FLORIA

Better detection of pollution events linked to natural disasters and human activities is becoming a major challenge. Against this backdrop, the FLORIA project is proposing an innovative statistical approach based on artificial intelligence coupled with satellite data, which will provide guidance to the various players responsible for managing the problems associated with climate change.

[fr]

Using space to anticipate air pollution. © Thales

Flexible algORIthm for the monitoring of Air pollution based on artificial intelligence and satellite observations

Overview

It is now well established that pollutant emissions are a major problem for the climate and our health. For the past two decades, level 2 satellite products (instantaneous products acquired during a single satellite pass) have been used to try and extract information on the concentration of pollutants at the surface. But the complex links between the data measured by the satellite from its orbit and the concentration of pollutants at the surface make these methods difficult to generalize. To take account of this complexity, numerical models such as CHIMERE (transport chemistry) and MOCAGE (large-scale atmospheric chemistry) used in the Prév'Air and CAMS platforms can simulate the atmosphere, the physico-chemistry and the transport of gaseous pollutants and fine particles, but they require significant computing resources, which makes them difficult to access.

To overcome these various difficulties, our innovative idea involves tackling the complexity of the physico-chemical model using a statistical approach based on artificial intelligence (surrogate model) coupled with satellite data. The added value of this solution is to offer continuous monitoring of air quality on a large scale, including areas with little or no in-situ sensor coverage, using satellite products from a wide variety of sensors (geostationary and polar orbiting).

Among the different types of pollutants, we propose to characterize and monitor PM10 concentrations at the surface, in order to respond to the feedback loop initiated by climate change:

The increase in extreme weather events (heatwaves) and natural disasters (fires) is changing the mechanisms by which PM10 is formed, transported and deposited, and therefore the type of pollution events.
This modulation of PM10 pollution events and its associated radiative effects in turn influences climate change.

Application site(s)

Czech Republic: Prague, Brno and Pilsen regions

Data

Satellite

Sentinel-3, L2 AOT products
Landsat-8 and Landsat-9: L2 surface temperature

Autres

In-situ PM10 measurements by air quality monitoring agencies
Measurements from national weather stations

Results – Final product(s)

The product consists of a database of PM10 surface concentrations in the territory concerned. It includes data processing for the 6 years of Sentinel-3, from 2019 to 2024, on a daily basis, at the satellite's native spatial resolution (4 km x 4 km).

👉 A monthly map of PM10 concentrations in Europe will be available on the SCO website for distribution to the community..

References

J. Staufer, C. Rakotondrainibe, J.-C. Péré, B. Gratadoux, J. Cuesta, G. Dufour, S. Tanguy, L. Chaumat and L. Le Barbier (2024) : Monitoring of gound-level pollutants concentrations from space, ESA ATMOS Conference, 1-4 July 2024, Bologna Italy, ATMOS 2024