AI system predicts levels of harmful PM2.5

The technology has the potential to provide new insight into the environmental factors that have significant impacts on air pollution levels.

Professor Qinggang Meng and Dr Baihua Li are leading the project which is focussed on using AI to predict PM2.5, which is particulate matter of under 2.5 microns (10⁻⁶ m) in diameter and a pollutant with the strongest evidence for public health concern. This is because the particles easily get into the lungs and then the bloodstream, resulting in cardiovascular, cerebrovascular and respiratory impacts.

Bath University to host petrol particulate reduction study

According to the UK’s Department for Environment, Food and Rural Affairs, there is understood to be ‘no safe threshold below which no adverse effects would be anticipated’.

The new system is said to give predictions for the levels of PM2.5 in one hour to several hours’ time, plus 1-2 days ahead, and interprets the various factors and data used for prediction, which could lead to a better understanding of the weather, seasonal and environmental factors that can impact PM2.5.