Convergence Accelerator Phase I (RAISE): Civil Infrastructure Systems Open Knowledge Network (CIS-OKN)

NSF融合加速器支持以团队为基础的多学科努力，以应对国家重要性的挑战，并在不久的将来展示可交付成果的潜力。 这个融合加速器第一阶段项目的重点是通过创建民用基础设施系统开放知识网络（CIS-OKN）来恢复和改善美国国家城市基础设施的重大挑战。该系统将提供收集和分析基础设施数据的工具，这些数据可以改善我们基础设施系统的评估、规划、设计、建设和运营。该项目包括一个由土木工程、数据科学、计算机科学和社会科学专家组成的多学科和多机构团队，并利用行业和政府的合作伙伴关系来识别和利用必要的数据，以实现更安全、更高效、更具成本效益的美国基础设施建设、运营和维护。CIS-OKN有可能改变民用基础设施系统决策者和利益相关者与以前孤立和异构数据交互和使用的方式。该项目旨在提高对导致基础设施恶化的因素的理解，并帮助决策者选择和优先考虑必要的运营，以保持美国基础设施系统的可靠性和提高其可持续性。项目团队？与工业界和政府机构的战略伙伴关系应使他们能够建立一个开放的知识网络，对民用基础设施系统的做法产生影响，从而帮助满足对有弹性和可持续的基础设施系统的需求。数据分析和机器学习的最新进展创造了一个独特的机会，可以从过去和当前的条件中学习，以更好地评估和预测民用基础设施系统的状况和可持续性。通过链接、整合和分析现有的大量数据，CIS-OKN将促进与建设、维护和投资决策相关的见解。研究目标是开发和测试一个开放，共享的公共网络基础设施，用于定位和访问来自多个来源和异构格式的民用基础设施系统数据，以促进知识发现，预测分析和数据驱动的决策。这一努力将包括从语义上理解不同类型数据的内容和相互之间以及与有形基础设施组成部分之间的关系;从非结构化数据源中提取关于基础设施系统状况的信息;将来自不同来源、格式不同、技术和描述细节程度不同的数据链接和融合成统一的知识表述;并为这些异构类型的数据开发集成的查询、推理和学习工具。CIS-OKN有潜力实现数据驱动发现的新模式，将孤立的数据转换为跨学科和机构边界的综合数据分析形式，从而有可能增强民用基础设施系统领域及其他领域的创新。该奖项反映了NSF的法定使命，并被认为值得通过使用基金会的知识价值和更广泛的影响审查标准进行评估来支持。

The NSF Convergence Accelerator supports team-based, multidisciplinary efforts that address challenges of national importance and show potential for deliverables in the near future. This Convergence Accelerator Phase I project focuses on the grand challenge of restoring and improving the U.S. national urban infrastructure by creating a Civil Infrastructure Systems Open Knowledge Network (CIS-OKN). This system will provide tools to assemble and analyze infrastructure data that can improve evaluation, planning, design, construction, and operation of our infrastructure systems. The project includes a multidisciplinary and multi-institutional team of civil engineering, data science, computer science, and social science experts and leverages industry and government partnerships to identify and harness the necessary data to enable safer, more efficient, and cost-effective construction, operation, and maintenance of U.S. infrastructure. The CIS-OKN has the potential to transform the way civil infrastructure systems decision-makers and stakeholders interact with and use what were previously isolated and heterogeneous data. The project seeks to improve understanding of the factors contributing to infrastructure deterioration and to help decision-makers select and prioritize the operations necessary to maintain the reliability and improve the sustainability of the U.S. infrastructure system. The project team?s strategic partnerships with industry and government agencies should enable them to produce an open knowledge network that can have an impact on civil infrastructure systems practices and thereby help meet the need for resilient and sustainable infrastructure systems. Recent advances in data analytics and machine learning have created a unique opportunity to learn from past and current conditions to better assess and predict the conditions and sustainability of civil infrastructure systems. By linking, integrating, and analyzing the wealth of data that exist, the CIS-OKN will facilitate insights relevant to construction, maintenance, and investment decision-making. The research objective is to develop and test an open, shared, public cyberinfrastructure for locating and accessing civil infrastructure systems data from multiple sources and in heterogeneous formats to facilitate knowledge discovery, predictive analytics, and data-driven decision making. The effort will include semantically understanding the content and relationships of different types of data to each other and to the physical infrastructure components; extracting information about infrastructure system conditions from unstructured data sources; linking and fusing data from disparate sources, in different formats, and with different levels of technical and descriptive detail into a unified knowledge representation; and developing integrated querying, reasoning, and learning tools for these heterogeneous types of data. The CIS-OKN has the potential to enable new modes of data-driven discovery, transforming isolated data into forms that enable integrative data analytics across disciplines and institutional boundaries, potentially enhancing innovation across the civil infrastructure systems domain and beyond.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.