Wildland fire management using near real time high resolution remote sensing data

该项目的目标是制定收集和分析数据的标准和方法，以更好地了解荒地火灾周围的地形，燃料和天气，以支持火灾管理和消防决策。无人驾驶飞机，辅以卫星图像，将用于收集视觉和多光谱植被（燃料）数据。机器学习方法将用于推断感兴趣的植被特征，包括树种、大小、形状、连通性、密度、表面燃料成分、树冠燃料特征和阶梯燃料分布。利用这些数据，将更好地预测火灾行为，这将有助于更好地管理加拿大的野火。具体来说，该项目探索了无人机的四种应用，以改进荒地火灾规划和运营决策（1）使用在面临荒地火灾风险的社区周边收集的数据来评估树木和植被的接近程度和密度，用于火灾风险评估，（2）在野火发生之前，将无人机飞到建筑物上，以进行现场暴露评估，并在火灾发生期间做出建筑物分类决策，（3）改进对火势蔓延和方向的预测，以及（4）使用收集的数据为改进灭火活动的部署决策提供信息，例如空中加油机、水上轰炸机、直升机和地勤人员。

The goal of this project is to develop standards and methods to collect and analyze data to generate a better understanding of topography, fuel and weather around wildland fires to support fire management and firefighting decisions. Drones, supplemented by satellite imagery, will be used to collect visual and multispectral vegetation (fuel) data. Machine learning methods will be used to infer vegetation characteristics of interest, including tree species, size, shape, connectivity, density, surface fuel composition, crown fuel characteristics and ladder fuel distributions. Using this data, better fire behavior predictions will be made which will allow for better management of wildland fires in Canada. Specifically, the project explores four applications of drones for improved wildland fire planning and operational decision making (1) use collected data around the perimeter of a community at risk to wildland fires to assess closeness and density of trees and vegetation, which is used for fire risk assessments, (2) fly drones to structures ahead of wildland fires to perform field exposure assessments and make structure triage decisions during active fires, (3) improve prediction of fire spread and direction, and (4) use collected data to inform improved decision making on deployment of suppression activities such as airtankers, waterbombers, helicopters and ground crews.