A geographical similarity-based sampling method of non-fire point data for spatial prediction of forest fires

Understanding the mechanisms and risks of forest fires by building a spatial prediction model is an important means of controlling forest fires.Non-fire point data are important training data for constructing a model,and their quality significantly impacts the prediction performance of the model.However,non-fire point data obtained using existing sampling methods generally suffer from low representativeness.Therefore,this study proposes a non-fire point data sampling method based on geographical similarity to improve the quality of non-fire point samples.The method is based on the idea that the less similar the geographical environment between a sample point and an already occurred fire point,the greater the confidence in being a non-fire point sample.Yunnan Province,China,with a high frequency of forest fires,was used as the study area.We compared the prediction performance of traditional sampling methods and the proposed method using three commonly used forest fire risk prediction models:logistic regression(LR),support vector machine(SVM),and random forest(RF).The results show that the modeling and prediction accuracies of the forest fire prediction models established based on the proposed sampling method are significantly improved compared with those of the traditional sampling method.Specifically,in 2010,the modeling and prediction accuracies improved by 19.1%and 32.8%,respectively,and in 2020,they improved by 13.1%and 24.3%,respectively.Therefore,we believe that collecting non-fire point samples based on the principle of geographical similarity is an effective way to improve the quality of forest fire samples,and thus enhance the prediction of forest fire risk.

Trends in Global and Mexico Research in Wildfires: A Bibliometric Perspective

In the last two decades, unprecedented changes have taken place in the frequency and severity of wildfires;in different regions of the world, some fires were even classified as megafires. Although there are studies about the diverse effects of fire, which have made significant theoretical contributions, a comprehensive review of the changes in fire research is required to understand worldwide patterns, particularly in those countries where fire activity is on the rise, such is the case of Mexico. The objective of this study was to analyze the trends in the research on wildfires published in Mexico and worldwide over a 40-year timescale. For this purpose, the Web of Science database, bibliometric tools, and the keywords TI = Forest fire* OR TI = Wildfire* were used to extract as many articles as possible related to fires from 1980 to 2020, without being restricted to those studies whose title included any of the variants of the keywords. There were 8458 publications about fires in the vegetation cover, with a notable increase in the frequency of studies in the previous decade;52% of the studies were concentrated in five countries and 20% of the articles focused on the study of different aspects of the soil. Mexico ranks thirteenth in volume of scientific production and studies in the country have focused mainly on the description of the quantitative relationship between the size of the affected area and the number of occurrences in the landscape, meanwhile, studies on fires and the consequences on the biotic interactions have been little explored.

基于BIMFire-YOLO的消防监控图像识别方法

在传统条件下,通常存在着火灾现场情况多变,建筑物内构造复杂等问题,使得消防监控系统难以通过现有方法精准检测识别火灾第一现场和所处室内环境。为了优化检测算法在复杂场景下的应用效果,文中提出BIMFire-YOLO检测方法,在以往YOLOv3主干网络中增加了新的卷积方式,在扩大了卷积感受野范围的同时,也保证了输出特征的不变性,对小火焰和烟雾等目标的检测能力有所提升。通过引入新的损失函数,降低了火灾发生的目标漏检率,融合BIM技术不仅提升了定位精度也实现了自动识别视频和图像中失火的场景。该算法不仅提高了检测效率,也实现了火灾的信息共享与管理的统一,在实际医院场景下的综合识别精度达到了45.6%,检测速度和精度均优于其他同类方法。

基于FireNet的古建筑火灾检测方法研究及改进

针对古建筑火灾检测需要快速、准确及实时的需求,建立了一个专门用于古建筑火灾检测的数据集,用于古建筑火灾检测的深度学习研究。利用CBAM注意力机制模块,结合多尺度特征融合,对FireNet网络进行改进,提出适用于古建筑火灾检测的轻量级FireNet-AMF网络,在FireNet数据集和本文构建的古建筑火灾检测数据集上验证了FireNet-AMF网络的火灾检测能力。与改进前的网络相比,FireNet-AMF网络在FireNet数据集上对火灾识别的准确率达到了95.08%,与原网络相比提高了1.17%,在本文构建的古建筑火灾检测数据集上的准确率达到了95.62%,比原网络提高了1.62%。该网络在保证轻量级的同时也保证了在古建筑火灾检测中较高的检测精度。

Performance Analysis of Support Vector Machine (SVM) on Challenging Datasets for Forest Fire Detection

This article delves into the analysis of performance and utilization of Support Vector Machines (SVMs) for the critical task of forest fire detection using image datasets. With the increasing threat of forest fires to ecosystems and human settlements, the need for rapid and accurate detection systems is of utmost importance. SVMs, renowned for their strong classification capabilities, exhibit proficiency in recognizing patterns associated with fire within images. By training on labeled data, SVMs acquire the ability to identify distinctive attributes associated with fire, such as flames, smoke, or alterations in the visual characteristics of the forest area. The document thoroughly examines the use of SVMs, covering crucial elements like data preprocessing, feature extraction, and model training. It rigorously evaluates parameters such as accuracy, efficiency, and practical applicability. The knowledge gained from this study aids in the development of efficient forest fire detection systems, enabling prompt responses and improving disaster management. Moreover, the correlation between SVM accuracy and the difficulties presented by high-dimensional datasets is carefully investigated, demonstrated through a revealing case study. The relationship between accuracy scores and the different resolutions used for resizing the training datasets has also been discussed in this article. These comprehensive studies result in a definitive overview of the difficulties faced and the potential sectors requiring further improvement and focus.

Lightning in a Forest (Wild) Fire: Mechanism at the Molecular Level

The mechanism of lightning that ignites a forest fire and the lightning that occurs above a forest fire are explained at the molecular level. It is based on two phenomena, namely, internal charge separation inside the atmospheric cloud particles and the existence of a layer of positively charged hydrogen atoms sticking out of the surface of the liquid layer of water on the surface of rimers. Strong turbulence-driven collisions of the ice particles and water droplets with the rimers give rise to breakups of the ice particles and water droplets into positively and negatively charged fragments leading to charge separation. Hot weather in a forest contributes to the updraft of hot and humid air, which follows the same physical/chemical processes of normal lightning proposed and explained recently[1]. Lightning would have a high probability of lighting up and burning the dry biological materials in the ground of the forest, leading to a forest (wild) fire. The burning of trees and other plants would release a lot of heat and moisture together with a lot of smoke particles (aerosols) becoming a strong updraft. The condition for creating lightning is again satisfied which would result in further lightning high above the forest wild fire.

EXPERIMENT OF SMOKE-PREVENTING AIR CURTAINS IN HIGH-RISE BUILDING FIRES

In high-rise building fires, the most immediate threat to passenger life and safety evacuation is the smoke inhalation. Some traditional models for smoke prevention and exhaust are analyzed and compared with the smoke-preventing air curtain. The rationality and the feasibility of the air curtain are theoretically expounded. The air volume, tuyere width and jet velocity in the air curtain experiment are designed according to the theoreti- cal calculation model. Experimental results indicate that the effect of air curtain to prevent smoke diffusion is re- markable as the volume ratio of air-smoke is about 0. 6, the jet angle is between 25^o and 35^o, and the jet thickness is between 25 mm and 45 mm. The efficiency of air curtain can reach 98% on the entraining effect. Meanwhile, experiments verify the theorectical calculation.

基于改进FireNet的轻型火灾实时检测方法

针对火灾检测精确不高,时间长等问题。设计了基于改进FireNet的轻型火灾实时检测方法,通过获取视频图像数据,网络模型进行火灾分析和识别;首先,在FireNet特征提取阶段使用多尺度卷积网络并引入通道注意力机制,以提高回归精度。其次,对全连接层的神经元个数进行压缩优化,减少计算耗时。实验表明,改进的FireNet算法模型检测精度达到96.43%,模型存储空间0.96MB,检测帧率37。相比标准算法精度提高2.5%,存储空间压缩85%,检测帧率提升35%。

Experimental Studies of Interactions Between Backfires and Coming Surface Fires\+*

In order to study the convection limits of surface fires and interactions between backfires and main fires,several experiments are conducted in a large space indoor laboratory: in which the effects of ambient wind speeds and changing temperatures can be avoided.The research shows that:(1) there is a convection field in front of coming fires in which the wind speed direction is toward the fire.In the convection area,the lower part has higher wind speed and when the height is taller than a certain value the convection wind speed is not significant;(2) the backfire and the main fire interact with each other even though they are far apart.When they come near each other to a certain distance,they begin to draw each other.This increases their rates of spread toward each other significantly.For surface fires with a fire line intensity of 160?kW\5m -1 ,their rate of spread increases by 27%.

Impacts of the Kuwait Oil Fires on the Mount Qomolangma Region

Mt. Qomolangma (also known as Mt. Everest), the world's highest mountain, is situated over the world＇s highest plateau, the Tibetan Plateau. Because of its height and because of its distance from industrialized areas, the environmental state of the Mt. Qonlolangma region can normally be considered 'undisturbed'. It is interesting to investigate how this “undisturbed” state has been changing with time and whether it has been influenced by large environmentally disruptive events such as the Kuwait oil fires of 1990 and 1991 (Small, 1991). In order to do this, river water samples were collected from the Rongpu River at Rongpu Temple Station in the summers of 1992 and 1993,as was done in 1975, and aerosol samples were collected in the summer of 1992 at the same station as was done in 1980. River water samples were analyzed using atomic absorption spectroscopy (AAS) at the Chinese Academy of Sciences. Aerosol samples were analyzed using proton-induced x-ray emission (PIXE) at the University of Fudan in Shanghai. The results show that the concentrations of chemical species in the river water at Rongpu Temple Station were much higher in the summer of 1992 than they were in 1975 and 1993, and the concentrations of atmospheric chemical species were much higher in 1992 than they were in 1980. The environment of the north slope of Mt.Qomolangma was therefore heavily polluted before and / or during the summer of 1992, possibly due to the Kuwait oil fires in 1990 and 1991.

Fire behaviour of multiple fires in a mine drift with longitudinal ventilation

The fire behaviour involving multiple fires in a mine drift with longitudinal ventilation was analysed. The conditions and fire phenomena occurring were described. The analysis was based upon experimental data from model-scale fire experiments. A fire involving several fuel items may lead to flames tilted horizontally and filling up the entire cross section, leading to earlier ignition, higher fire growth rates, higher fire spread rate and severe fire behaviour. Longer flame lengths will also result due to decreased air entrainment. A correlation for the continuous flame length was proposed. The results of the analysis will help identifying and preventing potentially dangerous fire situations with several large combustible items distributed along a mine drift.

Review of state-of-the-art decision support systems (DSSs) for prevention and suppression of forest fires

Forest ecosystems are our priceless natural resource and are a key component of the global carbon budget. Forest fires can be a hazard to the viability and sustainable management of forests with consequences for natural and cultural environments, economies, and the life quality of local and regional populations. Thus, the selection of strategies to manage forest fires, while considering both functional and economic efficiency, is of primary importance. The use of decision support systems(DSSs) by managers of forest fires has rapidly increased. This has strengthened capacity to prevent and suppress forest fires while protecting human lives and property. DSSs are a tool that can benefit incident management and decision making and policy, especially for emergencies such as natural disasters. In this study we reviewed state-of-the-art DSSs that use: database management systems and mathematical/economic algorithms for spatial optimization of firefighting forces; forest fire simulators and satellite technology for immediate detection and prediction of evolution of forest fires; GIS platforms that incorporate several tools to manipulate, process and analyze geographic data and develop strategic and operational plans.

Spatio-temporal changes of underground coal fires during 2008-2016 in Khanh Hoa coal field(North-east of Viet Nam) using Landsat time-series data

Underground coal fires are one of the most common and serious geohazards in most coal producing countries in the world. Monitoring their spatio-temporal changes plays an important role in controlling and preventing the effects of coal fires, and their environmental impact. In this study, the spatio-temporal changes of underground coal fires in Khanh Hoa coal field(North-East of Viet Nam) were analyzed using Landsat time-series data during the 2008-2016 period. Based on land surface temperatures retrieved from Landsat thermal data, underground coal fires related to thermal anomalies were identified using the MEDIAN+1.5×IQR(IQR: Interquartile range) threshold technique. The locations of underground coal fires were validated using a coal fire map produced by the field survey data and cross-validated using the daytime ASTER thermal infrared imagery. Based on the fires extracted from seven Landsat thermal imageries, the spatiotemporal changes of underground coal fire areas were analyzed. The results showed that the thermalanomalous zones have been correlated with known coal fires. Cross-validation of coal fires using ASTER TIR data showed a high consistency of 79.3%. The largest coal fire area of 184.6 hectares was detected in 2010, followed by 2014(181.1 hectares) and 2016(178.5 hectares). The smaller coal fire areas were extracted with areas of 133.6 and 152.5 hectares in 2011 and 2009 respectively. Underground coal fires were mainly detected in the northern and southern part, and tend to spread to north-west of the coal field.

Analysis of underground fires in Polish hard coal mines

In the period of the first twenty years after World War II the number of fires in Polish hard coal mines reached annually the value of several thousands of cases. About 80% of fires constituted spontaneous fires. Investigations into the development of new methods of fire hazard prediction and implementation of new methods and means of fire prevention as well as the introduction of prohibition concerning the use of products manufactured of combustible organic materials in underground mine workings re-duced considerably the hazard of underground fire rise. The worked out at the Central Mining Institute (GIG) new method of un-derground fire prediction allows the correct selection of fire prevention means. The introduction into common use of fire-resistant conveyor belts, the main factor giving rise to spontaneous fires, and methods of assessment of their fire resistance eliminated prac-tically the fire hazard. These activities contributed in an efficient way to the reduction of the number of underground fires to a sat-isfactory level.

Drought and Spatiotemporal Variability of Forest Fires Across Mexico

Understanding the spatiotemporal links between drought and forest fire occurrence is crucial for improving decision-making in fire management under current and future climatic conditions. We quantified forest fire activity in Mexico using georeferenced fire records for the period of 2005–2015 and examined its spatial and temporal relationships with a multiscalar drought index, the Standardized Precipitation-Evapotranspiration Index(SPEI). A total of 47975 fire counts were recorded in the 11-year long study period, with the peak in fire frequency occurring in 2011. We identified four fire clusters, i.e., regions where there is a high density of fire records in Mexico using the Getis-Ord G spatial statistic. Then, we examined fire frequency data in the clustered regions and assessed how fire activity related to the SPEI for the entire study period and also for the year 2011. Associations between the SPEI and fire frequency varied across Mexico and fire-SPEI relationships also varied across the months of major fire occurrence and related SPEI temporal scales. In particular, in the two fire clusters located in northern Mexico(Chihuahua, northern Baja California), drier conditions over the previous 5 months triggered fire occurrence. In contrast, we did not observe a significant relationship between drought severity and fire frequency in the central Mexico cluster, which exhibited the highest fire frequency. We also found moderate fire-drought associations in the cluster situated in the tropical southern Chiapas where agriculture activities are the main causes of forest fire occurrence. These results are useful for improving our understanding of the spatiotemporal patterns of fire occurrence as related to drought severity in megadiverse countries hosting many forest types as Mexico.

Human evacuation affected by smoke movement in mine fires

The objective of this work is to investigate the influence of smoke movement during mine fires on miner evacuation behaviors. A three-dimensional computational fluid dynamics method was conducted to reconstruct the lane- way conveyor belt fire scenes under two ventilating conditions. The parameters, including temperature-time histories, soot density, carbon monoxide and heat release rate, were simulated to characterize the mine fires at various ventilating speeds. A miner evacuation model affected by fire smoke movement was advanced to describe the miner evacuation behaviors, which can be divided into three stages. Based on the evacuation model coupled with the mine fire smoke movement, the available safety evacuation time for miners involved in coal mine fire located in different sites was estimated. Two evacuation patterns were advanced according to the ventilating speeds combined with the model of miner evacuation behaviors. The results show that the miners located between the inlet-air end and the air door in lane 1 should be evacuated to the inlet-air end and other miners involved in coal mine fire could choose the air door as the escaping destination, when the ventilation speed is greater than 3 m/s. Accordingly, the research can be used as references for the mine safety administration authorities to design the safety evacuation.

Coal fires in China

Coal fires have a very long history in China; the oldest coal fires have being burning for many million years. Up to now more than 56 coal fires spots were distin-guished. They mainly locate in West-North of China, North of China and East-North of China. About millions of tons of coal have been burned in fires every year. Xinjiang Autonomy is the most serious region in coal fires as it has 38 coal fires spots and about 6.85 million tons of coal was burned every year. Coal fires in China ignited by wildfires, spontaneous combustion and human being during mining activities. These fires have re-leased about 0.9 million tons of gasses (including CO, CO2, SO2, NO2 CH4, CO2, H2S etc.) into the atmosphere every year, most of which are brought to the east by wind and result-ing more heavier air pollution in northern China.

Estimation and Spatio-temporal Patterns of Carbon Emissions from Grassland Fires in Inner Mongolia,China

Grassland fires results in carbon emissions,which directly affects the carbon cycle of ecosystems and the carbon balance.The grassland area of Inner Mongolia accounts for 22%of the total grassland area in China,and many fires occur in the area every year.However,there are few models for estimation of carbon emissions from grassland fires.Accurate estimation of direct carbon emissions from grassland fires is critical to quantifying the contribution of grassland fires to the regional balance of atmospheric carbon.In this study,the regression equations for aboveground biomass(AGB)of grassland in growing season and MODIS NDVI(Normalized Difference Vegetation Index)were established through field experiments,then AGB during Nov.–Apr.were retrieved based on that in Oct.and decline rate,finally surface fuel load was obtained for whole year.Based on controlled combustion experiments of different grassland types in Inner Mongolia,the carbon emission rate of grassland fires for each grassland type were determined,then carbon emission was estimated using proposed method and carbon emission rate.Results revealed that annual average surface fuel load of grasslands in Inner Mongolia during 2000–2016 was approximately 1.1978×1012 kg.The total area of grassland which was burned in the Inner Mongolia region over the 17-year period was 5298.75 km2,with the annual average area of 311.69 km2.The spatial distribution of grassland surface fuel loads is characterized by decreasing from northeast to southwest in Inner Mongolia.The total carbon emissions from grassland fires amounted to 2.24×107 kg with an annual average of 1.32×106 for the study area.The areas with most carbon emissions were mainly concentrated in Old Barag Banner and New Barag Right Banner and on the right side of the Oroqin Autonomous Banner.The spatial characteristics of carbon emission depend on the location of grassland fire,mainly in the northeast of Inner Mongolia include Hulunbuir City,Hinggan League,Xilin Gol League and Ulanqab City.The area and spatial location of grassland fires can directly affect the total amount and spatial distribution of carbon emissions.This study provides a reference for estimating carbon emissions from steppe fires.The model and framework for estimation of carbon emissions from grassland fires established can provide a reference value for estimation of carbon emissions from grassland fires in other regions.

Determination of fire-access zones along road networks in firesensitive forests

Wild forest fires are one of the greatest environmental disasters affecting forest resources. Along the coastal zone of the Mediterranean region in Turkey, forested areas are classified as first-degree, fire-sensitive areas. Every year, thousands of hectares of forests have been destroyed in Turkey. In this study, fire-access zones were determined in the Mediterranean forests of Turkey, by utilizing geographic information systems （GIS） technology. The effective reach distance of fire hoses from both sides of roads was considered in order to delineate fireaccess zones. The effective reach distance can vary based on the technical capabilities and hydraulic capacity of fire trucks （minimum and maximum pressures on water pump）; terrain structures （uphill, downhill and flat）; and ground slope. These factors and their influences were studied in fire sensitive forest areas located in the eastern Mediterranean city of Kahramanmaras in Turkey. First, terrain structures on both sides of the road network and groundslope classes were determined based on GIS data layers. Then, fire access zones were delineated according to water pressure data, terrain structures, and ground-slope classes. The results indicated that 69.30 % of the forested areas were within the fire-access zones, while the rest of the forest was out of reach the fire hoses. The accessible areas were also calculated for forested areas with different fire- sensitivity degrees. The accessible areas were 69.59, 69.96, and 67.16 % for the forested areas that are sensitive to fires at the first, second, and third degrees, respectively. This finding has implications for the monitoring and management of fire threats in areas outside of the reach distance. The outside areas should receive extra attention and monitoring during the fire season so that fires are detected ahead of time and management has sufficient time to react. Besides, new roads should be considered for these areas in order to access more lands in a shorter amount of time.

Environmental and Economic Impact of Forest Fires in Puerto Rico 2013-2014

This study presents an analysis of the impact of forest fires in Puerto Rico for the period from 2013-2014. The climatological factors analyzed included precipitation, temperature, relative humidity, and wind. Several factors have combined to the increase of these forest fires, among others, a decrease in precipitation during this period, as well as an increase in the human involvement in these fires from approximately 40% occurs in the night period (5:00 pm to 8:00 am), where the weather conditions do not favor the appearance of these phenomena. An increase in fires of 44% occurred in 2013 compared to 2014, causing an economic loss of $13.8 million. Fire also adversely affected the flora and fauna of the island, but this was not evaluated in this paper.