Real-Time Participatory Sensing-Driven Computational Framework toward Digital Twin City Modeling

A concept of “digital twin” as a model to bridge between a real-world and a virtual twin has emerged in manufacturing and product management. In the context of civil and infrastructure domains, the term “digital twin” has been redefined as up-to-date digital representations of built environments. This paper proposes a real-time participatory sensing-driven computational framework to model the up-to-date state of built environments in a virtual environment. In the proposed framework, crowdsourced visual data are obtained from citizens’ participation to automatically identify the up-to-date states of infrastructure that would negatively impact the community resilience in extreme weather conditions. Then, to update the associated built environment information, real-time participatory sensing data are processed by using deep learning algorithms. Finally, the identified geometric and geospatial information of infrastructure is fed into the virtual environment toward a digital twin city model. Case studies in the context of power distribution infrastructure systems were conducted in Houston, TX, and it was demonstrated that the proposed method robustly updates the up-to-date condition of infrastructure into the digital twin city model. The proposed approach for updating virtual models based on participatory sensing-based real-time information has a great potential to facilitate data-driven decision-making for urban planning and infrastructure management in a smart city digital twin.