基于静止气象卫星时空变化的山火监测算法及验证  

Algorithm and validation of spatiotemporal variation-based wildfire monitoring using geostationary meteorological satellites

作　　者：周恺 张睿哲 叶宽 冯涛 Zhou Kai;Zhang Ruizhe;Ye Kuan;Feng Tao(State Grid Beijing Electric Power Research Institute,Beijing 100075,China;State Grid Hunan Electric Power Company Disaster Prevention and Mitigation Center,Changsha Hunan 410129,China)

机构地区：[1]国网北京市电力公司电力科学研究院,北京100075 [2]国网湖南省电力公司防灾减灾中心,湖南长沙410129

出　　处：《消防科学与技术》2025年第3期423-428,共6页Fire Science and Technology

基　　金：国网北京市电力公司科技项目(520223200068)。

摘　　要：山火对于输电线路的安全运行具有极大的威胁,尤其是小规模的山火,一旦发生,就可能导致输电线路跳闸,影响电力的正常供应。为了有效监测并应对这一隐患,本文基于Himawari-8静止气象卫星,提出了一种优化小规模山火监测效果的算法。该算法不仅运用空间上下文技术识别高强度火点,更通过深度挖掘静止气象卫星的高时间分辨率优势,结合火点的时序变化特征,对小规模山火进行精准的动态监测。实践应用证明,该算法在监测小规模山火方面具有显著优势,能够有效实现火点的早期发现与火势变化的实时跟踪。Wildfires are a great threat to the safe operation of transmission lines,especially small-scale wildfires.Once they occur,they may lead to transmission line tripping and affect the normal supply of power.In order to effectively monitor and deal with this hidden danger,based on the Himawari-8 geostationary meteorological satellite,this paper proposes an algorithm to optimize the monitoring effect of small-scale mountain fires.The algorithm not only uses the spatial context technology to identify high-intensity fire points,but also carries out accurate dynamic monitoring of small-scale wildfires by deeply exploiting the advantages of high time resolution of geostationary meteorological satellites and combining with the timing change characteristics of fire points.The practical application proves that the algorithm has significant advantages in monitoring small-scale wildfires,and can effectively realize the early detection of fire points and real-time tracking of fire changes.

关 键 词：山火监测 Himawari-8静止气象卫星 光谱特征 空间上下文 时序变化 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置]