Artificial intelligence (AI) can be applied -and in fact it has already been used for years- in improving the performance of multiple technologies, uses and services, not only in recently famous conversational or text creation systems (in the style of ChatGPT).
In the area of ​​the environment, the applications are very diverse and the growth expectations are immense. One of the most recent proposals has emerged from a group of experts from the Barcelona Supercomputing Center, a pioneering public entity in the development and use of supercomputers in Spain, and its objective is the application of artificial intelligence in the management of air quality in urban areas.
The BSC experts recall that “99% of the world population breathes air that exceeds the pollution limits that the World Health Organization (WHO) recommends not to exceed, and this scenario of poor air quality is exacerbated in areas urban areas where more than 50% of the population is concentrated”. To mitigate the problem of air pollution, which the WHO considers the main environmental risk factor for health worldwide, it is crucial to have more reliable and precise data on the concentration of air pollutants in our cities, especially nitrogen dioxide. (NO2) due to its detrimental effects on people’s quality of life and the associated economic consequences.
In order to advance in this line of research, a team of scientists from the Earth System Services group of the Department of Earth Sciences of the Barcelona Supercomputing Center – Centro Nacional de Supercomputación (BSC-CNS) has carried out a study that It shows that artificial intelligence can be very useful to obtain reliable information on the probability of exceeding the legal limits of air pollution throughout the city. The objective of the research, published in the journal Geoscientific Model Development, is to help improve air quality management in urban areas by obtaining hourly maps of NO2 concentrations at street level, as well as a quantification of their uncertainty. associate.
For the first time, the new method combines the results of CALIOPE-Urban, a unique model in Spain that allows forecasting air pollution with very high resolutions of up to ten meters, at different heights and at any point in the city, with an extensive base of urban data that includes observations from official air quality stations, low-cost sensor campaigns, information on the density of buildings, meteorological variables and a long list of geospatial information. In this way, it is possible to identify the areas of the city where it is necessary to improve the current monitoring system, helping to optimize strategies to reduce air pollution.
“The combination of the CALIOPE-Urban predictions with all this urban data using artificial intelligence allows us to improve the model, since where simulation cannot explain the spatial distribution of pollution, with machine learning we are able to correct and improve this predictionâ€, says Jan Mateu, leader of the BSC Air Quality Services team and one of the main authors of the study.
The use of automatic learning techniques (machine learning) with observational data obtained with passive dosimeters during previous campaigns represents an important advance, since the inherent uncertainties associated with air quality models are reduced due to the low density of the stations. control. In this way, a greater spatial characterization of excess air pollutants in different parts of the city is achieved.
The upper map on the left refers to the annual mean of NO2 for the year 2019, after applying the correction method presented. The central figure presents the field of uncertainty associated with the methodological correctness. The map on the right shows the probability of exceeding the legal limit of the annual average of 40 μg/m3 set by the European Commission during 2019, obtained by combining the two previous maps.
One of the main conclusions of the study, which has focused on this pilot phase in the city of Barcelona, ​​is that the district of the Catalan capital with the worst air quality is the Eixample, where 95% of its area has more than 50 % probability of exceeding the legal limit of the annual average of 40 μg/m3 of NO2 set by the European Commission (European Air Quality Directive 2008/50/EC).
“The Eixample district, the most populated in Barcelona, ​​is the most affected area of ​​the city, since the vast majority of its surface has more than a 50% probability of exceeding the legal annual NO2 limit legislated by the European Commission. Thanks to our methodology, the public Administration will be able to design and manage policies that improve air quality in urban areas, which is especially important because air pollution is the main environmental risk factor for human healthâ€, adds Ãlvaro Criado, researcher of the BSC Air Quality Services team and also one of the lead authors of the study.
