Dr Chris Rushton

Profile

I hold master’s degrees in Physics and in Transport Planning and the Environment, and completed my PhD at the Institute for Transport Studies (ITS), University of Leeds in 2016. My doctoral research focused on investigating and modelling real-world driving emissions at fleet level, bridging the gap between controlled laboratory studies and the complex realities of urban mobility.

Following my PhD, I worked in industry as a consultant, where I advised on projects addressing urban air pollution, vehicle emissions, and their policy implications. This period strengthened my ability to connect rigorous technical analysis with the practical challenges faced by cities, regulators, and industry.

I later returned to ITS, where I continue to work on research projects examining air pollution and vehicle emissions, with a strong focus on evidence-based approaches to improving environmental outcomes. Alongside my research, I lecture on these topics, combining technical insight with real-world experience to engage students in the urgent challenges of cleaner transport and sustainable urban environments.

My work sits at the intersection of science, policy, and practice, aiming to translate complex evidence into insights that support informed decisions for healthier, more sustainable cities.

Responsibilities

• Co-Leader SMaD Research Group

Research interests

My research explores the science and policy of vehicle emissions and urban air quality, with an emphasis on translating complex evidence into actionable insights. At its core, this work bridges the gap between measurement, modelling, and decision-making, connecting rigorous analysis with the pressing environmental challenges of modern transport systems.

• Fleet-level emissions and remote sensing

I design and apply remote sensing approaches to capture real-world emissions from vehicles in live traffic. These methods reveal hidden patterns — such as identifying “high-chance gross emitters” — and provide actionable intelligence for fleet management, regulation, and policy. Increasingly, I integrate AI-driven pattern recognition to enhance detection and prioritisation.

• Emissions modelling across scale

My work spans the micro-to-macro spectrum: from vehicle-level dynamics to city-scale emission inventories. I focus on stochastic fleet behaviour, spatial variability, and the integration of diverse data sources, including probe vehicle studies. Generative AI now plays a role in accelerating model calibration and scenario design, enabling richer representations of real-world variability.

• Emissions diagnostics and prioritisation

I investigate how to target interventions where they have the greatest impact. By defining Key Green Performance Indicators (KGPIs), I help policymakers and fleet operators distinguish between genuinely “clean” and “problematic” vehicles. Here too, AI-assisted systems are opening new possibilities for automated diagnostics and decision support.

• Exposure and health in urban mobility

Understanding emissions is only part of the picture; exposure defines risk. I study how travel behaviours, infrastructure, and land use shape population-level exposure, particularly in vulnerable groups such as children. GenAI offers tools to synthesize evidence and simulate exposure scenarios, improving the communication of health impacts to both experts and non-specialist audiences.

• Real-time data systems and informatics
I develop cloud-based systems for real-time emissions data capture and analysis, supporting adaptive interventions in urban transport. Integrating generative AI into these platforms makes it possible to transform raw, complex datasets into intuitive insights, bridging the gap between technical evidence and actionable decisions.

• Generative AI for transport and environment

A distinct and growing strand of my research focuses on how GenAI can accelerate the transition to cleaner transport and healthier cities. This includes AI-assisted modelling frameworks, intelligent dashboards for policymakers, and tools that make environmental evidence more transparent and persuasive. By combining emissions science with generative AI, my work aims not only to analyse the world as it is, but also to help imagine and design the systems we need next.

The web-application for the CARES project is linked below

CARES Project Public Web App