EAGER: SAI: Synchronizing Decision-Support via Human- and Social-centered Digital Twin Infrastructures for Coastal Communities

EAGER：SAI：通过以人和社会为中心的数字孪生基础设施为沿海社区同步决策支持

• 批准号: 2122054
• 负责人: Xinyue Ye
• 金额: $ 29.9万
• 依托单位: Texas A&M University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-01 至 2024-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2122054&HistoricalAwards=false
• 关键词: EAGER; SAI; Synchronizing; Decision; Support

Strengthening American Infrastructure (SAI) is an NSF Program seeking to stimulate human-centered fundamental and potentially transformative research that strengthens America’s infrastructure. Effective infrastructure provides a strong foundation for socioeconomic vitality and broad quality of life improvement. Strong, reliable, and effective infrastructure spurs private-sector innovation, grows the economy, creates jobs, makes public-sector service provision more efficient, strengthens communities, promotes equal opportunity, protects the natural environment, enhances national security, and fuels American leadership. To achieve these goals requires expertise from across the science and engineering disciplines. SAI focuses on how knowledge of human reasoning and decision making, governance, and social and cultural processes enables the building and maintenance of effective infrastructure that improves lives and society and builds on advances in technology and engineering.Coastal flooding and storms present a growing global challenge. This SAI project focuses on strategies, technologies, mechanisms, and policies for increasing coastal community resilience. The project centers on the use of digital twins – virtual copies of physical objects and systems that update in real time to match real-world conditions. Digital twins can provide the insights needed to inform resilient decision making in coastal communities. An initial case study is developed through the construction of a digital twin of Galveston Island and portions of other coastal Texan communities. The research adopts a holistic and integrated approach for evaluating, modeling, and testing resilience scenarios. It brings together multiple disciplines including geography, urban planning, landscape architecture, computer science, construction science, and marine science. A participatory and community engagement platform is used to collect ground truth data and gain further in-depth understanding of coastal infrastructure mechanisms at multiple scales. Residents and stakeholders will gain insights into: (1) comparing the pros and cons of different planning efforts; (2) the joint impacts that existing and future planning efforts may have on stakeholders’ individual goals and objectives; and 3) the assets and capacities involved with current dynamic sensors used in digital twin-based information modeling. Decision-makers can leverage the capabilities of this platform to test incremental and place-based planning approaches with real-time priorities, policies, and suggested infrastructure changes. Through software and hardware integration, this digital twin serves as a platform for pursuing solutions to coastal infrastructure challenges. The potential reward is high, as more informed decisions and better affordances for inter-agency coordination may lower the costs of maintaining or replacing the coastal resilience protective system. The digital twin-based decision-support framework serves as a catalyst for further research in data-driven decision making by connecting different datasets and by providing training and collaborative research opportunities for local project participants as well as graduate and undergraduate students.This SAI project supports the resilient design, planning, and development of sustainable infrastructure in coastal communities. It integrates physical, cyber, and social infrastructure data into an analytics platform for real-time, dynamic scenario testing for decision support. This digital twin-based decision support system allows (1) collection, compiling and sharing data on physical, cyber, and social infrastructure; (2) engagement of communities to disseminate information and facilitate citizen science; and (3) promoting a human- and social-centered approach for infrastructure planning and integrated social-environment system dynamics modeling in the context of short-term disasters and long-term climate change. The digital, data-driven decision-making framework integrates a variety of data sources, digital modeling and analytics platforms, and participatory-enhanced infrastructure management considerations. It creates a visualized common operating procedure within a digital twin of local circumstances that local residents and decision-makers can use to better reason about the relationships among different planning efforts, including disaster management, new construction, repair, rehabilitation and retrofitting activities, regular maintenance, system performance, and infrastructure additions. The digital platform collects and simulates highly dynamic and massive volumes of independently-acting, reacting, and interacting agents (such as people, vehicles, structures/infrastructure, and institutions) under different policy or hazard response scenarios. Coupled with immersive technologies, the platform allows people to better understand built and natural environment changes by visualizing how planning and infrastructure alteration and addition can alter resilience levels (positively or negatively). Local knowledge is combined with expert evaluation across multiple flood scenario types and infrastructure change scenarios to test different resilience levels to urban change. By revealing fundamental design and planning principles with implications for action, the research improves U.S. infrastructure for disaster resilience, in support of science-based measures for accessible, affordable, and universal geospatial design interventions.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.

加强美国基础设施 (SAI) 是一项 NSF 计划，旨在促进以人为本的基础性和潜在变革性研究，加强美国的基础设施，为社会经济活力和广泛的生活质量改善提供坚实的基础。私营部门创新、发展经济、创造就业机会、提供更多公共部门服务、加强社区、促进平等机会、保护自然环境、增强国家安全并增强美国的领导力。要实现这些目标，需要来自各个领域的专业知识。 SAI 侧重于人类推理和决策、治理以及社会和文化过程的知识如何能够建设和维护有效的基础设施，从而改善生活和社会，并以技术和工程的进步为基础。该 SAI 项目重点关注增强沿海社区复原力的战略、技术、机制和政策。该项目的重点是使用数字孪生——实时更新以匹配的物理对象和系统的虚拟副本。现实世界的条件可以。通过构建加尔维斯顿岛和德克萨斯州其他沿海社区的数字双胞胎，提供了为沿海社区做出弹性决策所需的见解。它汇集了地理学、城市规划、景观建筑、计算机科学、建筑科学和海洋科学等多个学科，使用参与式和社区参与平台来收集地面实况数据并进一步深入了解。多层面的沿海基础设施机制。居民和利益相关者将深入了解：(1) 比较不同规划工作的优缺点；(2) 现有和未来规划工作可能对利益相关者的个人目标和目的产生的共同影响；以及 3) 资产和能力；决策者可以利用该平台的功能，通过软件和硬件来测试基于实时优先级、政策和建议的基础设施变更的增量和基于地点的规划方法。集成，这个数字孪生作为寻求沿海基础设施解决方案的平台潜在的回报是很高的，因为更明智的决策和更好的机构间协调能力可能会降低维护或更换沿海复原力保护系统的成本，基于数字孪生的决策支持框架可以成为进一步研究的催化剂。通过连接不同的数据集以及为当地项目参与者以及研究生和本科生提供培训和协作研究机会，参与数据驱动决策。该 SAI 项目支持沿海社区可持续基础设施的弹性设计、规划和开发。将物理、网络和社会基础设施数据集成到分析中用于决策支持的实时动态场景测试平台。这种基于数字孪生的决策支持系统允许 (1) 收集、编译和共享有关物理、网络和社会基础设施的数据；(2) 社区参与传播信息和促进公民科学；(3) 在短期灾害和长期气候变化的背景下，促进以人和社会为中心的基础设施规划和综合社会环境系统动力学建模方法。 - 制作框架整合多种数据源，数字化它在当地情况的数字孪生中创建了一个可视化的通用操作程序，当地居民和决策者可以使用它来更好地推理不同规划工作（包括灾害管理）之间的关系。 、新建、维修、修复和改造活动、定期维护、系统性能和基础设施添加。数字平台收集并模拟高度动态和大量的独立作用、反应和交互的主体（例如人、车辆、结构）。 /基础设施，结合沉浸式技术，该平台可以通过可视化规划和基础设施改造和增加如何改变复原力水平（积极或消极）来更好地了解建筑和自然环境的变化。结合多种洪水情景类型和基础设施变化情景的专家评估，以测试不同的城市变化抵御能力水平。通过揭示对行动有影响的基本设计和规划原则，该研究改善了美国的抗灾基础设施，支持基于科学的措施。方便、实惠且通用地理空间设计干预措施。该奖项反映了 NSF 的法定使命，并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，被认为值得支持。

项目成果

Developing Human-Centered Urban Digital Twins for Community Infrastructure Resilience: A Research Agenda

开发以人为本的城市数字孪生以提高社区基础设施的复原力：研究议程

• DOI: 10.1177/08854122221137861
• 发表时间: 2022-11-29
• 期刊: Journal of Planning Literature
• 影响因子: 4.5
• 作者: Xinyue Ye;Jiaxin Du;Yu Han;Galen Newman;D. Retchless;Lei Zou;Youngjib Ham;Zhenhang Cai
• 通讯作者: Zhenhang Cai

Exploring the vertical dimension of street view image based on deep learning: a case study on lowest floor elevation estimation

基于深度学习的街景图像垂直维度探索——以最低楼层标高估计为例

• DOI: 10.1080/13658816.2021.1981334
• 发表时间: 2021-10-06
• 期刊: International Journal of Geographical Information Science
• 影响因子: 5.7
• 作者: H. Ning;Zhenlong Li;Xinyue Ye;Shaohua Wang;Wenbo Wang;Xiao Huang
• 通讯作者: Xiao Huang

Simulating the spatial impacts of a coastal barrier in Galveston Island, Texas: a three-dimensional urban modeling approach

模拟德克萨斯州加尔维斯顿岛沿海屏障的空间影响：三维城市建模方法

• DOI: 10.1080/19475705.2023.2192332
• 发表时间: 2023-12
• 期刊: Natural Hazards and Risk
• 作者: Cai, Zhenhang;Newman, Galen;Lee, Jaekyung;Ye, Xinyue;Retchless, David;Zou, Lei;Ham, Youngjib
• 通讯作者: Ham, Youngjib

Design and Implementation of a Human-Centered Interactive Transportation Dashboard for Small Towns through Heterogeneous Spatial Data Integration

通过异构空间数据集成设计与实现以人为中心的小城镇交互式交通仪表板

• 发表时间: 2023-05
• 期刊: the 18th International Conference on Computational Urban Planning and Urban Management
• 作者: Ye, X.;Li, S.;Du, J.;Li, W.
• 通讯作者: Li, W.

Agent‐based Modeling to Evaluate Human–Environment Interactions in Community Flood Risk Mitigation

基于代理的建模来评估社区洪水风险缓解中的人与环境相互作用

• DOI: 10.1111/risa.13854
• 发表时间: 2021-11
• 期刊: Risk Analysis
• 影响因子: 3.8
• 作者: Han, Yu;Mao, Liang;Chen, Xuqi;Zhai, Wei;Peng, Zhong‐Ren;Mozumder, Pallab
• 通讯作者: Mozumder, Pallab