CRISP Type 2/Collaborative Research: Resilience Analytics: A Data-Driven Approach for Enhanced Interdependent Network Resilience

最近的自然灾害对我们规划和管理破坏性事件的传统方法提出了挑战。今天，社交媒体提供了一个利用社区驱动数据的机会，帮助我们了解社区网络（如朋友、社区）、物理基础设施网络（如交通、电力）和服务提供商网络（如应急响应人员、恢复人员）的复原力或缺乏复原力。这个关键弹性相互依赖的基础设施系统和过程（CRISP）合作研究整合了工程、计算机科学和社会科学的多个学科观点，以解决社区驱动的数据如何帮助(i)了解这些相互依赖的网络在中断之前、期间和之后的行为，以及（ii）更有效地减少它们对中断的脆弱性并加强它们在中断后的恢复。研究结果将大大提高我们对自然灾害后基础设施恢复的认识和管理。在弹性分析中，有两个研究组成部分。第一个组成部分创建了基础设施网络、它们所服务的社区网络以及在中断后参与响应的服务网络之间相互依赖的网络模型。本部分将探讨社区弹性和基础设施网络性能之间的功能关系。模型结果将使决策者能够了解不同网络和地区的复原力平衡。第二个组件将相互依赖的网络模型与社区来源的数据集成在一起，以开发一个数据分析框架，以便更好地理解和规划弹性。这一组成部分建立在社会技术系统领域的研究基础上，该领域涉及对中断后监测的社交媒体数据进行分析。这些方法将利用社区社会科学家的专业知识评估由众包数据提供的信息的价值。这个项目借鉴了多个学科的多种方法。本项目探索的多学科方法对于弹性分析的突破至关重要。该项目旨在使我们进一步了解来自社交媒体和其他来源的实时数据如何描述、预测和规定在危机中管理相互依存网络的做法。

Recent natural disasters have challenged our traditional approaches of planning for and managing disruptive events. Today, social media provides an opportunity to make use of community-driven data to help us understand the resilience, or lack thereof, of community networks (e.g., friends, neighborhoods) physical infrastructure networks (e.g., transportation, electric power) and networks of service providers (e.g., emergency responders, restoration crews). This Critical Resilient Interdependent Infrastructure Systems and Processes (CRISP) collaborative research integrates multiple disciplinary perspectives in engineering, computer science, and social science to address how community-driven data can help (i) understand the behavior of these interdependent networks before, during, and after disruptions, and (ii) more effectively reduce their vulnerability to and enhance their recovery after a disruption. The results will significantly improve our understanding and management of infrastructure recovery from natural disasters. Two research components comprise this effort in resilience analytics. The first component creates a network model of the interdependence of infrastructure networks, the community networks that they serve, and the service networks engaged to respond after a disruption. This component will explore the functional relationships between community resilience and infrastructure network performance. Model results will enable decision makers to understand the balance of resilience across the several networks and regions. The second component integrates the interdependent network model with community-sourced data to develop a framework of data analytics to better understand and plan for resilience. This component builds on research in the field of socio-technical systems relating to the analysis of social media data monitored after a disruption. The methods will assess the value of information provided by crowd-sourced data with expertise of community social scientists. This project draws upon multiple methods across several disciplines. The multidisciplinary methods explored in this project are essential for a breakthrough in resilience analytics. This project aims at taking a significant step forward in our understanding of how real-time data from social media and other sources can describe, predict, and prescribe practices to manage interdependent networks in crises.