Imagine that you could know not only the weather that is going to be tomorrow in a neighborhood of your city or in your town, but you could also read the forecast of how polluted that area is going to be . Perhaps this information does not interest you very much, but surely you would like to know if you have a respiratory disease, allergy, etc.
To date, knowing these data in advance was generally not possible. The measurements of the pollution levels are made in real time or in reverse. However, they have created a technology that can go ahead and predict how polluted the air in a certain area will be.
The project is being led by a team of computer scientists from Loughborough University (UK). They have created an artificial intelligence that is capable of predicting pollution levels hours or even days (1 or 2) in advance . It does so by making use of public historical data for each location and, based on them, making forecasts.
The AI calculates PM2.5 , particles less than 2.5 microns in diameter characterized by that typical reduced visibility in cities and hazy air when their levels are soaring. This pollutant is one of the most worrisome to public health, because the particles are so tiny that they can easily reach the lungs of people and, later, the bloodstream and cause respiratory, cardiovascular or cerebrovascular problems.
Until now, some systems have been created that could predict PM2.5, but this technology represents several advances. One of the novelties of the system is that it can provide a new vision of environmental factors that have a significant impact on air pollution levels. Thus, it interprets different factors and data to get figures. And it not only gives an amount, but it offers a range of values by performing what is known as ‘uncertainty analysis’.
First tests carried out in China
The system is part of a larger research project that would have been funded by the Newton Fund, which has four partners: Satoshi Systems Ltd, Loughborough University, Shenzhen Institutes of Advanced Technology, and EEG Smart Intelligente Technology in China.
The researchers first used their system in China to test and train their algorithms. The choice had a reason: 145 of the 165 cities in the country tend to have serious air pollution problems.
Professor Qinggang Meng, one of the two researchers who is leading the creation of AI, has commented that: “Air pollution is a long-term accumulated challenge faced by the whole world and, especially, affects many developing countries” .
“The project aims to measure and forecast air quality and pollution levels. We are also exploring the feasibility of linking real-time information on carbon emissions with end-to-end carbon credit trading , thus dedicating ourselves to controlling carbon and reducing greenhouse gas emissions ”, he added.
The researcher hopes that this research will help “achieve cleaner air for the community and improve people’s health in the future.”
