A collaboration between the UKCRIC Urban Observatories of Newcastle, Birmingham, and Manchester, the Alan Turing Institute, and the Department for Transport (DfT) is demonstrating the potential of a science-led digital twin approach to decarbonising transport, and standardising this approach on a national scale.
The urgent need to address the climate emergency has led many cities and organizations in the UK to invest in Internet of Things (IoT) sensors to collect real-time data on metrics such as traffic flows, air quality, and passenger data. This data is then used to develop strategies to reduce their carbon footprints. However, as there are 115 urban centers in the UK, each may take a different path to sensor deployment, data management, and data access, leading to potential complications due to a lack of standardization and consistency in approach. The Urban Observatories collect a substantial amount of data regarding mobility and its effects on the environment. They have established a common ethos and data sharing access protocols. The challenge addressed in this research is to understand how these can be scaled to regional and national studies to support agile and data driven responses.
This collaboration aims to tackle this challenge by establishing the groundwork for a flexible yet consistent approach. This will be achieved by cataloguing existing sensor capabilities, benchmarking current metadata standards, developing mechanisms for data standardisation and data onboarding and exploring applications of real-time data for future urban digital twins. The project has developed a living sensor catalogue to complement existing DfT portals and has highlighted important issues in capturing key metadata for decision makers. A number of use cases have been developed that explore how new sensor assets data can then be exploited with improved models and an onboarding prototype has used the Urban Data Exchange model to demonstrate technology agnostic onboarding and common mapping to smart data models to achieve standardisation. From machine learning based traffic prediction, modelling of Low Traffic Neighbourhoods (LTNs) and monitoring black carbon have been prototyped, demonstrating the potential future use cases of digital twins. The collaboration is laying the groundwork and demonstrating the role that real-time high-resolution metrics can play in digital twins for local transport at the city, regional, and national levels.