Fire Type Research Articles

The number of seedlings from the soil seed bank of pine forests with differently dated fires near the Karabash copper smelter

We tested the hypothesis that the number of seedlings from the soil seed bank (SSB) in forests polluted by heavy metals and disturbed by recent fires decreases. It was also assumed that the consequences of pollution and fires for the soil seed bank are additive. We estimated the number of seedlings from the SSB of pine forests located near the Karabash copper smelter (KCS) (contaminated by Cu, Zn, Pb, and Cd) and from uncontaminated forests of the Ilmen State Reserve (ISR). In both areas, samples of the forest litter and humus horizon were taken from forests recently exposed to ground fires and long-term unburned forests. Samples were exhibited from June to September, conducting seven rounds of counting seedlings. Small peculiarities of the emergence of seedlings on the samples of the forest litter and the humus horizon were established. However, the regularities of the reaction of SSB to pollution and fire disturbances did not depend on the soil horizon. The number of seedlings on substrates from contaminated forests was 5–8 times lower than the number of seedlings on substrates from background forests. A decrease in the number of seedlings on polluted substrates was accompanied by an increase in the share of dicots in the total number of seedlings. The relationship between the number of seedlings and the age of fires was not found. The additivity of the consequences of pollution and fires has also not been established. Of the two types of damage, pollution and fires, the pollution factor is of leading importance for SSBs. The results indicate a low recovery capacity of the herb-shrub layer of polluted forests.

Determination of Toxicity at Different Trophic Levels of Aqueous Film-Forming Foams (AFFF) Used in Fire Fighting.

Aqueous film-forming foams (AFFF), containing perfluorinated surfactants, can reach the environment. The objective of this study was to determine the ecotoxicity of AFFF, according to the type of fire to be fought (A1: 1.05g.L- 1, A2: 3.15g.L- 1 and A3: 6.30g.L- 1), to bioindicators of different trophic levels. For Artemia salina a toxic effect was observed at sample A1 (at concentrations of 100%), A2 (at concentrations above 25%) and A3 (at concentrations above 12.5%). For Lactuca sativa all samples affected the number of germinated seeds, speed and percentage of germination and root length. To the Eisenia fetida earthworm, samples A2 and A3 were considered toxic due to the percent avoidance being 70% and 100%, respectively. In Macaca mullata renal cell culture test, none of the samples were toxic by the MTT test. Therefore, it is necessary to develop methods for the safe use of AFFF by professionals.

Estimation and Prediction of Carbon Emission from Typical Coalfield Fire in Xinjiang, China: Based on Field Detection and Historical Data

ABSTRACT Coalfield fires release large amounts of greenhouse gases like CO2 and methane. Quick and effective carbon emission estimates are vital for assessing fire control and enhancing carbon reduction. In this work, field detection was applied to estimate the coal loss of typical coalfield fires in Xinjiang, and a simplified model was used to estimate the carbon emission based on coal loss. This method was verified by comparing with literature data. Using this model, the carbon emissions of Jiangjunmiao, Sigonghe, and Changcaodong coalfield fire zones were estimated to be 1,245,187.5 t, 293,730 t, and 511,122 t, respectively. Besides the field test data, the historical data from government was also collected, in order to calculate the increase rate of carbon emission. In Xinjiang, substantial progress has been made in coal fire management. Our estimation indicates that from 1958 to 2019, Xinjiang’s efforts to control coalfield fires resulted in a reduction of 8.93 Gt of carbon emissions, roughly sevenfold the total carbon emissions of China in 2023. From 2019 to 2023, the annual rates of change in carbon emissions for coal fire areas in Xinjiang that were under active control and those that were left unregulated were −4% and + 13.3%, respectively. In order to achieve the carbon reduction targets in the coalfield fire zone, the three surveyed Xinjiang coalfields need to achieve an annual reduction rate of 58%-73% to achieve the 2030 plan, 20%-29% to achieve the 2050 plan, and 15%-22% to achieve the 2060 plan.

Using computer vision to classify, locate and segment fire behavior in UAS-captured images

The widely adaptable capabilities of artificial intelligence, in particular deep learning and computer vision have led to significant research output regarding flame and smoke detection. The composition of flame and smoke, also described as fire behavior, can be considerably different depending on factors like weather, fuels, and the specific landscape fire is being observed on. The ability to detect definable classes of fire behavior using computer vision has not been explored and could be helpful given it often dictates how firefighters respond to fire situations. To test whether types of fire behavior could be reliably classified, we collected and labeled a unique unmanned aerial system (UAS) image dataset of fire behavior classifications to be trained and validated using You Only Look Once (YOLO) detection models. Our 960 labeled images were sourced from over 21 h of UAS video collected during prescribed fire operations covering a large region of Texas and Louisiana, United States. National Wildfire Coordinating Group (NWCG) fire behavior observations and descriptions served as a reference for determining fire behavior classes during labeling. YOLOv8 models were trained on NWCG Rank 1–3 fire behavior descriptions in grassland, shrubland, forested, and combined fire regimes within our study area. Models were first trained and validated on classifying isolated image objects of fire behavior, and then separately trained to locate and segment fire behavior classifications in UAS images. Models trained to classify isolated image objects of fire behavior consistently performed at a mAP of 0.808 or higher, with combined fire regimes producing the best results (mAP = 0.897). Most segmentation models performed relatively poorly, except for the forest regime model at a box (locate) and mask (segment) mAP of 0.59 and 0.611, respectively. Our results indicate that classifying fire behavior with computer vision is possible in different fire regimes and fuel models, whereas locating and segmenting fire behavior types around background information is relatively difficult. However, it may be a manageable task with enough data, and when models are developed for a specific fire regime. With an increasing number of destructive wildfires and new challenges confronting fire managers, identifying how new technologies can quickly assess wildfire situations can assist wildfire responder awareness. Our conclusion is that levels of abstraction deeper than just detection of smoke or flame are possible using computer vision and could make even more detailed aerial fire monitoring possible using a UAS.

Fire enhances changes in phosphorus (P) dynamics determining potential post-fire soil recovery in Mediterranean woodlands

Soil phosphorus (P), which is essential for ecosystem functioning, undergoes notable changes after fire. However, the extent to which fire characteristics affect P dynamics remains largely unknown. This study investigated the impact of type of fire (prescribed burning and natural wildfires) of different levels of severity on P dynamics in Mediterranean soils. Soil P concentrations in the organic layers were strongly affected by fire severity but not fire type. Low severity fire did not have any observable effect, while moderate fire increased soil P levels by 62% and high severity decreased soil P concentration by 19%. After one year, the soil P concentration remained unchanged in the low severity fires, while rather complex recovery was observed after moderate and high severity fires. In the mineral layers, P concentration was reduced (by 25%) immediately after the fires and maintained for one year (at 42%). 31P-NMR spectroscopy revealed almost complete post-fire mineralization of organic P forms (mono- and diesters), large increases in inorganic orthophosphate and a decrease in the organic:inorganic P ratio (Po:Pi). After one year, di-esters and orthophosphate recovered to pre-fire levels at all sites, except those where parent material composition (high pH and Fe concentration) had an enduring effect on orthophosphate retention, and thus, on the total soil P. We showed that fire severity and soil pH (and hence, soil mineralogy) played an essential role in soil P dynamics. These findings are important for reliable assessment of the effects of fire on soil P conservation and for improving the understanding the impact of prescribed burning.

A COMPREHENSIVE REVIEW ON VATAJA GRAHANI ROGA

Grahani (duodenum) is regarded as the seat of Agni (digestive fire) and is sustained by its strength. Any factor that disrupts the normal function of Jatharagni (a type of digestive fire) can lead to Grahaniroga (Diarrhoea/Dysentry). Grahaniroga is categorised into different types based on the involvement of Doshas. Among all the kinds of Grahaniroga, Vataja Grahani Roga is more common and can be correlated with Irritable Bowel Syndrome (IBS). The causes of Vataja Grahani are primarily factors that aggravate Vata dosha. These include Katu, Tikta, Kashaya, Rooksha and Sheeta. The consumption of factors that aggravate Vata dosha leads to vitiated Vata enveloping the digestive fire (Agni), resulting in Manda Agni, or weak digestive fire. This condition causes delayed and difficult digestion, leading to Shukta paka forming, where the food becomes acidic. In Charaka Samhita, the treatment for Vataja Grahani is explained in detail. These include Aam Pachana, Deepaniya Ghrita, Anuvasana Basti,Virechana and Niruha Basti.

Seaport infrastructure risk assessment for hazardous cargo operations using Bayesian networks

Seaport infrastructure requires considerable resources and time for a full recovery from accidents caused by hazardous cargo. Despite their severity, the risk to seaport infrastructure from hazardous cargo operations has been insufficiently explored. This study aims to fill that gap by examining the risks to seaport infrastructure from the complex effects of hazardous cargo operations. It draws on literature, incident reports, and expert consultations to identify comprehensive risk factors and their interconnections. The study employs expert judgments alongside logistic regression to develop Conditional Probability Tables (CPTs) and conducts a risk analysis using Bayesian networks (BN). Our findings indicate that, under typical operating conditions, fire and explosion, corrosion, and improper handling are the most significant contributors to seaport infrastructure risk with probabilities of 8.73 %, 5.88 %, and 5.61 % respectively. Inverse propagation indicates that the contribution of improper handling and corrosion is enhanced by 153 % and 96 % respectively towards the increased risk. A sensitivity analysis was carried out to pinpoint critical risk factors. Based on these insights, the study suggests practical measures like the use of tracking and monitoring systems along with third-party audits for effective handling, augmented and virtual reality for advanced training, and automation technology for reduced human roles to subside risks to seaport infrastructure and promote uninterrupted operations.

The dynamic evolution characteristics of PM2.5 concentrations and health risk assessment during typical forest fires in China

In the context of climate change, increasingly frequent wildfire events are exacerbating the air quality crisis in China and have become a significant source of atmospheric PM2.5. This study selected 12 major forest wildfire events in China from 2018 to 2023. Using atmospheric pollutant and component concentration data, as well as meteorological data, the study employed MK trend analysis, forward trajectory simulation, potential source contribution function (PSCF), and health risk indices to investigate the evolution patterns of PM2.5 concentrations before and after each wildfire event. The study explored the driving role of meteorological factors in this evolution process and quantitatively analyzed the spatial distribution characteristics of health risks in surrounding cities post-wildfire. The results indicated that: 1) PM2.5 levels changed significantly before and after each wildfire event, although the proportion of components remained relatively stable. 2) PM2.5 concentrations exhibited varying characteristics within different buffer zones of the wildfire areas. In the forest wildfire events in Foshan, Guangdong Province, and Jinzhong, Shanxi Province, the average PM2.5 concentrations within the 50 km buffer zones reached approximately 90 μg/m3, about 4–5 times the multi-year average for these areas. 3) Wildfire emissions were mainly influenced by meteorological and topographical factors. Wind field dependence diagrams showed that PM2.5 tended to accumulate in all wind directions, particularly at lower wind speeds of 0–5 m/s 4) Potential source analysis revealed that PM2.5 emissions from wildfires posed significant risks to surrounding areas. Multiple events had high-risk areas (WPSCF ≥0.8), and among the cities in these high-risk areas, the health risk value (ΔM) for Ya'an City reached an extremely high 85.1. This study provides a theoretical basis for policymakers to develop locally tailored wildfire management policies, ensuring the protection of the public's right to breathe clean air.

Size scale effect on mass burning flux and flame behavior of solid fuels

The study investigates the horizontal fuel size effect on free-burning fires for PMMA plates and wood cribs. The fuel size effect on mass burning flux and flame behavior is mainly discussed and compared with typical pool fires. For the PMMA plate and liquid pool, when the fuel size is small (< 10 cm), either the 3D sidewall burning of PMMA or the container wall heated by flame can promote the burning flux at the horizontal projection area. As the fuel size increases, these side wall burning or heating effects decrease, causing the drop in burning flux with fuel scale for both the PMMA plate and liquid pool. For small-scale wood cribs, fire cannot self-sustain due to the large airflow cooling. With the increase in wood crib size, the burning rate first remains constant and then gradually increases, driven by the enhanced internal radiation. As the fuel size increases above 20–30 cm, the flame radiation dominates the burning flux for all fuel types. Fire dynamics simulator (FDS) was adopted to simulate the horizontal size effect by setting a varied fire source (horizontal projection) area. First, the flame geometry and heat release rate (HRR) of simulations were validated against experimental results. Subsequently, the validated fire model generates cases covering a broad range of fire scales. Finally, a new correlation of flame height with the fire heat release rate and fuel size is proposed, and its prediction capability is validated in the numerical fire modeling. This study quantifies the size effect on the burning rate for common solid fuels and provides valuable information for the numerical modeling of multi-scale fires.

Impact of Jet Fires on Steel Structures: Application of Passive Fire Protection Materials

Jet fires are the second most common fire scenario after spill fires. This type of fire is characteristic of gas and gas–oil fires occurring on oil platforms and gas production and processing plants. The consequences of such fires are characterized by high material damage; this is associated with extensive networks of technological communications, since there is a high density of technological facilities and installations in the territory where these fires occur. At such facilities, there is a large number of steel structures, which under the action of high temperature quickly lose their strength and deform. To protect steel structures in the oil and gas industry, fire protection is used, which consists of different types: boards in the form of flat plates, plasters, and epoxy paints. This paper compares three types of fire protection materials for steel structures under jet fire: board fireproofing, plaster composition, and epoxy coating. When comparing the efficiency in jet fire, cement boards were found to be the best. However, despite the better fire protection efficiency, their low application is expected due to their massiveness and the high cost of such protection and the difficulty of installation. Nevertheless, the development of fire depends on the place of its origin, the size of the initial fire zone, and the stability and massiveness of the metal elements of the vessel structure or the structure of the boards on which the equipment can be placed. Therefore, it is necessary to take these factors into account when selecting fire protection and to apply it depending on the required fire resistance limits of structures, which should be determined depending on the fire development scenarios.

Landcover-categorized fires respond distinctly to precipitation anomalies in the South-Central United States

Satellite detection of active fires has contributed to advance our understanding of fire ecology, fire and climate dynamics, fire emissions, and how to better manage the use of fires as a tool. In this study, we use active fire data of 12 years (2012–2023) combined with landcover information in the South-Central United States to derive a monthly, open-access dataset of categorized fires. This is done by calculating a fire predominance index used to rank fire-prone landcovers, which are then grouped into four main landscapes: grassland, forest, wildland, and crop fires. County-level aggregated analyses reveal spatial distributions, climatologies, and peak fire months that are particular to each fire type. Using the Standardized Precipitation Index (SPI), it was found that during the climatological fire peak-month, the SPI and fires exhibit an inverse relationship in forests and crops, whereas grassland and wildland fires show less consistent inverse or even direct relationship with the SPI. This varied behavior is discussed in the context of landscapes’ responses to anomalies in precipitation and fire management practices, such as prescribed fires and crop residue burning. In a case study of Osage County (OK), we find that large wildfires, known to be closely related to climate anomalies, occur where forest fires are located in the county and absent in areas of grassland fires. Weaker grassland fire response to precipitation anomalies can be attributed to the use of prescribed burning, which is normally planned under environmental conditions that facilitate control and thus avoided during droughts. Crop fires, on the other hand, are set to efficiently burn residue and are practiced more intensely in drier years than in wetter years, explaining the consistently strong inverse correlation between fires and precipitation anomalies. In our increasingly volatile climate, understanding how fires, vegetation, and precipitation interact has become imperative to prevent hazardous fire conflagrations and to better manage ecosystems.

Wildfire combustion emission inventory in Southwest China (2001–2020) based on MODIS fire radiative energy data

Wildfires, a persistent environmental menace, are a significant source of harmful gases and particulate emissions. This study leverages the fire radiative power (FRP) method to delineate a comprehensive wildfire emission inventory for Southwest China from 2001 to 2020. Daily fire radiative power data derived from 1 km MODIS Thermal Anomalies/Fire products (MOD14/MYD14) were used to calculate the FRE and combusted biomass. Available emission factors were assigned to three biomass burn types: forest, grass, and shrub fires. Over the span of two decades, we have compiled data and estimated the annual emissions of carbon dioxide (CO2), carbon monoxide (CO), methane (CH4), sulfur dioxide (SO2), ammonia (NH3), nitrogen oxides (NOx), total particulate matter (TPM), black carbon (BC), organic carbon (OC), and non-methane volatile organic compounds (NMVOCs) to be 9809.13, 566.82, 25.79, 5.37, 12.25, 16.67, 133.53, 4.16, 41.81, and 97.23 Gg per year (Gg yr−1), respectively. In terms of fire type, forest fires accounted for the largest portion of total CO2 emissions (59.23%), with grass fires and shrub fires coming in second and third, accounting for 20.41% and 20.36%, respectively. Geographically, Yunnan Province were identified as the major contributor in Southwest China, accounting for 69.67% of the total emissions. Temporally, the maximum emission occurred in 2010 (24263.33 Gg), and the minimum emission occurred in 2017 (2917.66 Gg). And the emissions were mainly concentrated in February (23.33%), March (25.52%), and April (22.61%), which accounted for nearly three-fourths of the total emissions. The results of this study are much higher than those obtained by the burned area method, almost three times as high. In contrast, the results of this study are close to the fire emission data from the GFED4s and GFASv1.2 and QFEDv2.5r1 databases.

The effects of F-500 Encapsulator Agent on canine alerts and laboratory analysis using passive headspace concentration and gas chromatography-mass spectrometry

F-500 Encapsulator Agent (EA) is a fire suppression agent that is an alternative to traditional firefighting foams. It is marketed as having the capability to act on all four parts of the fire tetrahedron as well as being environmentally friendly and non-toxic. An internal survey of the use of F-500 EA by fire departments encountered by the Bureau of Alcohol, Tobacco, Firearms and Explosives (ATF) ignitable liquid detection canine (ILDC) handlers in 2022 showed that this product is not yet in widespread use across the country, but where it has been implemented, it is frequently utilized on a variety of types of fires. Additional agencies are researching the product to determine if it should be adopted. As this product appears to be growing in popularity, it is important to understand whether the use of the product would affect a canine’s ability to detect ignitable liquids or a forensic laboratory’s ability to identify the presence of an ignitable liquid. Burned wood and burned carpet, two commonly encountered substrates, were spiked with gasoline or a heavy petroleum distillate (HPD) and F-500 EA was applied. At various time intervals, ILDC teams surveyed the samples and laboratory analysis was conducted. Results showed that the presence of F-500 EA can negatively affect canine alerts and the laboratory’s ability to identify ignitable liquids.

Multicategory fire damage detection of post‐fire reinforced concrete structural components

AbstractThis paper introduces an enhanced you only look once (YOLO) v5s‐D network customized for detecting various categories of damage to post‐fire reinforced concrete (RC) components. These damage types encompass surface soot, cracks, concrete spalling, and rebar exposure. A dataset containing 1536 images depicting damaged RC components was compiled. By integrating ShuffleNet, adaptive attention mechanisms, and a feature enhancement module, the capability of the network for multi‐scale feature extraction in complex backgrounds was improved, alongside a reduction in model parameters. Consequently, YOLOv5s‐D achieved a detection accuracy of 93%, marking an 11% enhancement over the baseline YOLOv5s network. Comparison and ablation tests conducted on different modules, varying dataset sizes, against other state‐of‐the‐art networks, and on public datasets validate the resilience, superiority, and generalization capability of YOLOv5s‐D. Finally, an application leveraging YOLOv5s‐D was developed and integrated into a mobile device to facilitate real‐time detection of post‐fire damaged RC components. This application can integrate diverse fire scenarios and data types, expanding its scope in future. The proposed detection method compensates for the subjective limitations of manual inspections, providing a reference for damage assessment.

Centering Amah Mutsun voices in the analysis of a culturally important, fire-managed coastal grassland.

Indigenous communities throughout California, USA, are increasingly advocating for and practicing cultural fire stewardship, leading to a host of social, cultural, and ecological benefits. Simultaneously, state agencies are recognizing the importance of controlled burning and cultural fire as a means of reducing the risk of severe wildfire while benefiting fire-adapted ecosystems. However, much of the current research on the impacts of controlled burning ignores the cultural importance of these ecosystems, and risks further marginalizing Indigenous knowledge systems. Our work adds a critical Indigenous perspective to the study of controlled burning in California's unique coastal grasslands, one of the most biodiverse and endangered ecosystems in the country. In this study, we partnered with the Amah Mutsun Tribal Band to investigate how the abundance and occurrence of shrubs, cultural plants, and invasive plants differed among three adjacent coastal grasslands with varying fire histories. These three sites are emblematic of the state's diverging approaches to grassland management: fire suppression, fire suppression followed by wildfire, and an exceedingly rare example of a grassland that has been repeatedly burned approximately every 2 years for more than 30 years. We found that Danthonia californica was significantly more abundant on the burned sites, whereas all included shrub species (Baccharis pilularis, Frangula californica, and Rubus ursinus) were significantly more abundant on the site with no recorded fire, results that have important implications for future cultural revitalization efforts and the loss of coastal grasslands to shrub encroachment. In addition to conducting a culturally relevant vegetation survey, we used Sentinel-2 satellite imagery to compare the relative severities of the two most recent fire events within the study area. Critically, we used interviews with Amah Mutsun tribal members to contextualize the results of our vegetation survey and remote sensing analysis, and to investigate how cultural burning contrasts from typical Western fire management approaches in this region. Our study is a novel example of how interviews, field data, and satellite imagery can be combined to gain a deeper ecological and cultural understanding of fire in California's endangered coastal grasslands.

Investigation into the overcurrent failure and combustion characteristics of copper‐clad aluminum conductors

AbstractElectrical fires perennially rank first in fire occurrence types, with conductor overcurrent being one of the main inducements. This topic draws significant attention from scientific researchers and fire investigators. To understand the overcurrent fault and combustion characteristics of copper‐clad aluminum conductors, this paper examines 2.5 mm2 copper‐clad aluminum conductors that meet national standards, investigating morphological changes, temperature variations in the core and insulation layer, and flame propagation patterns under overcurrent conditions. Experiments using an electrical fault simulation device were conducted to study overcurrent failures of copper‐clad aluminum conductors under 52.5–105 A conditions. The results indicate that when the current exceeds 67.5 A, the conductor undergoes a series of changes during energization, including smoking, expanding, carbonizing, burning, and breaking; at 52.5 A, the insulation layer reaches thermal equilibrium at 150 s without combustion; for currents between 60–67.5 A, wire core temperature variations can be divided into three stages; at 75 A, the insulation layer reaches thermal equilibrium 10s before breaking; currents above 82.5 A see a sharp increase in temperature in both the core and insulation layer before the conductor breaks; above 97.5 A, the conductor first breaks and then burns. The research results have significant theoretical value in improving the scientific rigor of fire accident investigations and forensic evidence examinations.

FireSonic: Design and Implementation of an Ultrasound Sensing-Based Fire Type Identification System.

Accurate and prompt determination of fire types is essential for effective firefighting and reducing damage. However, traditional methods such as smoke detection, visual analysis, and wireless signals are not able to identify fire types. This paper introduces FireSonic, an acoustic sensing system that leverages commercial speakers and microphones to actively probe the fire using acoustic signals, effectively identifying fire types. By incorporating beamforming technology, FireSonic first enhances signal clarity and reliability, thus mitigating signal attenuation and distortion. To establish a reliable correlation between fire type and sound propagation, FireSonic quantifies the heat release rate (HRR) of flames by analyzing the relationship between fire-heated areas and sound wave propagation delays. Furthermore, the system extracts spatiotemporal features related to fire from channel measurements. The experimental results demonstrate that FireSonic attains an average fire type classification accuracy of 95.5% and a detection latency of less than 400 ms, satisfying the requirements for real-time monitoring. This system significantly enhances the formulation of targeted firefighting strategies, boosting fire response effectiveness and public safety.

Experimental study on fire extinguishing performance of typical large space fires on ships

ABSTRACT A reliable fire extinguishing system is an effective measure to reduce the risk of ship fire. Based on a typical large space cabin platform, the experiments on the fire extinguishing performance of different fire extinguishing systems (high-expansion foam, aqueous film-forming foam and water spray) against oil pool fire (6 MW) and wood stack fire (0.3 MW) were carried out. The results show that for oil pool fire, the fire extinguishing performance of aqueous film-forming foam system is higher than that of high-expansion foam system. The fire extinguishing performance of high-expansion foam system is significantly affected by the relative location of high-expansion foam generator, fire source and obstacle. For wood stack fire, the fire extinguishing performance of water spray system is the best, and the fire extinguishing time is only 25 s, followed by the aqueous film-forming foam system (54 s) and the high expansion foam system (66 s).

PELATIHAN ALAT PEMADAM API RINGAN DAN KARUNG GONI SEBAGAI MEDIA PEMADAMAN KEBAKARAN KEPADA MAHASISWA POLIBATAM, SISWA DAN GURU SMK DI BATAM

Fire disaster is one of the many disasters that occur in the wider community both in the office and residential environment. This fire disaster generally occurs due to human factors such as: using electrical loads that exceed the power capacity and placing flammable items near the source of fire. This fire hazard will be easier to overcome if people know how to put out fires properly and know how to use extinguishers such as APAR (Light Fire Extinguisher) and the use of gunny sacks. APAR is generally categorized into 3 types, namely: Dry Chemical Extinguisher, Carbon Dioxide (CO2) Extinguisher, and Foam. Extinguishers containing dry chemical powder are very commonly used because they are able to extinguish almost all types of fires. The use of APAR is most likely to be used because of its portable nature, easy maintenance, and easy to use. In the community service that has been carried out at Batam State Polytechnic, a demonstration on how to extinguish fire with fire extinguisher and the use of gunny sacks was also carried out. Participants of this community service program are students, vocational school students and vocational school teachers.

Using AutoML and generative AI to predict the type of wildfire propagation in Canadian conifer forests

Accurate prediction of wildfire behaviour is critical for safe and effective fire management and suppression. This study focused on developing and evaluating machine learning (ML) models based on a dataset collected of outdoor experimental fires in Canadian conifer forests. Binary classification models (surface fire vs. crown fire) and multi-class fire type models (surface, passive crown, active crown) were created using ensemble tree methods (Random Forest, XGBoost) and automated ML (AutoGluon, TabPFN). Generative adversarial networks (GAN) were used to generate synthetic data to overcome imbalances in the type of fire distribution. The results show automated ML methods applied to the binary problem to perform best of all tested methods, with an overall accuracy of 91%. TabPFN had the highest accuracy for the multi-class problem, with the use of GAN improving model fit. Results show overfitting issues with some of the ML models, highlighting the need of independent evaluation when ML models are developed. The TabPFN models have potential for application in supporting fire management, namely in fuel management and identifying situations with high fire spread and intensity potential that can impact firefighter safety.