Fire Characteristics Research Articles

An Experimental Study of Pool Fire Characteristics under the Effects of Cross Winds and Baffles

The pool fires that occur behind obstructions in a ventilated environment are very different from other wind-blown pool fires. The pool fire formed by fuel leakage in an engine nacelle is a typical example of a pool fire influenced by cross winds and baffles. Mastering the combustion characteristics of this type of fire is of great significance for fire prevention and control. In this study, the burning rate, flame length, and flame tilt angle of heptane pool fires behind a baffle under different cross wind velocities (ranging from 0 to 5 m/s) were experimentally investigated. Square pool fires with dimension of 8 cm and 12 cm with baffle height from 4 to 12 cm and different distances between fire and baffle (0, 20, 30 cm) were tested in a wind tunnel. The experimental results show that the burning rate increases with the increase in cross wind velocity for each baffle height. As wind velocity exceeds 2 m/s, the burning rate first decreases and then increases with the increase in baffle height. The flame length initially increases and then decreases with increasing wind velocity. The upper flame tilt angle is mainly affected by the cross wind, while the bottom flame tilt angle is influenced by the combined effects of cross wind velocity, baffle height, and distance between baffle and flame. The empirical correlations under different distances between baffle and flame, with wind velocity and baffle height accounted for, are then proposed for the dimensionless heat release rate and the flame length of heptane pool fires.

The Use of Arak Bali as a Fuel Influence on Fire Characteristics of Combustion

Analyze the characteristics of gas fuel from arak Bali, like shape and flame speed. Test characteristics such as methanol and ethanol content material gas from arak Bali, after it tested the gas fuel combustion characteristics of arak Bali such as the shape and speed of flame. Testing characteristics such as the content of methane and ethanol gas from arak Bali performed in the forensic laboratory while testing the ignition characteristics of the shape and speed of fuel from evaporating arak Bali done using a helle-shaw cell combustion chamber model. Air mixture ratio variations with gas fuel from arak Bali is 24/1, 25/1, 26/1, 27/1, 28/1, 29/1, 30/1 and 31/1. The observed effect is the shape and speed of the premixed flame propagation in the helle-shaw cell combustion chamber model. The results of the study, the moisture content of the basic ingredients of gas fuel arak Bali consisting of 40% methanol and 60% ethanol. Gas fuel from arak Bali has a stoichiometry air-fuel ratio of 30/1. Getting closer to the stoichiometry air-fuel ratio, flame color changes from reddish color faded to red, reddish blue, blue and bright blue last. The maximum speed of propagation of fire occurring in stoichiometry air-fuel ratio is 328.33 cm/sec.

An Efficient Forest Fire Detection Algorithm Using Improved YOLOv5

Forest fires result in severe disaster, causing significant ecological damage and substantial economic losses. Flames and smoke represent the predominant characteristics of forest fires. However, these flames and smoke often exhibit irregular shapes, rendering them susceptible to erroneous positive or negative identifications, consequently compromising the overall performance of detection systems. To enhance the average precision and recall rates of detection, this paper introduces an enhanced iteration of the You Only Look Once version 5 (YOLOv5) algorithm. This advanced algorithm aims to achieve more effective fire detection. First, we use Switchable Atrous Convolution (SAC) in the backbone network of the traditional YOLOv5 to enhance the capture of a larger receptive field. Then, we introduce Polarized Self-Attention (PSA) to improve the modeling of long-range dependencies. Finally, we incorporate Soft Non-Maximum Suppression (Soft-NMS) to address issues related to missed detections and repeated detections of flames and smoke by the algorithm. Among the plethora of models explored, our proposed algorithm achieves a 2.0% improvement in mean Average Precision@0.5 (mAP50) and a 3.1% enhancement in Recall when compared with the YOLOv5 algorithm. The integration of SAC, PSA, and Soft-NMS significantly enhances the precision and efficiency of the detection algorithm. Moreover, the comprehensive algorithm proposed here can identify and detect key changes in various monitoring scenarios.

Quantifying fire-specific smoke exposure and health impacts.

Rapidly changing wildfire regimes across the Western United States have driven more frequent and severe wildfires, resulting in wide-ranging societal threats from wildfires and wildfire-generated smoke. However, common measures of fire severity focus on what is burned, disregarding the societal impacts of smoke generated from each fire. We combine satellite-derived fire scars, air parcel trajectories from individual fires, and predicted smoke PM2.5 to link source fires to resulting smoke PM2.5 and health impacts experienced by populations in the contiguous United States from April 2006 to 2020. We quantify fire-specific accumulated smoke exposure based on the cumulative population exposed to smoke PM2.5 over the duration of a fire and estimate excess asthma-related emergency department (ED) visits as a result of this exposure. We find that excess asthma visits attributable to each fire are only moderately correlated with common measures of wildfire severity, including burned area, structures destroyed, and suppression cost. Additionally, while recent California fires contributed nearly half of the country's smoke-related excess asthma ED visits during our study period, the most severe individual fire was the 2007 Bugaboo fire in the Southeast. We estimate that a majority of smoke PM2.5 comes from sources outside the local jurisdictions where the smoke is experienced, with 87% coming from fires in other counties and 60% from fires in other states. Our approach could enable broad-scale assessment of whether specific fire characteristics affect smoke toxicity or impact, inform cost-effectiveness assessments for allocation of suppression resources, and help clarify the growing transboundary nature of local air quality.

Numerical analysis of liquid sodium spreading on sloped floor surface under pool fire scenario in SFR systems

The accidental leaks of coolant from the heat transport circuit of Sodium-cooled Fast Reactor (SFR) can create fire events due to the reactivity of sodium with atmospheric oxygen, which can pose threat to safe operation of the reactor. The leaked sodium eventually reaches the cell floor, spreads gradually, and forms a burning pool. The thermal consequences of pool fire depend on its surface area, which is determined by the spreading process of sodium on the floor surface. In this context, numerical investigation has been carried out on the spreading behavior of burning sodium pool on the plane/sloped cell floor by developing a 3-D numerical model based on the viscous-gravity current equation of the shallow layer model. The governing equations of the model have been solved numerically by implementing the Finite Volume Method. The model developed has been validated using the experimental results published on liquid pool spreading under burning and non-burning conditions on plane and sloped floors for different leak rates. Using this model, numerical simulations have been carried out on sodium pool spreading under various leak scenarios envisaged in SFR cells based on the specific burning characteristics of sodium pool fire. The time-varying pool size and shape, pool height profile, and maximum pool area have been estimated for a wide range of sodium leak rates and typical floor slopes of interest to nuclear power plants. These predictions contribute towards the numerical evaluation of sodium pool fire scenarios pertaining to the safety of SFR.

Characteristics of fires in coal mine roadways and comparative analysis of control effectiveness between longitudinal ventilation and cross-section sealing

Enhancing ventilation velocity and constructing sealing walls are prevalent strategies aimed at managing fires in coal mine roadways. To assess the efficacy of these control tactics, this study investigates the fire characteristics with varying heat release rates (HRR) using a 1:10 experiment and numerical simulations. Results reveal that an increase in the HRR corresponds to a decrease in ceiling temperature, alongside an increase in both smoke back-layering length and critical velocity. Longitudinal ventilation proves effective in lowering ceiling temperature and inhibiting upstream smoke propagation from fire source, but it does not extinguish the fire, instead reducing downstream visibility and escalating risk downstream of fire. When the actual velocity exceeds 3.1 m/s, it effectively prevents smoke backflow in a fire of 10 MW. Cross-section sealing works by reducing oxygen levels within roadway to suffocate the fire. As the sealing ratio increases, flame inclination angle and burning time decline, whereas ceiling temperature rises. When it exceeds 75%, CO concentration sharply rises and fire enters the extinguishment phase, if ratio is 100%, fire with higher HRR are extinguished more quickly. This study provides valuable insights into roadway fire control: longitudinal ventilation aids personnel evacuation, while cross-sectional sealing effectively extinguishes fires in unpopulated spaces.

Mini but Mighty: Oscillations in diffusion flames at sub-atmospheric conditions

The oscillatory behaviour of buoyant diffusion flames plays a vital role in determining how flames evolve. Although previous studies have established an inverse square root relationship between oscillatory frequency and pool diameter, f ∼ D-1/2, few have explored the synergistic effect of diameter and reduced pressure on the pulsation phenomenon. This study mainly investigates the characteristics of convection-controlled pool fires (D < 20 cm) at varying sub-atmospheric pressures, with a particular focus on the influence of eddy effects. Four burner sizes (7 cm, 10 cm, 13 cm, and 16 cm) are selected, and pressure levels are set at 95 kPa, 80 kPa, 60 kPa, and 40 kPa, respectively. A pressure chamber, maintaining a nearly constant pressure during combustion, is employed. The morphology of diffusion flames is recorded and subsequently analysed at different pressures. The study finds that flame shapes change from turbulent to laminar as pressure decreases, which is attributed to the smaller vortex size and corresponds to the varicose and sinuous models. Flame height and oscillatory frequency show a slight increase with decreasing pressure. A new correlation based on the dimensionless Richardson number and Strouhal number is proposed to correlate the oscillation and diameter at different pressures, St=0.58(1/Ri)0.54. This study provides interesting insights into the behaviour of buoyant diffusion flames under sub-atmospheric conditions, highlighting the transition from turbulent to laminar flame shapes, changes in flame height, and pulsation frequency trends. This research could potentially contribute to the comprehension of buoyant diffusion flames at sub-atmospheric conditions in future.

Modelling study of the spread of liquid fuel spill fires using shallow water equations

In oil spill–fire accidents, the spread of burning fuel from petroleum product containers may increase accident losses and trigger further accidents. Studying the spreading process of spill fires is important to prevent accidents and mitigate losses. Herein, a spill-fire spread model was proposed to predict the spread rate and time varying burning area of liquid fuel spill fires. The model was developed using one-dimensional nonlinear shallow water equations. Fuel consumption was used as the source term in the equations. To ensure numerical stability and accuracy, the third-order TVD Runge–Kutta method and the second-order MUSCL scheme were used for time advancement and numerical space reconstruction, respectively. Numerical flux was calculated by using the HLL approximate Riemann solver. The algorithm of the shallow water equations was modified in accordance with the spread characteristics of spill fires. Using the developed spread model, the dynamic burning area and dynamic fuel thickness of a spill fire were calculated. The simulation results were verified using the experimental results on continuously released n-heptane spill fires, and the two results were in good agreement.

Analysis of methods for assimilating fire perimeters into a coupled fire-atmosphere model

Correctly initializing the fire within coupled fire-atmosphere models is critical for producing accurate forecasts of meteorology near the fire, as well as the fire growth, and plume evolution. Improperly initializing the fire in a coupled fire-atmosphere model can introduce forecast errors that can impact wind circulations surrounding the fire and updrafts along the fire front. A well-constructed fire initialization process must be integrated within coupled fire-atmosphere models to ensure that the atmospheric component of the model does not become numerically unstable due to excessive heat fluxes released during the ignition, and that realistic fire-induced atmospheric circulations are established at the model initialization time. The primary objective of this study is to establish an effective fire initialization method in a coupled fire-atmosphere model, based on the analysis of the impact of the initialization procedure on the model’s ability to resolve fire-atmosphere circulations and fire growth. Here, we test three different fire initialization approaches leveraging the FireFlux II experimental fire, which provides a comprehensive suite of observations of the pyroconvective column, local micrometeorology, and fire characteristics. The two most effective fire initialization methods identified using the FireFlux II case study are then tested on the 380,000-acre Creek Fire, which burned across the central Sierra Nevada mountains during the 2020 Western U.S. wildfire season. For this case study, simulated pyroconvection and fire progression are evaluated using plume top height observations from MISR and airborne fire perimeter data, to assess the effectiveness of different initialization methods in the context of establishing pyroconvection and resolving the fire growth. The analyses of both the experimental fire simulation and the wildfire simulation indicate that the spin-up initialization method based on historical fire progression that masks out inactive fire regions provides the best results in terms of resolving the fire-induced vertical circulation and fire progression.

Radiative flamelet/progress variable modelling of the UMD turbulent line fires under varying oxygen concentrations

Advanced combustion models for fire simulations remain challenging due to the complex interaction of turbulence, combustion and radiation. Among these models, the flamelet-based model is a promising candidate to incorporate detailed chemistry at low computational cost. To this end, flamelet large-eddy simulations (LES) are performed to investigate extinction characteristics of a turbulent line fire, which is a target case in the Measurement and Computation of Fire Phenomena (MaCFP) workshop and has been experimentally studied at the University of Maryland. Two radiative flamelet formulations are investigated: (a) the radiative laminar flamelet model (RLFM-u) and (b) the radiative flamelet/progress variable (RFPV-u) model. In the normal air case where XO2 = 21%, RLFM-u and RFPV-u perform similarly, both yield reasonable agreement with experimentally measured temperature. However, in the under-ventilated case (XO2 = 13%), RFPV-u outperforms RLFM-u as it manages to capture the local flame extinction. Two dimensionless indices are introduced to quantify the role of radiation heat loss and local strain in flame weakening. It is revealed that radiative heat loss dominates the flame weakening in the normal air case while strain-induced local extinction contributes significantly to flame weakening in under-ventilated conditions, which is only captured by RFPV-u, highlighting its advantages in predicting fires with strong extinction.

After the ‘Black Summer’ fires: Faunal responses to megafire depend on fire severity, proportional area burnt and vegetation type

Abstract Climate change and human activities have disrupted historical fire regimes, leading to complex and far‐reaching impacts on global ecosystems. Despite extensive research in fire ecology, studies exploring vertebrate responses to megafires, and to nuanced fire characteristics, remain limited. We collected camera trap data 3–27 months following Australia's 2019–20 ‘Black Summer’ megafires from 30 burnt sites and 10 unburnt sites. Our data included 14 animal species/groups, encompassing mammalian predators, small and medium‐sized mammals, large herbivores, and birds. We used generalised additive mixed models to assess the influence of time‐since‐the‐fires, burn status, fire severity, proportional area burnt, and vegetation type on species' activity. Models that included fire variables were well‐supported for all species. The proportional cover of low‐moderate or high‐extreme severity fire had substantial support for five species, particularly herbivores, which generally showed a preference for burnt sites but at differing fire severities. The proportional area burnt, disregarding severity, was well supported for four species. At highly burned sites fox activity peaked shortly after the fires while small to medium‐sized mammal activity increased more gradually. Vegetation type strongly influenced the response of four species to fire; in particular, wet forest birds preferred unburnt areas. Policy implications. We document variable short‐ to medium‐term responses of a range of species to fire which could help guide management interventions. We demonstrate that animal species' responses to fire are diverse and better captured using broader landscape scale fire variables. We found that species were strongly influenced by proportional area burnt, fire severity and vegetation type. Introduced foxes were attracted to recently burnt areas, so timely predator control may benefit vulnerable prey species. Wet forest species were sensitive to fires and could benefit from preservation and restoration of these habitats. Some species exploited low‐moderate severity burnt areas, while others preferred high‐severity burns. This suggests that species will face diverse challenges and opportunities in future extreme fire events. We emphasise the importance of using multi‐faceted approaches to account for the complex responses of co‐occurring species to fire events.

FuF-Det: An Early Forest Fire Detection Method under Fog

In recent years, frequent forest fires have seriously threatened the earth’s ecosystem and people’s lives and safety. With the development of machine vision and unmanned aerial vehicle (UAVs) technology, UAV monitoring combined with machine vision has become an important development trend in forest fire monitoring. In the early stages, fire shows the characteristics of a small fire target and obvious smoke. However, the presence of fog interference in the forest will reduce the accuracy of fire point location and smoke identification. Therefore, an anchor-free target detection algorithm called FuF-Det based on an encoder–decoder structure is proposed to accurately detect early fire points obscured by fog. The residual efficient channel attention block (RECAB) is designed as a decoder unit to improve the problem of the loss of fire point characteristics under fog caused by upsampling. Moreover, the attention-based adaptive fusion residual module (AAFRM) is used to self-enhance the encoder features, so that the features retain more fire point location information. Finally, coordinate attention (CA) is introduced to the detection head to make the image features correspond to the position information, and improve the accuracy of the algorithm to locate the fire point. The experimental results show that compared with eight mainstream target detection algorithms, FuF-Det has higher average precision and recall as an early forest fire detection method in fog and provides a new solution for the application of machine vision to early forest fire detection.

RAGN-L: A stacked ensemble learning technique for classification of Fire-Resistant columns

One of the main challenges in using reinforced concrete materials in structures is to comprehend their fire resistance. The assessment of fire resistance can be performed in a laboratory environment using fire. However, such tests are time-consuming and expensive, and they may not provide a complete assessment of all relevant properties of a particular tested specimen. To that end, the implementation of machine learning (ML) in the investigation of fire-resistant structural performance would be beneficial, as it would also contribute to the reduction of time and cost problems related to traditional techniques. Here, this research proposes a novel ensemble ML approach to classify columns according to their fire resistance characteristics, supporting the application of ML techniques by fire engineers and scientists. The proposed model, named RAGN-L, combines Random Forest, Adaptive Boosting, and Gradient Naive Bayes, and is stacked using the Logistic Regression approach. RAGN-L is evaluated on real-world databases of reinforced concrete columns and concrete-filled steel tube columns, as well as a synthetic database generated by the TVAE deep learning model. The performance of the proposed solution is compared with ten different ML classifiers based on common statistical metrics, accuracy, precision, recall, and f1-score, and validated using the k-fold cross-validation approach. The developed algorithm outperforms ten different classifiers in all databases, with classification accuracies of 86.6%, and 99.6% for the real-world and synthetic databases of reinforced concrete columns, respectively, and 88.1% for the real-world database of concrete-filled steel tube columns.

The Destructive Sir Ivan Fire in New South Wales, Australia; Simulations Using a Coupled Fire—Atmosphere Model

The destructive Sir Ivan Dougherty fire burned 55,000 hectares around 250 km northwest of Sydney in New South Wales on 12 February 2017. Record hot temperatures were recorded in the area during the lead-in days and the fire conditions at the time were described as the ‘worst ever seen in NSW’. The observed weather conditions were hot, dry and very windy ahead of a synoptic frontal wind change during the afternoon. ‘Extreme’ to ‘catastrophic’ fire weather was predicted, and the potential for extreme fire behaviour was identified several days in advance. The Australian coupled fire–atmosphere model ACCESS-Fire has been run to explore the characteristics of the Sir Ivan fire. Several features resulting from fire–atmosphere interaction are produced in the simulations. Simulated heat flux along the fire perimeter shows increased intensity on the northern fire flank in response to gradual backing winds ahead of the main frontal wind change. Temporal and spatial variability in fire activity, seen as pulses in fire intensity and fireline wind speed, develop in response to boundary layer rolls in the wind fields. Deep moist convection consistent with the observed pyrocumulonimbus (pyroCb) cloud is simulated over the fire at around the time of the frontal wind change, and matches guidance from the ‘PyroCb Firepower Threshold’ tool, which showed transient favourable conditions. After the wind change, short-lived near-surface and elevated vortices suggest organised rotating features on the northern flank of the fire. The coupled model captures processes that cannot be produced in uncoupled fire predictions and that are not captured in current operational meteorological forecast products provided to Australian fire agencies. This paper links the features from coupled simulations to available observations and suggests pathways to embed the learnings in operational practice.

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&lt;sup&gt;2&lt;/sup&gt; in total floor area and no more than 10 stories (less than 33 m in height). In addition, in &amp; 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.

Fire Characteristics of Lithium-ion Battery According to the State of Charge in an Accelerating Rate Calorimeter

Recently, the interest in ecofriendly energy as an alternative to fossil fuels, which cause climate change and sea level rise, has increased. To achieve the efficient utilization of ecofriendly energy, such as a renewable energy, considerable effort has been made to use energy storage systems (ESSs) and smart grid systems. However, many safety problems, such as battery fires caused by the increase in the use of secondary batteries, significantly limit their application scope. In this study, to investigate the fire characteristics of lithium ion batteries (LIBs), the characteristics of the spontaneous exothermic reaction and thermal runaway phenomenon that occur at each temperature of an LIB battery were investigated using an accelerating rate calorimeter. The batteries used in the experiments were standard 18650 cylindrical batteries with a capacity of 2600 mAh, and they were tested at three different state-of-charge (SOC) levels: 0%, 50%, and 100%. The type of heat generated by each experimental condition was classified into four stages, and the existence and temperature rise characteristics of each stage were investigated according to the SOC. Although thermal runaway occurred at both 50% and 100% SOC, the reaction at 50% SOC did not escalate into violent explosions like the reaction observed at 100% charging. Furthermore, the activation energies for the thermal runaway observed in the experiments conducted at 50% and 100% SOC are presented.

Spatio-Temporal Characteristics of Ice–Snow Freezing and Its Impact on Subtropical Forest Fires in China

Ice–snow freezing may disrupt the growth condition and structure of forest vegetation, increasing combustible loads and thus triggering forest fires. China’s subtropical regions are rich in forest resources, but are often disturbed by ice–snow freezing, especially due to climate change. Clarifying the responsive areas and times of forest fires to ice-snow freezing in this region is of vital importance for local forest fire management. In this study, meteorological data from 2001 to 2019 were used to extract the precipitation and its duration during the freezing period in order to analyze the freezing condition of forest vegetation in subtropical China. To improve the accuracy of identifying forest fires, we extracted forest fire information year-by-year and month-by-month based on the moderate resolution imaging spectroradiometer (MODIS) active fire data (MOD14A2) using the enhanced vegetation index (EVI), and analyzed the forest fire clustering characteristics in the region using the Moran’s Index. Then, correlation analysis between forest fires and freezing precipitation was utilized to explore the responsive areas and periods of forest fires caused by ice–snow freezing. Our analysis shows the following: (1) during the period of 2001–2019, the ice–snow freezing of forest vegetation was more serious in Hunan, Jiangxi, Hubei, and Anhui provinces; (2) forest fires in subtropical China have shown a significant downward trend since 2008 and their degree of clustering has been reduced from 0.44 to 0.29; (3) forest fires in Hunan, Jiangxi, and Fujian provinces are greatly affected by ice–snow freezing, and their correlation coefficients are as high as 0.25, 0.25, and 0.32, respectively; and (4) heavy ice–snow freezing can increase forest combustibles and affect forest fire behavior in February and March. This research is valuable for forest fire management in subtropical China and could also provide a reference for other regions.

Study into the Fire and Explosion Characteristics of Polymer Powders Used in Engineering Production Technologies

Polymers and their processing by engineering production technologies (injection, molding or additive manufacturing) are increasingly being used. Polymers used in engineering production technologies are constantly being developed and their properties are being improved. Granulometry, X-ray, FTIR and TGA were used to characterize polymer samples. Determination of the fire parameters of powder samples of polyamide (PA) 12, polypropylene, and ultra-high molecular weight (UHMW) polyethylene is the subject of the current article. An explosive atmosphere can be created by the powder form of these polymer materials, and introduction of preventive safeguards to ensure safety is required for their use. Although the fire parameters of these basic types of polymers are available in databases (e.g., GESTIS-DustEx), our results showed that one of the samples used (polypropylene) was not flammable and thus is safe for use in terms of explosiveness. Two samples were flammable and explosive. The lower explosive limit was 30 g·m−3 (PA12) and 60 g·m−3 (UHMW polyethylene). The maximum explosion pressure of the samples was 6.47 (UHMW polyethylene) and 6.76 bar (PA12). The explosion constant, Kst, of the samples was 116.6 bar·m·s−1 (PA12) and 97.1 bar·m·s−1 (UHMW polyethylene). Therefore, when using polymers in production technologies, it is necessary to know their fire parameters, and to design effective explosion prevention (e.g., ventilation, explosive-proof material, etc.) measures for flammable and explosive polymers.

Forecasting wildfire hazard across northwestern south America

Fire hazard is often mapped as a static conditional probability of fire characteristics’ occurrence. We developed a dynamic product for operational risk management to forecast the probability of occurrence of fire radiative power in the locally possible near-maximum fire intensity range. We applied standard machine learning techniques to remotely sensed data. We used a block maxima approach to sample the most extreme fire radiative power (FRP) MODIS retrievals in free-burning fuels for each fire season between 2001 and 2020 and associated weather, fuel, and topography features in northwestern south America. We used the random forest algorithm for both classification and regression, implementing the backward stepwise repression procedure. We solved the classification problem predicting the probability of occurrence of near-maximum wildfire intensity with 75% recall out-of-sample in ten annual test sets running time series cross validation, and 77% recall and 85% ROC-AUC out-of-sample in a twenty-fold cross-validation to gauge a realistic expectation of model performance in production. We solved the regression problem predicting FRP with 86% r2 in-sample, but out-of-sample performance was unsatisfactory. Our model predicts well fatal and near-fatal incidents reported in Peru and Colombia out-of-sample in mountainous areas and unimodal fire regimes, the signal decays in bimodal fire regimes.

Transportation of wind-smoke flow in full-scale laneway fire experiments

The mechanism of fire smoke movement and its effects on ventilation systems in coal laneways have attracted considerable interest because underground laneway fires threaten safe production. In this study, we investigated the fire characteristics of an intake laneway in a U-shaped working face by conducting a full-scale laneway fire experiment at Kailuan. Results indicated that the two groups of fire combustion states chosen for this study are fuel-controlled, and the amount of CO produced by combustion is significantly influenced by the ventilation conditions. The fire in the laneway has a significant throttling effect on the air intake laneway and return air laneway, which further affects the ventilation system. The smoke temperature decay along the ceiling is not continuous. The temperature drops quickly after the smoke touches the turning wall, and the smoke temperature decay coefficient k is corrected. Besides, the critical velocity and smoke backlayering length equations developed by other researchers are validated. Finally, the smoke thickness and uniform mixing distance are determined.