ERI: Advancing Understanding of Data-driven Wildfire Evacuation Planning for Communities with Transient Populations in the Wildland-Urban Interface

由于过去几年野火造成的重大生命财产损失，野火疏散规划已成为荒地-城市界面（WUI）社区的优先事项。兼职居民和流动人口（如游客）在疏散后勤和行为方面可能与全职居民不同，这对社区疏散规划提出了重大挑战。该工程研究启动（ERI）项目将利用大数据和计算机模型开发一种新的野火疏散规划方法，该方法可以将兼职居民和流动人口纳入考虑，并考虑不同的疏散方案。研究成果将与社区利益相关者分享，以改进当地的野火疏散计划。本项目产生的知识将帮助疏散研究人员和从业人员更好地利用大数据和最新的野火疏散建模技术来改善野火公共安全。此外，该项目将支持下一代地理信息系统（GIS）专业人员、数据科学家/工程师和疏散研究人员/从业人员的教育和培训。该项目将促进对大数据和耦合野火疏散模型在流动人口社区野火疏散规划中的应用的理解。研究小组将进行入户调查，研究全职居民和兼职居民在疏散后勤和行为方面的差异。然后，我们将整合火灾蔓延和微观交通模拟模型，建立一个耦合的野火疏散模型，该模型可以纳入全职和兼职居民的疏散物流和行为以及其他流动人口。利用来自不同来源的各种数据，系统地设计一系列疏散场景，并利用开发的疏散模型对这些疏散场景进行疏散模拟。生成的火灾周长和高分辨率车辆轨迹数据将用于导出疏散时间估计和车辆暴露计数信息。研究小组将使用GIS可视化车辆暴露计数信息。此外，将采用疏散规划方法为研究地点创建数据驱动的疏散计划。研究结果将通过在线研讨会、出版物、会议报告和网络地理信息系统应用程序广泛传播。该项目由人类、灾害和建筑环境（HDBE）和促进竞争研究的既定计划（EPSCoR）共同资助。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

Due to the significant loss of life and property caused by wildfires in the past few years, wildfire evacuation planning has become a priority for communities in the wildland-urban interface (WUI). Part-time residents and transient populations (e.g., visitors) can differ from full-time residents in terms of evacuation logistics and behavior, which poses a significant challenge for community evacuation planning. This Engineering Research Initiation (ERI) project will leverage big data and computer models to develop a new wildfire evacuation planning approach that can incorporate part-time residents and transient populations and take into account different evacuation scenarios. Research outputs will be shared with community stakeholders to improve local wildfire evacuation plans. The knowledge generated in this project will help evacuation researchers and practitioners better use big data and the newest wildfire evacuation modeling techniques to improve wildfire public safety. Furthermore, this project will support education and training for the next-generation of geographic information systems (GIS) professionals, data scientists/engineers, and evacuation researchers/practitioners.This project will advance understanding the use of big data and coupled wildfire evacuation models in wildfire evacuation planning for communities with transient populations. The research team will conduct a household survey to study the difference between full-time and part-time residents with regard to evacuation logistics and behavior. Then we will integrate fire spread and microscopic traffic simulation models to develop a coupled wildfire evacuation model that can incorporate full-time and part-time residents’ evacuation logistics and behavior and other transient populations. A variety of data from different sources will be used to systematically design a series of evacuation scenarios, and the developed evacuation model is used to perform evacuation simulations for these evacuation scenarios. The generated fire perimeter and high-resolution vehicle trajectory data will be used to derive evacuation time estimates and vehicle exposure count information. The research team will use GIS to visualize vehicle exposure count information. Additionally, the evacuation planning approach will be employed to create data-driven evacuation plans for the study site. The research findings will be broadly disseminated via an online workshop, publications, conference presentations, and a Web GIS application.This project is jointly funded by Humans, Disasters, and the Built Environment (HDBE) and the Established Program to Stimulate Competitive Research (EPSCoR).This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.