A new generation of mobile air pollution sensors, enhanced with Artificial Intelligence (AI), could significantly improve the accuracy of air quality measurements and help individuals better understand pollution levels in their local areas, according to a recent study by Kingston University.
Image Credit: dee karen/Shutterstock.com
Published in Sensors (MDPI), the study looked at how low-cost, portable electrochemical sensors—about the size of a mobile phone—could be enhanced with AI to provide accurate, real-time air quality readings at any location.
Current air monitoring systems are expensive, fixed in place, and relatively few in number. That means the nearest monitoring station often doesn’t reflect the air quality on your street or in your neighborhood. The World Health Organization reports that air pollution contributes to around seven million deaths each year, with children particularly vulnerable due to developing lungs, weaker immune systems, and faster breathing rates.
Backed by internal Seedcorn funding, Innovate UK, and the UK Shared Prosperity Fund, the Kingston University team partnered with Technocomm Consulting Ltd—experts in sensor and network technologies—to explore solutions. Technocomm developed the affordable sensor, called EnviroSense, while Kingston researchers investigated how environmental conditions and other gases affect its accuracy.
To test performance, the team installed the sensors alongside high-precision reference instruments at the Weybourne Atmospheric Observatory on the North Norfolk coast. This location was ideal due to varying pollution levels carried in by southwesterly winds from urban and industrial regions across the UK.
Over 12 weeks—from May to August 2024—the sensors recorded carbon monoxide (CO), carbon dioxide (CO2), and ozone (O3) levels every 30 minutes. Weather conditions were also tracked to better understand how pollutants interact with environmental factors.
The data collected was then processed using advanced AI models. The result was a reduction in measurement errors by up to 46 %.
The study shows that AI can take affordable, imperfect sensors and refine their output to a level of accuracy useful for public health and policy decisions.
Thanks to these findings, Technocomm has since released an upgraded commercial version: EnviroSense AI. The project has been recognized as a success story by Innovate UK.
Professor Jean-Christophe Nebel, co-investigator and Director of Kingston University’s Knowledge Exchange and Research Institute for Cyber, Engineering and Digital Technologies, emphasized the practical impact of the work.
We’ve discovered that portable air sensors, powered by AI, give accurate enough data to really make a difference to the public. The data has the potential to inform policy decisions and enable emergency measures at local levels to directly contribute to protect the health of the public – revolutionizing air quality monitoring and traffic management.
Jean-Christophe Nebel, Study Co-Investigator and Professor , Knowledge Exchange and Research Institute Director for Cyber, Engineering and Digital Technologies, Kingston University
“Our dream is to have one of these sensors on every bus or refuse collection vehicles visiting every single postcode, and for this to provide easily accessible and highly accurate air pollution data to everyone about where they live or work,” added Nebel.
Dr. Farzana Rahman, principal investigator and senior lecturer in data science, said the project tackled a critical public health challenge.
Dr. Rahman added, “The innovative AI-powered sensors transform air quality monitoring and have made the data more accurate and accessible than ever. This collaboration has not only addressed a critical public health challenge but also set the stage for future advancements and impactful partnerships.”
Technocomm Managing Director Bijan Mohandes credited the close partnership with Kingston for the project’s success.
The regular team meetings with follow-on action items and execution were instrumental in defining the successful outcome of the project on time. The research showed that Machine Learning and AI have a role to play in modelling accurate electrotechnical sensors.
Bijan Mohandes, Managing Director, Technocomm Consulting Ltd.
Trials are already underway with Rey Juan Carlos University in Madrid and a university in Kuala Lumpur, Malaysia, to test the sensors and AI in different climates and pollution conditions.
Journal Reference:
Colleaux, Y., et al. (2025) Air Pollution Monitoring Using Cost-Effective Devices Enhanced by Machine Learning. Sensors. doi.org/10.3390/s25051423