Knowledge Discovery in Smart City Digital Twins
Neda Mohammadi, John Taylor
Abstract
Despite the abundance of available urban data and the potential for reaching enhanced capabilities in the decision-making and management of city infrastructure, current data-driven approaches to knowledge discovery from city data often lack the capacity for collective data exploitation. Loosely defined data interpretation components, or disciplinary isolated interpretations of specific datasets make it easy to overlook necessary domain expertise, often resulting in speculative decision-making. Smart City Digital Twins are designed to overcome this barrier by integrating a more holistic analytics and visualization approach into the real-time knowledge discovery process from heterogeneous city data. Here, we present a spatiotemporal knowledge discovery framework for the collective exploitation of city data in smart city digital twins that incorporates both social and sensor data, and enables insights from human cognition. This is an initial step towards leveraging heterogeneous city data for digital twin-based decision-making.