17.03.20
Scientists at Loughborough Uni develop AI air pollution system
Computer scientists at Loughborough University have developed a new artificial intelligence (AI) system that can predict air pollution levels.
Air pollution kills an estimated seven million people per year around the world, making it a huge concern for at-risk communities.
The AI system created by a team of computer scientists at Loughborough University has the ability to predict air pollution levels hours in advance.
This technology could have a profound impact on world health as it could provide new insight into the environmental impact affecting air pollution levels.
The project, led by Professor Qinggang Meng and Dr Baihua Li, uses AI to predict ‘PM2.5’, normally more prevalent in cities, resulting in reduced or ‘hazy’ visibility when levels are high.
This specific type of particulate matter poses the biggest threat to health according the to The World Health Organization. This is because the size is small enough to get into the lungs and bloodstream, having an impact on the respiratory and cardiovascular systems.
While the technology already exists to predict PM2.5 levels, the team’s research is aiming to push this technology to the next level.
The system is novel because it predicts PM2.5 levels in advance and interprets the various factors and data used, which could help to identify and understand seasonal and environmental factors attributed to these particles.
The system can predict an entire range of values the air pollution reading could fall into, known as ‘uncertainty analysis’ and has the capabilities to be used as an analysis tool in a carbon credit trading system.
To test the new system, researchers used public historical data on air pollution in Beijing to train the algorithms, and the developed system will now be used for live data captured by sensors deployed in Shenzhen, China.
Professor Meng said:
“Air pollution is a long-term accumulated challenge faced by the whole world, and especially in many developing countries.
“The project aims to measure and forecast air quality and pollution levels. We also explore the feasibility of linking the real-time information on carbon emission to end-to-end carbon credit trading, thus dedicating to carbon control and greenhouse gas emission reduction.
“We hope this research will help lead to cleaner air for the community and improve people’s health in the future.”