基于APRIORI算法的林火发生与气象关系的分析

传统的气象林火火险预测方法只适应于省级以上的大地域林火发生风险的宏观预测,不能用于林场一级的小地域的林火发生预测。林场一级的单位缺乏精确的林火发生数据和实用有效的林火监测手段,记录数据一般较粗放,难以用精确的方法进行预测。本文利用关联算法Apriori,分析了北京市房山区林火发生的可能性及发生强度与气象因子间的关系。研究结果表明,Apriori算法可以有效地利用粗放的林火数据集进行林火预测,为基层林场预测林火发生提供了方法。     

基于3S技术的森林防火指挥系统的设计

在吉林省永吉县林火扑救与森林防火指挥中,以35技术为基础建立森林防火指挥系统,对永吉县森林火灾进行准确预测预报以及扑救,对空间数据和非空间数据进行管理,并且建立工程技术档案库。在林火扑救和林火指挥调度中进行合理的决策,全面发挥永吉县森林防火指挥中心的作用,不断完善和修正监测和指挥中的各项技术指标,使这一指挥系统长期进入良性循环状态。     

大兴安岭雷击火发生条件分析

根据2007—2009年大兴安岭林区闪电和林火监测结果进行分析,研究火灾发生时的火险状况和雷击火灾案例,提高对这一区域雷击火的认识。根据研究区内11个气象站定时观测数据,采用加拿大林火天气指数系统计算各站点每日火险指数,分析研究时段内火灾发生与火险和闪电分布的关系。结果表明:2007—2009年共发生野火195起,其中林火148起,主要发生在4,5和8月份。雷击天气主要出现在5—9月份,其中6,7和8月份闪电最多。闪电分布密度较高的区域主要在研究区东北部,大部分闪电活动伴随着降水,但在比较干旱的年份,容易出现干雷暴天气,易引发雷击火。根据林火及火灾发生前24h的闪电分布分析,雷击火占总火灾的5.1%,闪电活动不是影响林火发生的主要原因。雷击火主要发生在火险比较高、闪电活动频繁且无有效降雨的区域。     

林火发生预报模型研究进展

森林火灾直接影响森林生态环境质量,严重威胁人类生命财产安全,还会造成病虫害频发、群落退化等次生灾害。由于综合考虑了各类影响林火发生的因子,林火发生预报模型是目前预报结果最为准确的林火预报预测方法。文中从林火驱动因子、林火发生预报模型构建、模型检验方法等3个方面综述国内外林火发生预报模型的发展现状和研究成果,讨论各类林火发生预报模型的优缺点,梳理目前研究中存在的问题,对其研究前景进行展望,并结合我国实际情况提出开展更大空间尺度林火预报的研究建议,以期为相关研究和林火管理工作提供参考。     

多源遥感影像在森林火灾监测中的应用

随着森林火灾造成的危害越来越大,防控的科学性和有效性已引起世界各国的关注,遥感技术在监测和预警方面的突破已成为林火防控的发展方向。针对当前林火监测的遥感影像众多、火点识别方法多样等问题,文中分析和总结了各种遥感数据的优势与不足,以及监测和预警技术的发展趋势,特别是对多源信息融合及人工智能的自动化火灾监测预警进行了展望,以期对遥感林火监测理论研究、应用研发和生产实践应用提供参考。     

基于Hadoop和Spark的森林火灾混合大数据分析系统研究

针对当前森林火灾动态监测与预警中海量、异构、多源、动态的数据在存储、计算、管理方面所面临的挑战,以及国内外在森林火灾动态监测与预警上的研究往往只考虑单一领域或技术的问题,结合新兴的大数据分析与处理技术,融合林火动态监测与预警不同技术领域的研究成果,对林火多源异构数据采用混合处理方法,基于Hadoop和Spark大数据集成平台构建了一个森林火灾混合大数据分析系统。并设计一个林火火点检测实验,通过实验验证了该系统的可行性和有效性,可为后续研究和建立森林火灾动态监测与预警可视化大数据平台提供参考。     

黑龙江省1980—2005年森林火灾时空特征

森林火灾是林火失去人为控制,在森林内自然蔓延和扩展,对生态系统和人类带来一定危害和损失的森林起火。森林火灾属世界性、跨国性的重大自然灾害,进入20世纪80—90年代以来,全球气候变暖导致森林火灾有上升的趋势,虽然各国的森林防火费用不断增加,但森林火灾发生的面积并未相     

谷歌地球（Google Earth）在森林火灾扑救应急指挥中的应用

谷歌地球（Google Earth）是美国谷歌公司推出的免费全球地理信息系统服务软件,其以卫星照片和航空照片为底图,结合DTM数字模型,通过网络提供全球的遥感图像。以谷歌地球提供的共享空间数据和森林火灾预防、监测、扑救等数据为基础,可以对谷歌地球进行二次开发。通过森林防火的空间数据与属性数据相结合可以实现森林火场定位、火场信息查询、GPS辅助决策指挥、火灾损失评估、火灾数据统计分析等功能;能够在短时间内实现森林火灾的准确定位并提供森林火灾发生地和火场周围的地理信息,以便快速准确地引导扑火队员到达火场进行火灾扑救。     

基于遥感技术的宜良县云南松蓄积量反演

以云南省宜良森林二类调查数据为样本,基于Google Earth Engine云平台Landsat 8 OLI影像,结合植被因子、纹理特征以及K-T变化为自变量,构建了多元线性回归和随机森林的建模方法,建立了森林蓄积量反演模型.以宜良县云南松为研究对象,运用Landsat8 OLI遥感影像数据结合地面角规控制样地调查数...     

Operational flexibility in forest fire prevention and suppression: a spatially explicit intra-annual optimization analysis,considering prevention, (pre)suppression,and escape costs

Increasing wildfire threats and costs escalate the complexity of forest fire management challenges, which is grounded in complex interactions between ecological, social, economic, and policy factors. It is immersed in this difficult context that decision-makers must settle on an investment mix within a portfolio of available options, subject to limited funds and under great uncertainty. We model intra-annual fire management as a problem of multistage capacity investment in a portfolio of management resources, enabling fuel treatments and fire preparedness. We consider wildfires as the demand, with uncertainty in the severity of the fire season and in the occurrence, time, place, and severity of specific fires. We focus our analysis on the influence of changes in the volatility of wildfires and in the costs of escaped wildfires, on the postponement of capacity investment along the year, on the optimal budget, and on the investment mix. Using a hypothetical test landscape, we verify that the value of postponement increases significantly for scenarios of increased uncertainty (higher volatility) and higher escape costs, as also does the optimal budget (although not proportionally to the changes in the escape costs). Additionally, the suppression/prevention budget ratio is highly sensitive to changes in escape costs, while it remains mostly insensitive to changes in volatility. Furthermore, we show the policy implications of these findings at operational (e.g., spatial solutions) and strategic levels (e.g., climate change). Exploring the impact of increasing escape costs in the optimal investment mix, we identified in our instances four qualitative system stages, which can be related to specific socioecological contexts and used as the basis for policy (re)design. In addition to questioning some popular myths, our results highlight the value of fuel treatments and the contextual nature of the optimal portfolio mix.     

Fuel types and crown fire potential in <Emphasis Type="Italic">Pinus halepensis</Emphasis> forests

There is a lack of knowledge to identify and classify forest structures according to the risk of crown fires, especially in Mediterranean regions. In this study, for the first time, we use real information, obtained after a wildfire that burnt under extreme meteorological conditions, to classify forest structures of Pinus halepensis into fuel types as a function of crown fire potential. We identified fourteen forest structures which characterize many forest types in Western Mediterranean areas depending on canopy closure, number of tree layers, percent of each tree layer and overall tree density. By using the pattern of fire types that burnt the most numerous forest structures, we have identified four fire hazard groups of forest structures which are considered different fuel types. The first two had the lowest risk of active crown fires and they differed in the proportion of surface fires and passive crown fires. The third fuel type was the threshold between structures with low and high extreme fire behavior; while the fourth had a high risk of active crown fires. Firefighters and forest managers who are demanding this kind of schema, will test and upgrade this classification of fuel types in function of crown fire potential during future wildfires.     

红外热成像仪林火识别性能测评技术研究

红外热成像仪在森林火灾远程视频监测中应用广泛,但每种红外热成像仪性能各异,需要对 其林火识别性能进行测评,以便为红外热成像仪的选型提供依据。文章提出了一种基于红外裸数据的红 外热成像仪测评方法。该方法从火点的辨识度和理论可识别距离两方面对不同的红外热成像仪进行性能 测评和实验测试,可客观地评价红外热成像仪对林火的识别能力。     

天水市近30年林地动态变化遥感监测研究

[目的]以甘肃省天水市为例,基于遥感影像变化监测技术,探讨黄土高原丘陵沟壑与小陇山-西秦岭山地交接过渡区域近30年来森林(林地)资源空间分布规律、时间变化趋势及变化影响因素。[方法]以1988—2015年5期夏季Landsat TM/OLI遥感影像为主要数据源,结合辅助数据和外业实地样本点,以光谱特征和指数特征为特征变量,分别利用随机森林(RF)和参数优化支持向量机(POSVM)分类器对土地覆盖类型进行分类,然后基于分类后比较法进行森林资源动态变化监测。[结果]分类结果表明,两种分类器的分类效果均较好,且随机森林分类器在分类精度、效率和稳定性方面明显优于参数优化支持向量机分类器。变化监测结果表明,近30年来森林资源总体变化趋势为林地面积先减少后增加。1990—1996年,林地面积减少0.74%;1996—2002年,林地面积减少2.74%;2002—2008年,林地面积增加1.06%;2008—2015年,林地面积增加8.89%。[结论]本研究采用的基于非参数分类器分类后比较法的变化监测技术是复杂地形地貌过渡区森林资源动态变化监测的一种有效途径,在分类结果分析统计的基础上,得出研究区森林资源变化的总体趋势:以2002年(2002年影像)为界,林地总体趋势为先减少后增加,2002年后林地面积增加显著。     

Forest fuel mapping and evaluation of LANDFIRE fuel maps in Boulder County,Colorado, USA

A key challenge in modern wildfire mitigation and forest management is accurate mapping of forest fuels in order to determine spatial fire hazard, plan mitigation efforts, and manage active fires. This study quantified forest fuels of the montane zone of Boulder County, CO, USA in an effort to aid wildfire mitigation planning and provide a metric by which LANDFIRE national fuel maps may be compared. Using data from 196 randomly stratified field plots, pre-existing vegetation maps, and derived variables, predictive classification and regression tree models were created for four fuel parameters necessary for spatial fire simulation with FARSITE (surface fuel model, canopy bulk density, canopy base height, and stand height). These predictive models accounted for 56–62% of the variability in forest fuels and produced fuel maps that predicted 91.4% and 88.2% of the burned area of two historic fires simulated in the FARSITE model. Simulations of areas burned based on LANDFIRE national fuel maps were less accurate, burning 77.7% and 40.3% of the historic fire areas. Our results indicate that fuel mapping efforts that utilize local area information and biotic as well as abiotic predictors will more accurately simulate fire spread rates and reflect the inherent variability of forested environments than do current LANDFIRE data products.     

基于距离相关系数和KNN回归模型的森林蓄积量估测研究

【目的】探究Landsat8 OLI数据和KNN算法在森林蓄积量估测中的潜力。【方法】以湖南省湘潭县为研究区,采用Landsat8 OLI数据和同时期的二类调查数据,通过距离相关系数筛选特征,分别采用线性回归模型(MLR)、K-近邻模型(KNN)、距离加权KNN模型(DW-KNN)和优化欧式KNN模型(FW-KNN)对森林蓄积量进行估测。使用十折交叉方法进行精度检验,对检验结果进行对比分析。【结果】3种KNN模型的估测结果均高于传统的线性模型,并且在3种KNN模型中,FW-KNN算法效果最好,决定系数达到0.69,为3种模型中最高;3种KNN模型中,本研究优化欧氏距离KNN模型的估测精度最高,其均方根误差为30.3%,相比于传统KNN模型的均方根误差降低了5.1%,相比于DW-KNN模型降低了3.3%。【结论】采用DW-KNN蓄积量估测结果明显优于其他两种模型,说明通过特征与蓄积量的相关性优化样本间的距离是一种可行的KNN优化方法。     

Long-term decrease of organic and inorganic nitrogen concentrations due to pine forest wildfire

? Growing concerns about fires and the increase of fire frequency and severity due to climate change have stimulated a large number of scientific papers about fire ecology. Most researchers have focused on the short-term effects of fire, and the knowledge about the long-term consequences of fires on ecosystem nutrient dynamics is still scarce.

? Our aim was to improve the existing knowledge about the long-term effects of wildfires on forestlabile N concentrations. We hypothesized that fires may cause an initial decline in organic and inorganic N availability, and in the amount of microbial biomass-N; this should be followed by the recovery of pre-fire N concentrations on a long-term basis. We selected a fire chronosequence in Pinus canariensis forests on La Palma Island (Canary Islands, Spain). These forests are under low anthropogenic atmospheric deposition, and forest management is completely lacking; wildfires are therefore the only significant disturbance. Soil samples were collected during the winter and spring at 22 burned and unburned plots.

? Fire produced a significant decrease in microbial biomass N, mineral N and dissolved organic N. Almost 20 y after fire, pre-fire levels of N concentrations had not recovered.

? These results demonstrate that P. canariensis forest soils have a lower resilience against fire than expected. The magnitude of these observed changes suggests that pine forest wildfires may induce long-term (2 decades) changes in soil and in plant primary production.

     

Spatio-temporal perspectives of forest fires regimes in a maturing Mediterranean mixed pine landscape

It has been suggested that during the past several decades, the frequency and the intensity of wildfires have markedly increased in the Mediterranean basin. We came to assess this postulation in the forested region of Mount Carmel, Israel. This region is characterized by Quercus spp. and Pistacia spp. maquis and has been intensely afforested with Pinus spp. stands since the 1920s. We compiled a GIS-based database of the fires recorded in the region since 1983, in addition to archiving data beginning from the 1940s. The data were collected from land stewardship agencies’ archives, fire departments and aerial photographs. Prior to the early 1980s, no systematic documentation of the fires was available, rather just sporadic qualitative documentation of the large forest fires that occurred. Between 1944 and 1982, only 6 large fires were documented, while after that 11 large fires occurred. Analysis indicated that the spatial distribution of the fires does not occur at random, and their locations are significantly closer to roadsides compared to an expected random distribution. The annual number of fires and the areas burned during the last two decades were not correlated with annual precipitation in any manner. Accordingly, we suggest that the increased number of large forest fires during the last decades is associated with the maturation and senescence of the planted forest coupled with increased human activities.     

2003—2018年中国森林火灾时空分布格局研究

基于2003—2018年的中国森林火灾统计数据,全面分析了森林火灾发生的时空分布格局,定量分析了其统计学规律,旨在为森林火灾预测、管理和风险决策提供基础支撑.分析结果表明,森林火灾的发生具有极强的随机性和离散性,通过森林火灾总次数、火场面积和受害森林面积的平均数来反映森林火灾发生风险将会导致评估结果偏高.森林火灾发生次...     

基于气象因子深度学习的森林火灾预测方法

森林火灾一旦发生将对生态系统造成严重的破坏,间接导致气候的变化和极端天气频发。对森林火灾的发生进行准确预测可提前采取有效的防控措施,具有重要意义。传统林火预测模型多为数学方法和浅层神经网络,当数据量增大时易出现建模困难以及预测精度降低等问题。深度学习模型在处理大量非线性数据上具有一定的优势,其模型具有多层网络结构,通过训练大量数据可提取出具有代表性的特征值,发现数据间的隐含关系,达到准确分类预测的目的。因此,本研究提出一种基于深度学习的林火预测方法,将深度信念网络(deep belief network,DBN)作为预测模型,气象因子作为输入数据,以解决传统林火预测模型在面对大量数据时预测效果不佳的问题;同时结合过采样SMOTE(synthetic minority oversampling technique)算法,平衡林火数据集和增加训练数据量,提升了森林火灾的预测准确度。结果表明,在面对更大的数据量时,该模型预测精度明显优于其他传统林火预测模型,证明了将深度学习应用在林火预测的优越性。该研究可为深度学习在林业领域的应用提供参考。