fuzziness is combined with D-S theory’s strength in fusing multi-source data. Multi-source heterogeneous information is integrated to obtain the confidence levels of key nodes across low, medium, and high-risk categories. Based on these results, high-risk scenarios in oil storage tank emergency response are dynamically adjusted, enabling the updating and prediction of accident evolution. Finally, the proposed method is validated using the 2015 Gulei PX plant explosion case study. The results demonstrate that the approach effectively identifies high-risk scenarios, enhances dynamic situational perception, and is generally consistent with actual accident progression, thereby improving emergency response capability. Full article

Frequent grassland fires have severely affected regional ecosystems as well as the production and living conditions of local residents. Grassland fire prevention capabilities constitute an integral part of the disaster prevention and mitigation system and play an important role in improving grassroots governance. To gain a deeper understanding of the practical foundation and influencing mechanisms of grassland fire prevention capabilities, establish an evaluation index system for prevention capabilities covering the four dimensions of disaster prevention, disaster resistance, disaster relief, and recovery. Combining micro-level survey data, a quantile regression model is used to analyze the influencing factors. The research findings indicate that (1) disaster resistance (0.49) plays a prominent role in grassland fire prevention capabilities, with economic foundations and individual disaster relief capabilities being particularly critical for overall improvement. Although residents have strong fire prevention awareness, their organizational collaboration capabilities are relatively weak, and there are significant differences in prevention capabilities across regions, necessitating tailored, precise enhancements. (2) There are significant differences in prevention capabilities among residents of different agricultural and pastoral production types, with semi-agricultural and semi-pastoral areas having the strongest comprehensive capabilities and pastoral areas relatively weaker. (3) A significant analysis of factors influencing grassland fire prevention capabilities: effective and diverse risk communication is a prerequisite for enhancing residents’ prevention capabilities; the level of panic regarding grassland fires and road infrastructure are important influencing factors, but residents’ understanding of climate change and grassroots organizations’ capacity for mechanism construction have insignificant impacts. Therefore, in future grassland fire disaster prevention and mitigation efforts, it is essential to strengthen risk communication, improve infrastructure, monitor environmental changes and the spatiotemporal patterns of grassland fires, enhance residents’ understanding of climate change, reinforce the emergency response capabilities of grassroots organizations, and stimulate public participation awareness to collectively build a multi-tiered grassland fire prevention system. Full article

Polycyclic aromatic hydrocarbons (PAHs) are increasingly recognized as a major contributor to the occupational cancer risk among firefighters. In response, the National Fire Protection Association (NFPA) and other regulatory bodies have recommended rigorous decontamination protocols to minimize PAH exposure. Despite these efforts, a critical gap persists: the absence of real-time, field-deployable devices capable of detecting these invisible and toxic compounds during firefighting operations or within fire stations. Additionally, the lack of effective and optimized methods for the removal of these hazardous substances from the immediate environments of firefighters continues to pose a serious occupational health challenge. Although numerous studies have investigated PAH detection in environmental contexts, current technologies are still largely confined to laboratory settings and are unsuitable for field use. This review critically examines recent advances in PAH decontamination strategies for firefighting and explores alternative sensing solutions. We evaluate both conventional analytical methods, such as gas chromatography, high-performance liquid chromatography, and mass spectrometry, and emerging portable PAH detection technologies. By highlighting the limitations of existing systems and presenting novel sensing approaches, this paper aims to catalyze innovation in sensor development. Our ultimate goal is to inspire the creation of robust, field-deployable tools that enhance decontamination practices and significantly improve the health and safety of firefighters by reducing their long-term risks of cancer. Full article

To enhance the understanding and management of fire risks in subway stations, this study aims to identify critical fire risk transmission paths using an integrated PSR–DEMATEL–ISM approach. A comprehensive evaluation framework is first constructed based on the Pressure–State–Response (PSR) model, systematically categorizing 22 influencing factors into three dimensions: pressure, state, and response. The Decision-Making Trial and Evaluation Laboratory (DEMATEL) method is then employed to analyze the causal relationships and centrality among these factors, distinguishing between cause and effect groups. Subsequently, Interpretive Structural Modeling (ISM) is applied to organize the factors into a multi-level hierarchical structure, enabling the identification of risk propagation pathways. The analysis reveals five high-centrality and high-causality factors: fire safety education and training, completeness of fire management rules and regulations, fire smoke detection and firefighting capability, operational status of monitoring equipment, and effectiveness of emergency response plans. Based on these key drivers, six major transmission paths are derived, reflecting the internal logic of fire risk evolution in subway environments. Among them, chains originating from Fire Safety Education and Training (S6), Architectural Fire Protection Design (S7), and Completeness of Fire Management Rules and Regulations (S16) exhibit the most significant influence on system-wide safety performance. This study provides theoretical support and practical guidance for proactive fire prevention and emergency planning in urban rail transit systems, offering a structured and data-driven approach to identifying vulnerabilities and improving system resilience. Full article

Conveyor belts are critical in various industries, particularly in the barrier eddy current separator systems used in recycling processes. However, hidden issues, such as belt misalignment, excessive heat that can lead to fire hazards, and the presence of sharp or irregularly shaped materials, reduce operational efficiency and pose serious threats to the health and safety of personnel on the production floor. This study presents an intelligent monitoring and protection system for barrier eddy current separator conveyor belts designed to safeguard machinery and human workers simultaneously. In this system, a thermal camera continuously monitors the surface temperature of the conveyor belt, especially in the area above the magnetic drum—where unwanted ferromagnetic materials can lead to abnormal heating and potential fire risks. The system detects temperature anomalies in this critical zone. The early detection of these risks triggers audio–visual alerts and IoT-based warning messages that are sent to technicians, which is vital in preventing fire-related injuries and minimizing emergency response time. Simultaneously, a machine vision module autonomously detects and corrects belt misalignment, eliminating the need for manual intervention and reducing the risk of worker exposure to moving mechanical parts. Additionally, a line-scan camera integrated with the YOLOv11 AI model analyses the shape of materials on the conveyor belt, distinguishing between rounded and sharp-edged objects. This system enhances the accuracy of material separation and reduces the likelihood of injuries caused by the impact or ejection of sharp fragments during maintenance or handling. The YOLOv11n-seg model implemented in this system achieved a segmentation mask precision of 84.8 percent and a recall of 84.5 percent in industry evaluations. Based on this high segmentation accuracy and consistent detection of sharp particles, the system is expected to substantially reduce the frequency of sharp object collisions with the BECS conveyor belt, thereby minimizing mechanical wear and potential safety hazards. By integrating these intelligent capabilities into a compact, cost-effective solution suitable for real-world recycling environments, the proposed system contributes significantly to improving workplace safety and equipment longevity. This project demonstrates how digital transformation and artificial intelligence can play a pivotal role in advancing occupational health and safety in modern industrial production. Full article

Extreme spread events (ESEs), often characterized by high intensity and rapid rates of spread, can overwhelm fire suppression and emergency response capacity, threaten responder and public safety, damage landscapes and communities, and result in high socioeconomic costs and losses. Advances in remote sensing and geospatial analysis provide an improved understanding of observed ESEs and their contributing factors; however, there is a need to improve anticipatory and predictive capabilities to better prepare, mitigate, and respond. Here, leveraging individual-fire day-of-arrival raster outputs from the FSim fire modeling system, we prototype and evaluate methods for the simulation and categorization of ESEs. We describe the analysis of simulation outputs on a case study landscape in Colorado, USA, summarize daily spread event characteristics, threshold and probabilistically benchmark ESEs, spatially depict ESE potential, and describe limitations, extensions, and potential applications of this work. Simulation results generally showed strong alignment with historical patterns of daily growth and the proportion of cumulative area burned in the western US and identified hotspots of high ESE potential. Continued analysis and simulation of ESEs will likely expand the horizon of uses and grow in salience as ESEs become more common. Full article

The large-scale storage and stable supply of oil products are essential for national energy security and economic development. As the economy expands and energy demands rise, centralized storage and supply systems become increasingly vital for ensuring the efficiency and reliability of oil product distribution. However, large oil storage depots present substantial safety risks. In the event of fires, explosions, or other accidents, emergency response efforts face stringent demands and challenges. To enhance the emergency response capabilities of oil storage and transportation bases (OSTBs), this paper proposes an innovative approach that integrates the improved analytic hierarchy process (IAHP) with the Entropy Weight Method (EMW) to determine the combined weights of various indices. This approach reduces the subjective bias associated with the traditional analytic hierarchy process (AHP). The emergency response capabilities of OSTBs are subsequently evaluated through fuzzy comprehensive analysis. An empirical study conducted on an OSTB in the Zhoushan archipelago quantitatively assesses its emergency preparedness. The results show that the base excels in pre-incident prevention, demonstrates robust preparedness and response capabilities, and exhibits moderate recovery abilities after incidents. These findings provide a theoretical foundation for reducing the likelihood of accidents, enhancing emergency response efficiency, and mitigating the severity of consequences. Practical recommendations are also offered based on the results. Full article

Taipei mass rapid transit (MRT), operational since 1996, serves up to two million passengers daily. Equipment malfunctions pose a safety risk, making the dual goals of cost reduction and safety a significant challenge. Recently, outsourcing non-core technical tasks has emerged as an effective cost-control strategy, allowing resource allocation to employee salaries and operational efficiency. This study uses the analytic hierarchy process (AHP) and fuzzy analytic hierarchy process (FAHP) to prioritize outsourcing for electromechanical equipment. It incorporates analysis from the outsourcing literature, historical data, and ISO documents from Taipei MRT. The research included interviews and surveys with seven senior managers, using software to analyze the outsourcing priorities of four key systems: electrical and fire safety, environmental air conditioning, escalators and elevators, and power supply. It suggests prioritizing environmental air conditioning, followed by power supply systems, escalators and elevators, and electrical and fire safety systems. Additionally, this study employed the FAHP and the technique for order of preference by similarity to ideal solution (TOPSIS) for the rigorous evaluation and monitoring of vendor selection to ensure quality service and effective contract execution. By comparing technical expertise, problem-solving capabilities, certifications, response times, and contractual performance, this study identified the most suitable vendors. It concludes with recommendations for Taipei MRT to enhance maintenance quality and reduce costs. Full article

The fire heat release rate (HRR) is a crucial parameter for describing the combustion process and its thermal effects. In recent years, some studies have employed fire scene images and deep learning algorithms to predict real-time fire HRR, which has led to the advancement of HRR prediction in terms of both lightweightness and real-time monitoring. Nevertheless, the development of an early-stage monitoring system for fires and the ability to predict future HRR based on current moment data represents a crucial foundation for evaluating the scale of indoor fires and enhancing the capacity to prevent and control such incidents. This paper proposes a deep learning model based on continuous fire scene images (containing both flame and smoke features) and their time-series information to predict the future transient fire HRR. The model (Att-BiLSTM) comprises three bi-directional long- and short-term memory (Bi-LSTM) layers and one attention layer. The model employs a bidirectional feature extraction approach, followed by the introduction of an attention mechanism to highlight the image features that have a critical impact on the prediction results. In this paper, a large-scale dataset is constructed by collecting 27,231 fire scene images with instantaneous HRR annotations from 40 different fire trials from the NIST database. The experimental results demonstrate that Att-BiLSTM is capable of effectively utilizing fire scene image features and temporal information to accurately predict future transient HRR, including those in high-brightness fire environments and complex fire source situations. The research presented in this paper offers novel insights and methodologies for fire monitoring and emergency response. Full article

Natural hazards such as wildfires have proven to be more frequent in recent years, and to minimize losses and activate emergency response, it is necessary to estimate their impact quickly and consequently identify the most affected areas. Volunteered geographic information (VGI) data, particularly from the social media platform Twitter, now X, are emerging as an accessible and near-real-time geoinformation data source about natural hazards. Our study seeks to analyze and evaluate the feasibility and limitations of using tweets in our proposed method for fire area assessment in near-real time. The methodology involves weighted barycenter calculation from tweet locations and estimating the affected area through various approaches based on data within tweet texts, including viewing angle to the fire, road segment blocking information, and distance to fire information. Case study scenarios are examined, revealing that the estimated areas align closely with fire hazard areas compared to remote sensing (RS) estimated fire areas, used as pseudo-references. The approach demonstrates reasonable accuracy with estimation areas differing by distances of 2 to 6 km between VGI and pseudo-reference centers and barycenters differing by distances of 5 km on average from pseudo-reference centers. Thus, geospatial analysis on VGI, mainly from Twitter, allows for a rapid and approximate assessment of affected areas. This capability enables emergency responders to coordinate operations and allocate resources efficiently during natural hazards. Full article

Nowadays, underground coal mine accidents occur frequently, causing huge casualties and economic losses, most of which are gas explosion accidents caused by fires. In order to improve the emergency rescue capability of coal mine fires and reduce the losses caused by coal mine fires, this article is dedicated to the assessment of coal mine fire rescue capability. Taking the fire emergency rescue system of Lugou mine as an example, based on the introduction of gray system theory and gray evaluation method, an evaluation model was established to assess the risk of the fire emergency rescue index system of Lugou mine. Four primary and 19 secondary indicators were delineated, and a hierarchical structure model of the fire emergency rescue capability of the Lugou mine was established by combining expert opinions, and the weights of indicators at all levels were calculated by using hierarchical analysis. We then used the gray system evaluation method and expert scoring to judge the safety level of various indicator factors in the index system. The evaluation results show that the risk level of the emergency rescue system of the Lugou mine fire is higher than the fourth level. The main risk indicator factors are firefighting equipment, decision-making command, emergency education and training, and fire accident alarm. In response to this evaluation result, corresponding control measures were formulated in four aspects: rescue organization guarantee, personnel guarantee, material guarantee, and information guarantee, which optimally improved the emergency rescue capability of the Lugou mine fire and reduced the loss caused by fire. Full article

Road tunnels are equipped with various safety installations that enable the tunnel’s autonomous response to fire in order to ensure conditions suitable for safe self-rescue and evacuation. A key role in this effort is played by the monitoring of the longitudinal airflow velocity and its regulation. This study contributes to validation of the Fire Dynamics Simulator (FDS 6) capabilities to model tunnel airflow generated by emergency ventilation. A previous study, in which an FDS 6 model of a real 900 m long motorway tunnel was developed and validated by a full-scale ventilation test, pointed to the relatively high inaccuracies of the average steady-state airflow velocity generated by ventilation measured by tunnel anemometers (13%, 17% and 14% for three ventilation modes). In this paper, it is shown that the application of a modified evaluation procedure and improving the representation of tunnel anemometers leads to the significant improvement of simulation results with inaccuracies of 5%, 1% and 3% for the considered ventilation modes. The observed inaccuracies are even comparable to the measurement accuracy of the tunnel anemometers. A further extension of the modeling of the steady-state airflow velocity generated by emergency ventilation measured by the used anemometers is also described. Full article

This paper presents the MINDED-FBA, a remote-sensing-based tool for the determination of both flooded and burned areas. The tool, freely distributed as a QGIS plugin, consists of an adaptation and development of the previously published Multi Index Image Differencing methods (MINDED and MINDED-BA). The MINDED-FBA allows the integration and combination of a wider diversity of satellite sensor datasets, now including the synthetic aperture radar (SAR), in addition to optical multispectral data. The performance of the tool is evaluated for six case studies located in Portugal, Australia, Pakistan, Italy, and the USA. The case studies were chosen for representing a wide range of conditions, such as type of hazardous event (i.e., flooding or fire), scale of application (i.e., local or regional), site specificities (e.g., climatic conditions, morphology), and available satellite data (optical multispectral and SAR). The results are compared in respect to reference delineation datasets (mostly from the Copernicus EMS). The application of the MINDED-FBA tool with SAR data is particularly effective to delineate flooding, while optical multispectral data resulted in the best performances for burned areas. Nonetheless, the combination of both types of remote sensing data (data fusion approach) also provides high correlations with the available reference datasets. The MINDED-FBA tool could represent a new near-real-time solution, capable of supporting emergency response measures. Full article

One of the United Nations (UN) Sustainable Development Goals is climate action (SDG-13), and wildfire is among the catastrophic events that both impact climate change and are aggravated by it. In Australia and other countries, large-scale wildfires have dramatically grown in frequency and size in recent years. These fires threaten the world’s forests and urban woods, cause enormous environmental and property damage, and quite often result in fatalities. As a result of their increasing frequency, there is an ongoing debate over how to handle catastrophic wildfires and mitigate their social, economic, and environmental repercussions. Effective prevention, early warning, and response strategies must be well-planned and carefully coordinated to minimise harmful consequences to people and the environment. Rapid advancements in remote sensing technologies such as ground-based, aerial surveillance vehicle-based, and satellite-based systems have been used for efficient wildfire surveillance. This study focuses on the application of space-borne technology for very accurate fire detection under challenging conditions. Due to the significant advances in artificial intelligence (AI) techniques in recent years, numerous studies have previously been conducted to examine how AI might be applied in various situations. As a result of its special physical and operational requirements, spaceflight has emerged as one of the most challenging application fields. This work contains a feasibility study as well as a model and scenario prototype for a satellite AI system. With the intention of swiftly generating alerts and enabling immediate actions, the detection of wildfires has been studied with reference to the Australian events that occurred in December 2019. Convolutional neural networks (CNNs) were developed, trained, and used from the ground up to detect wildfires while also adjusting their complexity to meet onboard implementation requirements for trusted autonomous satellite operations (TASO). The capability of a 1-dimensional convolution neural network (1-DCNN) to classify wildfires is demonstrated in this research and the results are assessed against those reported in the literature. In order to enable autonomous onboard data processing, various hardware accelerators were considered and evaluated for onboard implementation. The trained model was then implemented in the following: Intel Movidius NCS-2 and Nvidia Jetson Nano and Nvidia Jetson TX2. Using the selected onboard hardware, the developed model was then put into practice and analysis was carried out. The results were positive and in favour of using the technology that has been proposed for onboard data processing to enable TASO on future missions. The findings indicate that data processing onboard can be very beneficial in disaster management and climate change mitigation by facilitating the generation of timely alerts for users and by enabling rapid and appropriate responses. Full article