Our first challenge…
The AI4EO Air Quality & Health challenge was a joint effort of the European Centre for Medium-Range Weather Forecasts (ECMWF) and the Copernicus Atmosphere Monitoring Service (CAMS). It focused on developing AI-powered solutions to facilitate the downscaling of analyses and forecasts of surface concentrations of particulate matter (PM2.5) and nitrogen dioxide (NO2). Participants were challenged to develop new methods to downscale air quality products to a resolution that can be used at a local level to deliver surface concentration maps of PM2.5 and NO2 of a higher resolution than Sentinel-5P satellite data and the CAMS products. A quantitative and qualitative evaluation of the results was performed over the three selected Areas of Interest, namely Northern Italy, California and South Africa.
The Sentinel-5 Precursor – also known as Sentinel-5P – is the first Copernicus mission dedicated to monitoring our atmosphere. The satellite carries the Tropomi instrument to map a multitude of trace gases such as nitrogen dioxide, ozone, formaldehyde, sulphur dioxide, methane, carbon monoxide and aerosols – all of which affect the air we breathe and therefore our health, and our climate.
Why
According to the World Health Organisation, air pollution is responsible for over 7 million premature deaths annually
Better information about air pollution and reducing emissions of key pollutants such as fine particulate matter and nitrogen dioxide could save millions of lives
The Copernicus Atmosphere Monitoring Service provides global information about air pollutants
With CAMS product at a spatial resolution of about 40 km on a global scale and with a resolution of about 10 km over Europe, local applications require to downscale information to finer scales
Reducing exposure to fine particulate matter (PM2.5) is among the United Nations Sustainable Development Goals
The most successful methods could be eventually considered for benchmarking currently used methodologies