Energy-aware Transport Digital Twins: Real-time Calibration and Update
Project ID: 2531ad1478
(You will need this ID for your application)
Research Theme: Energy and Decarbonisation
UCL Lead department: Bartlett School of Environment, Energy and Resources (BSEER)
Lead Supervisor: Emmanouil Chaniotakis
Project Summary:
Why is this research important? Digital Twin (DT) technology has the potential to transform the transport sector and deliver better outcomes for the user, more reliable cross modal services, and advance the transition to net zero, while producing high economic benefits. This PhD project aims to enhance our understanding and capabilities on generating energy-aware real-time Digital Twin technology by developing advanced calibration and estimation methods. Leveraging users’ activity schedules, transport network simulations, and performance data, this PhD project will explore innovative Machine Learning and Optimization-based computational frameworks for accurate state estimation in dynamic transport environments. The proposed methods will provide a comprehensive spatio-temporal representation of each transport system component (e.g. vehicles and users), and predict their responses to system excitations (e.g. short-term or long-term disruptions) enhancing system resilience and efficiency.
Who will you be working with? You will be jointly affiliated with the Mobility and Urban Systems Analytics (MUSA Lab), led by Dr Emmanouil (Manos) Chaniotakis from the Bartlett School of Environment, Energy & Resources (BSEER, UCL) which focuses on understanding mobility and urban systems with advanced analytics and the Behaviour & Infrastructure Group, led by Dr Tim Hillel (Civil and Geomatic Engineering, UCL), as part of their ongoing London Digital Twin (LonDiT) initiative.
What will you be doing? You will be performing exciting research on how we can make Digital Twin technologies become reality. Building upon pre-existing datasets and models (activity schedules, transport network simulations, and network performance data), you will be developing real-time updating Machine Learning and Optimisation frameworks taking into account the transport-energy interactions.
Who are we looking for? We seek an enthusiastic and creative individual with strong mathematical and computing skills, experience with optimisation, machine learning, and/or transport/energy demand modelling, and a passion for conducting research that drives positive change.