Fake plates and "ghost" vehicles are not only a burden on the taxpayer, but also impact road safety. This session looks at how we can use AI to spot cloning and plate anomalies in real-time. We’ll explore how smart tech helps authorities identify and address fraud, fix data gaps and make roads fairer.

TransHumanity's vision is to empower faster, smarter human decisions by transforming data into accessible intelligence using large language model based agentic AI. Its product, AptIq, is designed to help transport authorities and organisations quickly analyse data and models, turning days of analysis into seconds then giving the user the tools to communicate this analysis. By simply asking questions in plain English, users can gain instant insights to support key initiatives like congestion reduction, road safety, creation of business cases and net-zero targets.

The award-winning Tees Valley Digital Twin is the UK’s first region-wide automated traffic management system, developed by Aimsun and Yunex Traffic for the Tees Valley Combined Authority. It integrates real-time traffic, bus, and signal data with predictive simulation and machine learning to enable proactive network management. Monitoring and evaluation show a 13.7% reduction in delays on high-demand corridors and significant bus performance improvements, with average speeds increasing by over 11 mph within minutes of intervention. The system operates alongside existing traffic management platforms, reducing manual input and emissions through optimised signal strategies. 

AI in the transport sector has the potential to deliver major decarbonisation benefits through improving efficiency, optimising systems, and reducing waste. However, the environmental costs associated with building, training, and running AI systems are opaque and not well understood.

As AI is rapidly rolled out and scaled up, how can you as a decision-maker or practitioner make sense of the carbon impacts and trade-offs of the AI tools being deployed in your area? How do different types of AI models vary in their environmental impact, and what does that mean for choosing the right approach? Are some AI applications more 'worth it' than others?