SCC-CIVIC-PG Track B: Community-Centric Pre-Disaster Mitigation with Unmanned Aerial and Marine Systems

该项目将建立一个以社区为中心的应急管理联盟，以试点一项旨在提高社区对长期重大灾害（洪水、野火、飓风、龙卷风和热带风暴）的复原力的计划。 提高抗灾能力的一个关键是在灾害发生前通过全面的环境评估和持续监测记录和了解当前的状况。虽然小型无人驾驶空中和海上机器人与人工智能和地理空间信息系统的进步相结合，为这些评估提供了很大的希望，但各机构没有足够的人员来覆盖脆弱地区。德克萨斯州A M将领导该试点计划，德克萨斯州应急管理部和德克萨斯州林业局将确定三个具有不同脆弱性，人口统计和土地使用的社区的灾前减灾需求：巴斯特罗普，休斯顿，加尔维斯顿。这些社区的高风险高中生将接受培训，使用带有人工智能和GIS工具的无人系统收集和处理数据，然后将结果整合回应急管理框架。因此，社区的复原力将得到改善，同时填补STEM管道，提高经济竞争力，并为熟练的应急响应人员创造职业道路，这些人员精通创新和新兴技术。该项目将使用开源数据集进一步改进和自动化灾前减灾评估。标记的纵向空中和水下数据集将使基础研究和CV/ML以及灾害科学的新进展成为可能。该项目将建立CV/ML的可信度，开发新的算法来识别不同季节和天气条件下的漏洞，并进一步从根本上理解从一个灾难到另一个灾难的迁移学习。关于航空和海洋资产调查频率的数据将产生一个基于信息的采样模型，该模型将在准确性、分辨率和频率之间进行权衡，以确定物体和场景理解。该项目是响应公民创新挑战计划，轨道B-恢复自然灾害，是NSF和国土安全部之间的合作。该奖项反映了NSF的法定使命，并已被认为是值得通过使用基金会的智力价值和更广泛的影响审查标准进行评估的支持。

This project will establish a community-centric emergency management consortium to pilot a program intended to increase community resilience to chronic major disasters: flooding, wildfires, hurricanes, tornadoes, and tropical storms. One key to improving resilience is to document and understand the current conditions through comprehensive environmental assessments and continuous surveillance prior to a disaster. While small unmanned aerial and marine robots combined with advances in artificial intelligence (AI) and geo-spatial information systems (GIS) offer great promise for these assessments, agencies do not have sufficient personnel to cover vulnerable areas. Texas A&M will lead the pilot program where the Texas Department of Emergency Management and Texas Forestry Service will determine the pre-disaster mitigation needs for three communities with different vulnerabilities, demographics, and land use: Bastrop, Houston, Galveston. At-risk high school students in these communities will be trained to use unmanned systems with AI and GIS tools to collect and process the data, then integrate the results back into the emergency management framework. Thus the resilience of the communities will be improved while filling the STEM pipeline, increasing economic competitiveness, and creating career paths for a skilled emergency response workforce that is savvy with innovative and emerging technologies.This project will use open source datasets to further improve and automate pre-disaster mitigation assessments. The labeled longitudinal aerial and underwater datasets will enable fundamental research and new advances in CV/ML as well as disaster science. The project will establish the trustworthiness of CV/ML develop new algorithms for recognition of vulnerabilities during different seasons and weather conditions, and further fundamental understanding of transfer learning from one disaster to another. The data on the frequency of surveying with aerial and marine assets will lead to an informatics-based model of sampling that captures the tradeoffs between accuracy, resolution, and frequency on identifying objects and scene understanding. This project is in response to the Civic Innovation Challenge program, Track B—Resilience to Natural Disasters—and is a collaboration between NSF and the Department of Homeland Security.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.