Fire Risk Factors Research Articles

Wildfire risk assessment and mapping – an approach for Natura 2000 forest sites

Over the last ten years, Bulgaria's forest areas have been under almost year-round fire activity, severely impacting the Natura 2000 sites: Managing forests and maintaining traditional links between people and nature in mountain sites is becoming increasingly challenging. However, the National Methodology for determining the risk of forest fires (proposed in 2016) is applicable only at the regional administrative level (NUTS 3). This study is motivated by the actual need for an approach and a toolbox that can accurately assess the risk of wildfires, considering the unique characteristics of each location. An object-oriented vulnerability analysis is necessary to ensure that all parties involved in wildfire risk management can respond effectively. The main objective of this study is to suggest a flexible and scalable approach for spatial assessment and mapping of wildfire risk in geographic units relevant to natural heritage maintenance and resource management. A single register of potential fire risk factors is proposed, integrating 29 indicators into five thematic groups reflecting up-to-date data on hazards, vulnerability, and emergency response capacity. The factors are assessed and overlayed to come out with an integrated evaluation of the fire risk within a forestry subdivision - the smallest unit of forest management and inventory. The evaluation process involved geospatial technologies for analyzing the data and mapping the results. The methodology is tested on two Natura 2000 sites - BG0000496 “Rilski Manastir” (includes UNESCO’ World Heritage Site and symbol of Bulgarian identity – Rila Monastery) and BG0001011 “Osogovska Planina”, for which a conservation concern has been identified under the influence of wildfire risk. It has been confirmed that risk maps have the potential to support response teams, as demonstrated during a fire event that occurred on October 30th, 2022. The results from the study were used to identify suitable locations for the construction of fire towers and a visitor information system at BG0000496 “Rilski Manastir”.

Forest fire risk zoning based on fuzzy logic and analytical network process.

Forest fires have a significant impact on human life, property safety, and ecological environment. Deve-loping high-quality forest fire risk maps is beneficial for preventing forest fires, guiding resource allocation for firefighting, assisting in fire suppression efforts, and supporting decision-making. With a multi-criteria decision analysis (MCDA) method based on geographic information systems (GIS) and literature review, we assessed the main factors influencing the occurrences of forest fires in Youxi County, Fujian Province. We analyzed the importance of each fire risk factor using the analytic network process (ANP) and assigned weights, and evaluated the sub-standard weights using fuzzy logic assessment. Using ArcGIS aggregation functions, we generated a forest fire risk map and validated it with satellite fire points. The results showed that the areas classified as level 4 or higher fire risk accounted for a considerable proportion in Youxi County, and that the central and northern regions were at higher risk. The overall fire risk situation in the county was severe. The fuzzy ANP model demonstrated a high accuracy of 85.8%. The introduction of this novel MCDA method could effectively improve the accuracy of forest fire risk mapping at a small scale, providing a basis for early fire warning and the planning and allocation of firefighting resources.

전통시장 화재위험요인과 대응방안 우선순위에 관한 연구

Fires in traditional markets are a yearly occurrence and are highly likely to expand into large-scale fires and disasters. Therefore, in order to prevent the spread of large fires in traditional markets, it is important to closely analyze fire risk factors and derive countermeasures. Accordingly, the results of the previous research case survey — the traditional market fire status survey — were analyzed and countermeasures were presented based on the derived fire risk factors and problems. In addition, 30 fire officials who are experts in the field of fire risks were surveyed (expert survey techniques) and the importance and priority of fire risk factors and countermeasures were analyzed through risk assessment and Analytic Hierarchy Process.

A PSO-CNN-Based Deep Learning Model for Predicting Forest Fire Risk on a National Scale

Forest fires have a significant impact on terrestrial ecosystems, leading to harm to biodiversity and environment. To mitigate the ecological damage caused by forest fires, it was necessary to develop prediction models of fire risk. In this study, by evolving the optimal architecture and parameters using the particle swarm optimization (PSO) algorithm, a convolutional neural network (CNN) deep learning model was proposed to predict forest fire risk on a national scale. Utilizing fire data and fire risk factors from 2001 to 2020 in China, the PSO-CNN-based deep learning model (PSO-CNN) was utilized and tested. Compared to logistic regression, random forest, support vector machine, k-nearest neighbors, and CNN models, the PSO-CNN model exhibited superior performance with an accuracy of 82.2% and an AUC value of 0.92. These results clearly highlighted the effectiveness of the PSO-CNN model in enhancing the accuracy of forest fire prediction. Furthermore, the forest fire risk prediction level estimated by the proposed model on a national scale for the entire country was mostly consistent with actual fire data distribution, indicating its potential to be used as an important direction for deep learning in forest fire prediction research.

The Effect Of Fire Prevention On Restricted Area Protection Efforts At DPPU Iswahjudi Magetan

One of the fire risk factors at the Iswahjudi Aviation Fuel Depot Intoplane Services is negligence in the process of receiving, stockpiling and distribution (RSD). This is in accordance with the results of field observations that show negligence. The purpose of this study is to determine the Effect of Fire Prevention on Restricted Area Protection Efforts at the Iswahjudi Magetan Aviation Fuel Depot Intoplane Services (DPPU). This study using quantitative research with a crossectional approach, with a population of all workers and outsourced workers, totaling 27 workers. The sampling technique uses the total sampling technique. In this research, the researchers use primary data in the form of fire prevention questionnaires, and restricted area protection, with analysis using the chi square test. The results showed fire prevention with a p-value of 0,008 ≤ 0,05 so that there was an influence between fire prevention and restricted area protection efforts in DPPU Iswahjudi Magetan. Fire prevention at DPPU Iswahjudi Magetan is in the good category, while area protection efforts are restricted in the excellence category. The suggestion from the researchers to realize effective and suistainable restricted area protection efforts such as in security aspects with patrol programs and team coordination.

Fatal structure fire classification from building fire data using machine learning

PurposeThis study aims to develop a machine learning model to detect structure fire fatalities using a dataset comprising 11,341 cases from 2011 to 2019.Design/methodology/approachExploratory data analysis (EDA) was conducted prior to modelling, in which ten machine learning models were experimented with.FindingsThe main fatal structure fire risk factors were fires originating from bedrooms, living areas and the cooking/dining areas. The highest fatality rate (20.69%) was reported for fires ignited due to bedding (23.43%), despite a low fire incident rate (3.50%). Using 21 structure fire features, Random Forest (RF) yielded the best detection performance with 86% accuracy, followed by Decision Tree (DT) with bagging (accuracy = 84.7%).Research limitations/practical implicationsLimitations of the study are pertaining to data quality and grouping of categories in the data pre-processing stage, which could affect the performance of the models.Originality/valueThe study is the first of its kind to manipulate risk factors to detect fatal structure classification, particularly focussing on structure fire fatalities. Most of the previous studies examined the importance of fire risk factors and their relationship to the fire risk level.

An Analysis of Related Laws and Literatures to Identify Fire Risk Factors for Factories in Industrial Complexes

Owing to recent factory fires in industrial complexes, fire safety measures are being prepared nationally. Accordingly, this study conducted an analysis of related laws and literatures to identify fire risk factors for factories in industrial complexes as part of the development of fire prediction, control, and response technologies. Through this, the definition and classification system for industrial complexes, application of fire safety measures, fire risk factor identification methods and processes, and fire characteristics and protection measures for factories in industrial complexes were examined. The review results confirmed that the buildings corresponding to factories in industrial complexes were large, and the facilities were of Type 3. Based on this, the scale and scope of buildings located in fire risk blind spots in factories within industrial complexes were set to be less than 5,000 m<sup>2</sup> in total floor area and no more than 10 stories (less than 33 m in height). In addition, in & exterior of protection and risk (IEPR) analysis using strengths, weaknesses, opportunities, threats (SWOT) analysis was proposed to select fire risk factors for factories in industrial complexes. In conclusion, the following four fire risk factor selection models were proposed through matrix creation: fire risk, life safety, fire spread, and fire protection.

A fire risk assessment system and application for process industry using fuzzy Petri net and HAZID method

The safety risk assessment of process industries can determine the degree of safety risk and remind or warn safety management personnel to take corresponding measures according to the probability of accidents. In this paper, hazard identification (HAZID) method is combined with fuzzy Petri net to construct a hybrid safety assessment system. Firstly, the fire risk factors of HAZID are determined according to the fire statistics data. By dividing the whole industrial process into four stages, the complex hazard sources in the factory are investigated item by item, thus the fuzzy Petri net of real-time risk assessment is constructed. Taking an acetic acid enterprise as a case, this paper introduces how to construct such a risk assessment system in detail, and the system can dynamically predict the risk with changes in process conditions. This also demonstrates the feasibility of this method, which can be used as a reference for related research.

Analysis of the fire risks and mitigation approaches in the apparel manufacturing industry: Implications toward operational safety and sustainability

Fire risks pose a substantial threat to the apparel manufacturing industry since they can lead to immense property damage, potential loss of life, disruption of business operations, and reputational damage. In an emerging economy like Bangladesh, fire-related hazards are crucial due to the numerous deadly industrial fire incidents in recent years. This research, thereby, proposes an integrated multi-criteria decision-making (MCDM) framework to identify and mitigate fire risk hazards in the apparel manufacturing industry. Initially, the study identified 30 significant fire risk factors from the literature review. Then, after expert validation, an integrated Best Worst Method (BWM) and Weighted Sum Model (WSM) framework was utilized to prioritize the fire risk factors. Twenty-three mitigation actions were proposed afterward for the top-ranked risk factors based on National Fire Protection Association (NFPA) codes. An Interpretive Structural Modeling (ISM) with a Cross-Impact Matrix Multiplication Applied to Classification (MICMAC) analysis was later used to explore the interrelationships and dependencies among the mitigation actions. The ranking obtained from the BWM-WSM assessment revealed ‘combustible storage unseparated by fire-rated construction,’ ‘non-standard inspection, testing, and maintenance’, and ‘inadequate means of egress for the occupant load’ as the three most critical fire risk factors. The ISM-MICMAC analysis revealed ‘fire-rated construction’ and ‘standardized detection and protection’ as the most-driving mitigation actions. The study outcomes are expected to aid the managers and policymakers in emerging economies in formulating sustainable fire risk management strategies for the apparel industry and thus improve the operational safety and resilience of the sector.

Prediction of Peatlands Forest Fires in Malaysia Using Machine Learning

The occurrence of fires in tropical peatlands poses significant threats to their ecosystems. An Internet of Things (IoT) system was developed to measure and collect fire risk factors in the Raja Musa Forest Reserve (RMFR) in Selangor, Malaysia, to address this issue. In this paper, neural networks with different layers were employed to predict peatland forests’ Fire Weather Index (FWI). The neural network models used two sets of input parameters, consisting of four and nine fire factors. The predicted FWI values were compared with actual values obtained from the Malaysian meteorological department. The findings revealed that the five-layer neural network outperformed others in both the four-input and nine-input models. Specifically, the nine-input neural network achieved a mean square error (MSE) of 1.116 and a correlation of 0.890, surpassing the performance of the four-input neural network with the MSE of 1.537 and the correlation of 0.852. These results hold significant research and practical implications for precise peatland fire prevention, control, and the formulation of preventive measures.

Factors Contributing to Increased Building Fire Incidents in Sri Lanka

Aim: Despite the existence of established fire codes, the frequency of building fires in Sri Lanka has been on the rise in recent years. The primary objective of building codes is to ensure minimum acceptable fire safety standards in buildings, but deviations from the code can increase fire risk factors and exacerbate the severity of fires. This study aims to identify and rank such risk factors in three stages, beginning with design and concluding with maintenance. Introduction: Metodologia tego badania obejmuje podejście jakościowe, które uwzględnia przegląd literatury, ankietę opartą na kwestionariuszu oraz częściowo ustrukturyzowane wywiady ze specjalistami z branży pożarniczej. Kwestionariusz został opracowany w kontekście Sri Lanki. Wykwalifikowany i doświadczony zespół specjalistów ds. pożarnictwa został poproszony o uszeregowanie przygotowanego kwestionariusza, który został podsumowany w dwunastu kategoriach ryzyka. Chociaż metod oceny ryzyka pożarowego jest niewiele, w niniejszym badaniu zastosowano metodę wskaźnika względnej istotności. Wyniki uzyskane z pięciostopniowej skali Likerta, gdzie „1” to najmniejszy poziom ryzyka, a „5” to najwyższy poziom ryzyka, zostały przekonwertowane w celu identyfikacji priorytetów z RII. Project and methods: The methodology of this research consists of a qualitative approach, which includes a literature review, a questionnaire-based survey, and semi-structured interviews with fire industry professionals. The questionnaire was developed in a Sri Lankan context following an extensive literature review that included the author's experience. The qualified and experienced panel of fire specialists was asked to rank the prepared questionnaire, which was summarized into twelve risk categories. Though there are few fire risk ranking methods, the relative importance index method was applied in this research as it is simple and easy to use for ranking the risk factors. The results obtained from the five-point Likert scale, where “1” is the least risk level and “5” is the highest risk level, were converted to identify priorities with RII. Results: In the Sri Lankan context, it was discovered that issues with design and the approval of inaccurate building plans are the first and second major isk factors, respectively, out of the twelve categories identified. Thus, it was evident that deviations made at the design stage are the most significant risk factors, according to the Sri Lankan setting. Most of the mistakes that are made at the design stage cannot be rectified at a later stage under normal conditions, as it could incur huge costs to change the building structures. Conclusions: The study summarizes twelve factors that contribute to fire-related incidents in Sri Lankan buildings. Among these factors, the survey data shows that incorrect building design and the approval of inaccurate building plans for construction are the primary contributors to the high frequency and severity of fire-related incidents. Despite the availability of comprehensive fire safety regulations in Sri Lanka, the research reveals a significant gap in their implementation, from design to maintenance. These findings stress the importance of incorporating fire and safety management criteria into the building design stage, covering both construction and subsequent maintenance, to prevent fire incidents in Sri Lanka. Keywords: prescriptive fire codes, fire risk factors, fire risk assessment, fire risk ranking, building fire safety

HGV fire risk assessment method in highway tunnel based on a Bayesian network

The complex characteristics of long-distance highway tunnels may lead to serious loss of life and property in fire incidents. According to the statistical analysis, heavy goods vehicle (HGV) is one of the primary risk factors for tunnel fires. In this study, a quantitative risk assessment model of HGV-involved tunnel fires is established based on the functional resonance analysis method (FRAM) and Bayesian network (BN). Using FRAM, the mechanisms of the incident occurrence and evolution and critical risk factors of HGV-involved tunnel fires are determined, and the BN model is used to quantify the risk based on a probabilistic analysis. Focusing on operational management, monitoring system construction, type of transporting goods, emergency rescue, and egress facilities, the incident severity is determined in terms of casualties and economic losses. The proposed risk assessment method is expected to assist the tunnel operational management and the fire services in identifying critical risk factors in HGV-involved tunnel fires.

Surgical Fires Involving Alcohol-Based Preparation Solution, 1991-2020.

Alcohol-based skin preparations were first approved for surgical use in 1998 and have since become standard in most surgical fields. The purpose of this report is to examine incidence of surgical fires because of alcohol-based skin preparation and to understand how approval and regulation of alcohol-based skin preparations impacted trends in fires over time. We identified all reported surgical fires resulting in patient or staff harm from 1991 through 2020 reported to the Food and Drug Administration's Manufacturer and User Facility Device Experience (MAUDE) database. We examined incidence of fires because of these preparations, trends after approval and regulation, and common causes. We identified 674 reports of surgical fires resulting in harm to patients and surgical personnel, in which 84 involved an alcohol-based preparation. The time-adjusted model shows that from 1996 through 2006, there was a 26.4% increase in fires followed by a 9.7% decrease from 2007 to 2020. The decrease in fires was most rapid for head and neck and upper aerodigestive tract surgeries. Qualitative content analysis revealed improper surgical site preparation as well as close proximity of surgical sites to an oxygen source as the most common causes of fires. Since FDA approval, alcohol-based preparation solutions have been associated with a significant percentage of surgical fires. Warning label updates from 2006 to 2012 coupled with increased awareness efforts of associated risks of alcohol-based surgical solutions likely contributed to the decrease in fires. Improper surgical site preparation technique and close proximity of surgical sites to oxygen continue to be risk factors for fires. 4 Laryngoscope, 134:607-613, 2024.

Research on Urban Fire Station Layout Planning Based on a Combined Model Method

With the rapid development of urbanization, fire risk factors have increased greatly, indicating a higher requirement for urban firefighting security. Fire rescue capabilities can be effectively improved by the scientific layout of fire stations, and therefore, the optimal spatial arrangement of fire stations has practical implications for urban safety. In this paper, a method for planning the locations of urban fire stations is presented, taking into account the fire risk points of interest (POIs) data, road networks and fire station planning principles. The combined model method is validated against the nearest facility point model, and the service area model is proposed for the coverage of POIs and regional areas of planned new sites. The efficacy of the model is demonstrated through an improvement in the coverage of crosspoints of the regional area and points of interest (POIs), with increases of 10.20% and 12.43%, respectively. We applied the combined model method to Fengdong New Town, Shaanxi Province, China. A total of 11 new potential sites were proposed to improve the efficiency of spatial coverage, and subsequently, the coverage rate of the POIs and regional area reached 97.66% and 84.80%, respectively. This study provides application guidelines for the decision-making of fire services and the allocation of firefighting resources.

Identification and Assessment of Fire Risk Factors Using the Delphi Technique and Multiple-Criteria Decision Analysis A Case Study: Forest Parks in the Southern Slopes of Alborz, Iran

Identification and Assessment of Fire Risk Factors Using the Delphi Technique and Multiple-Criteria Decision Analysis A Case Study: Forest Parks in the Southern Slopes of Alborz, Iran

Factors associated with residential fire-related hospitalisations and deaths: A 10-year population-based study

This study aims to identify residential fire risk factors and their health outcomes in terms of hospital admissions from burns and smoke inhalation together with related readmissions, length of hospital stay (LOS), costs of hospitalisation and mortality within 30 days of the fire incidence. Residential fire-related hospitalisations from 2005 to 2014 in New South Wales, Australia were identified using linked data. Univariate and multivariable Poisson regression analyses were performed to determine factors associated with residential fires on hospital admission and loss of life. During the study period, 1862 individuals were hospitalised due to residential fires. In terms of prolonged LOS, high hospitalisation cost or mortality, fire incidents’ that damaged both contents and structures of the property; were ignited by smokers’ materials and/or due to mental or physical impairment of the residents had more adverse outcomes. Individuals aged 65 and over with comorbidities and/or acquired severe injuries from the fire incident were at a higher risk of long-term hospitalisation and death. This study provides information to response agencies in communicating fire safety messages and intervention programs to target vulnerable population. In addition, it also supplies indicators on hospital usage and LOS following residential fires to health administrators.

Old age and fire injury

Previous studies indicated that the elderly are vulnerable to fire injury. In this article, the nature of such vulnerability in terms of fire injury risk factors including age band, gender, occupancy level, deprivation, mobility, alcohol consumption and attempting to fight the fire is examined in a UK Fire and Rescue Service between April 2011 and April 2022. Fire injury risk was more common the greater the age of the elderly individual, more likely for males up to 74, but more likely for females above that age, possibly due to the greater proportion of females to males above age 74 in the area and time period studied. Elderly fire injuries mainly occurred in single occupancy housing and in more deprived areas. Cooking-related fire injuries accounted for 60.2% of elderly fire injuries, followed by smoking-related fire injuries (14.3%) and heating-related fire injuries (7.2%). Fire fatalities were not included in the analysis.

Analysis of Fire Risk Factors in Seoul, Korea, by Machine Learning

Analysis of Fire Risk Factors in Seoul, Korea, by Machine Learning

Risk Assessment of Green Intelligent Building Based on Artificial Intelligence.

Green smart building is the development direction of future architecture. It is of great significance to carry out risk assessment. Fire risk is the key content of building risk, so this paper takes fire risk as the research object, with the help of artificial intelligence technology, to carry out the risk assessment research of green smart buildings. With the rapid development of the economy, urban fire risk factors are increasing, and the fire situation is becoming more and more serious. Building fire risk assessment is an important measure to effectively prevent and control urban building fires. This paper uses Internet of Things data to carry out fire risk assessment and realize Internet of Things data mining. Collect a large number of expert samples to build training samples, train the green intelligent building monomer fire risk assessment and prediction model based on deep neural network, constantly adjust the model parameters to optimize the model, and finally verify and modify the model.

Electrical Responses of Pinus halepensis Mill. as an Indicator of Wildfire Risk in Mediterranean Forests by Complementing Live Fuel Moisture

Pinus halepensis forests, as Mediterranean-type ecosystems, are subject to high levels of wildfire risk in times of drought, with meteorological conditions of water stress and very high temperatures, mainly in summer. Considering the difficulty of knowing the phenological state of this species, the objective of this research was to evaluate the possibility of implementing the electrical responses (voltage and short-circuit current) as a variable in fire risk management models, compared to live fuel moisture. On the one hand, the obtained results demonstrate non-significant differences between the moisture content of the different fractions of the living branches (base and half of the branch and live fuel), even in times of drought with hydric stress and very high temperatures. Live fuel moisture of Pinus halepensis does not show significant seasonal variations under the influence of extreme fire risk factors. For this reason, it should be complemented with other variables for fire risk management models. On the other hand, the differences registered in the electrical signal show oscillations with significant variations, which are strongly correlated with the periods of extremely favourable meteorological conditions for wildfires. So, the voltages measured show ranges that correspond with great accuracy to the FWI. Voltage variation is dependent on the hydraulic dynamic plant behaviour and a result of the physiological response of pine trees to abiotic stress of drought. It is an easy-to-measure electrical parameter as well as a very reliable indicator with a high correlation with wildfire risk. Thus, electrical responses could add more knowledge about the phenological state of the trees in dependence on stress climatic conditions, allowing integration of these variables in the preventive wildfire modelling and management.