University of Pretoria (UP)’s team of researchers has created an artificial intelligence tool that monitors and predicts daily air pollution against national air quality standards. The team, led by Professor Rebecca Garland, found that certain areas of Mpumalanga and Gauteng have high levels of air pollution. Professor Garland is based at the university’s department of Geography, Geo-informatics and Meteorology.
Mpumalanga is a hotspot of air pollution
According to the available data, Mpumalanga accounts for about 83 percent of South Africa’s coal production and it is home to Eskom’s 12 (of its 15) coal-fired power plants. Sasol’s coal-to-liquids plant in Secunda, and the NatRef refinery in Sasolburg are two main polluters which make Mpumalanga a hotspot of highly toxic air pollution. The extent of the pollution received government’s attention and it designated the region a ‘High Priority Area’s with the then minister of environment publishing air quality management plan to manage the pollution.
Damage to the lungs
Professor Garland was part of an international research team that fed data into a smart computer model to predict PM2.5 levels where there are shortcomings in the available data. PM2.5 refers to particles less than 2.5 micrometres in size emitted by polluting industries like coal-fired power plants and many other sources in the atmosphere. Medical experts have shown that these minute particles can severely damage the lungs.
Using advance machines
According to the World Health Organisation (WHO), PM2.5 particles have been linked to 4.2 million premature deaths worldwide. Since so many different sources emit PM2.5 where people live, it is crucial to make sure PM2.5 levels don’t exceed healthy levels. The researchers used satellite, weather, and land use data to develop a highly accurate machine learning model that estimates daily PM2.5 levels in Gauteng and Mpumalanga. They also used the advanced machine learning model to fill the gaps left by the sparse ground monitors.
Atmospheric science experience
Said Professor Garland: “When you want to know about pollution and its impacts on health, you want to understand how this pollution is distributed in space.” She brought her vast atmospheric science experience to the international team of researchers at Emory University in the USA. “One way of doing this is a machine learning approach to integrate multiple data streams to map out pockets of air pollution,” she added
Ground stations
According to the researchers there are 130 ground stations that monitor air quality all over South Africa. However, these are not enough to get an accurate picture of daily PM2.5 levels. Most of these stations, said the team, do not have adequate PM2.5 data, creating even larger areas where air quality isn’t monitored properly. The team’s model successfully reflected the real world’s seasonal trends and used them to predict daily PM2.5 levels. The model identified that many areas across Gauteng and neighbouring provinces have high levels of PM2.5, with high levels seen in some low-income settlements. “There are PM2.5 sources within low-income settlements and we see high particulate matter levels in winter in the highveld region,” said Professor Garland. “She said the use of solid fuels for cooking and for heating contribute to the increase of PM2.5 and this gets exacerbated during winter.
Creating sufficient monitoring policies
She said although the model showed reduced PM2.5 levels in Tshwane from 2016 to 2018, they still disturbingly remained the same in Johannesburg and surrounding areas. Professor Garland said even though the research was specific to Gauteng and Mpumalanga, it has opened the door for governments all over the world to adopt this method to track PM2.5 for their own areas. This method can help create and adequately monitor policies that manage the risk associated with high PM2.5 levels, she added.
