Integrated Stage-based Evacuation with Social Perception Analysis and Dynamic Population Estimation

在灾难性事件中有效疏散是美国许多地方政府机构面临的最具挑战性的问题之一。该研究项目将开发一个原型综合野火疏散决策支持系统，并创建分析工具，供疏散规划者和应急资源管理人员进行评估。我们的跨学科研究团队将与圣地亚哥县应急服务办公室（OES）、美国红十字会圣地亚哥/帝国县分会和圣地亚哥2-1-1合作开发这个基于网络的系统。这项研究将有助于应急响应机构在灾难性事件期间更好地了解公众的看法和需求，并为当地社区制定更有效的疏散计划。研究框架可以扩展到其他类型的自然灾害（如海啸、飓风、洪水灾害），并进行一些修改，以应对疏散计划的不同需求。本项目开发的动态人口密度模型可应用于城市规划、选举、企业营销和设施管理。社会感知分析模型和民意监测可以帮助其他研究领域，如交通事件检测和公共运动。这个项目最有价值的组成部分之一是建立一个居民反馈网络，通过手机应用程序和在线论坛将注册的当地志愿者联系起来。该项目还将包括研究生的参与，通过各种论坛进行传播，包括一个项目网站和一个涉及多学科研究人员的论坛。将组织三次夏季研讨会，以促进未来研究人员和政府机构之间的多学科合作。利用大数据驱动技术，该项目将整合多个数据源，包括社交媒体、人口普查、地理信息系统（GIS）数据层、志愿者建议和遥感数据，开发一个综合的野火疏散决策支持系统（IWEDSS）。该系统将提供数据采集、交通需求建模、疏散操作和信息发布等关键功能。它将为疏散规划者和政府机构提供基于科学和数据驱动的分析工具，以做出更好的决策，从而减少疏散时间和潜在的伤亡人数。该项目的四个主要目标是：(1)通过整合多个数据源和GIS模型，建立城市地区动态估计人口分布（密度）模型；(2)考虑人口密度分布，设计基于阶段的疏散方案，建立考虑需求不确定性的稳健优化模型；(3)通过实时分析社交媒体和志愿者建议，了解当地社区对灾害的社会感知，建立舆情监测和居民反馈网络，完善疏散方案；(4)构建基于网络的地理空间分析平台，为决策者、应急资源管理者和公职人员提供交互式决策支持工具。这个跨学科项目将依靠地理信息科学、地图学、土木工程、交通运输和社交媒体分析的融合，促进传统的静态疏散规划程序向动态、以用户为中心、易于使用和数据驱动的空间决策支持系统的转变。

Effective evacuation during disastrous events is one of the most challenging issues for many local government agencies in U.S. This research project will develop a prototype integrated wildfire evacuation decision support system and create analytic tools that will be evaluated with evacuation planers and emergency resource managers. Our interdisciplinary research team will collaborate with the Office of Emergency Services (OES) of San Diego County, the San Diego/Imperial Counties Chapter of the American Red Cross, and 2-1-1 San Diego to develop this web-based system. This research will help emergency response agencies better understand public perceptions and needs during disastrous events, and create more effective evacuation plans for local communities. The research framework can be extended to other types of natural disasters (e.g., tsunami, hurricanes, flood hazards) with some modifications to cope with different needs of evacuation plans. The dynamic population density model developed in this project can be applied in urban planning, elections, business marketing, and facility management. The social perception analysis model and public opinion monitors can help other research domains such as traffic incident detection and public campaigns. One of the most valuable components in this project is the establishment of a resident feedback network by connecting registered local volunteers using a mobile phone application and an online forum. The project will also include involvement of graduate students, dissemination through various fora, including a project website and a discussion forum to involve multidisciplinary researchers. Three summer workshop meetings will be organized to facilitate future multidisciplinary collaborations among researchers and government agencies.Using Big Data-driven techniques, this project will integrate multiple data sources including social media, census survey, geographic information systems (GIS) data layers, volunteer suggestions, and remote sensing data to develop an integrated wildfire evacuation decision support system (IWEDSS). This system will provide key functions for data collection, traffic demand modeling, evacuation operation, and information dissemination. It will offer scientifically-based and data-driven analytic tools for evacuation planers and government agencies to make better decisions that can reduce the evacuation time and potential number of injuries and deaths. The four main goals of this project are to (1) build a dynamic estimated population distribution (density) model in urban areas by integrating multiple data sources and GIS models; (2) design stage-based evacuation plans with population density distributions and develop robust optimization models to account for demand uncertainties; (3) create a public opinion monitor and a resident feedback network to improve evacuation plans by understanding social perception of the disasters in local communities through the real-time analysis of social media and volunteer suggestions; (4) build a web-based geospatial analytics platform and provide interactive decision support tools for decision makers, emergency resource managers, and public officers. This interdisciplinary project will rely upon a convergence among GIScience, cartography, civil engineering, transportation, and social media analytics to facilitate the transformation of traditional static evacuation planning procedures into a dynamic, user-centered, easy-to-use, and data-driven spatial decision support system.