Uncertainty-Aware Real-Time Decision-Making in Digital Twins

Digital Twin research not only focuses on creating virtual replicas of physical systems, but also on enabling bi-directional interaction between the physical and the virtual counterpart. By integrating data from sensors, IoT devices, and advanced analytics, Digital Twins provide a dynamic, data-driven approach to understanding and optimizing complex systems.

This stream of research leverages Digital Twin technology for system design, performance optimization, and lifecycle management, with an emphasis on enhancing decision-making and predictive capabilities. Through the integration of AI, machine learning, uncertainty quantification, and real-time data, I aim to develop solutions that bridge the gap between physical and digital domains — positioning Digital Twins as trustworthy and intelligent learning systems that offer robust, real-time decision support.