Risk-Informed Digital Twin of Buildings and Infrastructures for Sustainable and Resilient Urban Communities

Abstract

The digital twin (DT) is a virtual replica of real-world buildings, processes, structures, people, and systems created and maintained to answer questions about its physical part, the physical twin (PT). In the case of the built environment, the PT is represented by smart buildings and infrastructures. Full synchronization between the DT and the PT will allow for a perpetual learning process and updating between the two twins. In this work, we introduce a novel concept of DT called risk-informed digital twin (RDT). In the DT the model predictions are developed through data-driven tools and algorithms. However, multiple sources of uncertainty during the lifecycle challenge our understanding and ability to effectively model the performance of the modeled systems. The RDT’s importance lies in its integration of the methods and tools of statistics and risk analysis with machine learning. To this aim, the platform incorporates a novel framework of data-driven uncertainty quantification and risk analysis rooted in information theory. At the core of the RDT is a framework of sustainable and resilient based engineering (SRBE), introduced in this work and considered the first step toward the extension of performance-based engineering (PBE) approaches to socioecological-technical systems under uncertainty. A risk-informed multicriteria decision support tool able to incorporate social aspects is also included, and it can be used for sustainable and resilient design in the early stage, or management under uncertainty of smart buildings and infrastructure systems.