skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.


Title: Towards an AI-driven framework for multi-scale urban flood resilience planning and design
Abstract Climate vulnerability is higher in coastal regions. Communities can largely reduce their hazard vulnerabilities and increase their social resilience through design and planning, which could put cities on a trajectory for long-term stability. However, the silos within the design and planning communities and the gap between research and practice have made it difficult to achieve the goal for a flood resilient environment. Therefore, this paper suggests an AI (Artificial Intelligence)-driven platform to facilitate the flood resilience design and planning. This platform, with the active engagement of local residents, experts, policy makers, and practitioners, will break the aforementioned silos and close the knowledge gaps, which ultimately increases public awareness, improves collaboration effectiveness, and achieves the best design and planning outcomes. We suggest a holistic and integrated approach, bringing multiple disciplines (architectural design, landscape architecture, urban planning, geography, and computer science), and examining the pressing resilient issues at the macro, meso, and micro scales.  more » « less
Award ID(s):
1739491 1937908
PAR ID:
10295179
Author(s) / Creator(s):
; ; ; ;
Date Published:
Journal Name:
Computational Urban Science
Volume:
1
Issue:
1
ISSN:
2730-6852
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Project Overview: This NSF-funded project (Award #2019754) is part of the Belmont Forum’s Disaster Risk, Reduction, and Resilience (DR3) initiative, a global effort to assess and mitigate disaster risks through transdisciplinary collaboration. The study investigates strategies to enhance the resilience of low-income communities living in flood-prone and climate-vulnerable regions, with a geographic focus on Brazil, East Africa, and the southeastern United States. The U.S. component centers on coastal and urban communities in Florida, particularly those at risk from flooding and extreme weather events. Research Objectives: Through a transdisciplinary approach, the project integrates machine learning, geospatial analytics, and socio-economic data to: - Assess community-level vulnerabilities to flooding and extreme heat, -Identify barriers to adopting disaster-resilient housing, - Co-design affordable, climate-resilient housing prototypes using sustainable, locally sourced materials. The research aims to support community-informed design strategies and policy recommendations that are adaptable across different socio-economic and geographic contexts. Dataset Description: The dataset contains responses from approximately 500 residents aged 18+ living in low-income, flood-prone neighborhoods in Florida. The survey captures detailed information on: - Housing conditions and infrastructure, - Disaster preparedness and flood risk perception, - Access to services during and after disasters, - Health and economic impacts of extreme weather events, - Community cohesion and recovery strategies. This dataset serves as a resource for researchers, urban planners, emergency response agencies, and policymakers seeking data-driven insights to inform resilient housing design, climate adaptation, and disaster recovery planning. Data Collection and Anonymity: Survey distribution and data collection were conducted in partnership with Centiment, a third-party research company that recruits demographically targeted panels for academic and applied research. For this study, Centiment distributed the survey to residents of low-income, flood-prone communities in Florida, based on geographic and socio-economic criteria specified by the research team. All personally identifiable information (PII), such as IP addresses, email addresses, and precise geolocation data, was removed prior to uploading the dataset to DesignSafe. The dataset has been reviewed to ensure participant anonymity in accordance with DesignSafe data protection policies and applicable ethical standards. 
    more » « less
  2. We describe a framework for deploying agent-based models as a tool for decision-making during resilience planning, with an emphasis on flood mitigation. Prior work has demonstrated that agent-based models can be effective tools for modelling evolving community flood resilience and risk perception when they incorporate elements of individual decision-making. We argue for extending this methodology and incorporating it into regional infrastructure and resilience planning in order to 1) create more distributed and robust green infrastructure implementations and performance management systems; 2) provide a critique and alternatives to existing planning and delivery processes based on public sector jurisdictional boundaries; and, 3) validate and improve the modelling process by connecting it directly to stakeholder decision-making processes. This final point will effectively merge these systems-centric modelling approaches with human-centred community organising that employs various co-design methods. In regard to the ABMs, co-design methods can be a useful source of real-world data about individual decision-making that can inform and validate iterations of the models. For stakeholders, they can be a valuable source of information and education about flood risk and climate-related impacts that might not be available through other channels. And finally, hands-on workshops coupled with potential small implementation grants can be effective ways of providing skills and incentives to stakeholders who may wish to undertake projects on their own property, reshaping the way green infrastructure planning and implementation can be accomplished. 
    more » « less
  3. This study systematically reviews the diverse body of research on community flood risk management in the USA to identify knowledge gaps and develop innovative and practical lessons to aid flood management decision-makers in their efforts to reduce flood losses. The authors discovered and reviewed 60 studies that met the selection criteria (e.g., study is written in English, is empirical, focuses on flood risk management at the community level in the USA, etc.). Upon reviewing the major findings from each study, the authors identified seven practical lessons that, if implemented, could not only help flood management decision-makers better understand communities’ flood risks, but could also reduce the impacts of flood disasters and improve communities’ resilience to future flood disasters. These seven lessons include: (1) recognizing that acquiring open space and conserving wetlands are some of the most effective approaches to reducing flood losses; (2) recognizing that, depending on a community’s flood risks, different development patterns are more effective at reducing flood losses; (3) considering the costs and benefits of participating in FEMA’s Community Rating System program; (4) engaging community members in the flood planning and recovery processes; (5) considering socially vulnerable populations in flood risk management programs; (6) relying on a variety of floodplain management tools to delineate flood risk; and (7) ensuring that flood mitigation plans are fully implemented and continually revised. 
    more » « less
  4. Coastal Communities are exposed to multiple hazards including hurricanes, storm surges, waves, and riverine flash floods. This paper presents the outcome of a Basin-wide Flood Multi-hazard Risks module that was developed and offered as part of a collaboration between two research projects: the UPRM-DHS Coastal Resilience Center of Excellence (CRC) funded by the Department of Homeland Security and the Resilient Infrastructure and Sustainability Education Undergraduate Program (RISE-UP) funded by the National Science Foundation (NSF). The content was designed to give students an understanding of complex project management in coastal communities. The main learning objective was for students to be able to assess and recognize the actions that can be taken to improve resiliency in coastal communities. Students learned how to manage multi-hazard floods. Through knowledge gained by participating in lectures, discussions, and the development of case studies, students were able to assess flood risk and current mitigation strategies for coastal communities in Puerto Rico. The learning experience provided an overview of the history, needs, and challenges that coastal communities face regarding flood and coastal hazards. Through the case studies, students were able to appreciate and understand the risk exposure on the natural and built infrastructure, and the importance of always taking into consideration the social impact. 
    more » « less
  5. Power grids based on traditional N-1 design criteria are no longer adequate because these designs do not withstand extreme weather events or cascading failures. Microgrid system has the capability of enhancing grid resilience through defensive or islanded operations in contingency. This paper presents a probabilistic framework for planning resilient distribution system via distributed wind and solar integration. We first define three aspects of resilient distribution system, namely prevention, survivability and recovery. Then we review the distributed generation planning models that comprehend moment estimation, chance constraints and bi-directional power flow. We strive to achieve two objectives: 1) enhancing the grid survivability when distribution lines are damaged or disconnected in the aftermath of disaster attack; and 2) accelerating the recovery of damaged assets through pro-active maintenance and repair services. A simple 9-node network is provided to demonstrate the application of the proposed resilience planning framework 
    more » « less