Doctoral Study Uses AI and Satellite Imagery to Enhance Finland’s Air‑Quality Monitoring

Andrea Porcheddu, who holds an MSc in Technical Physics, is set to defend his doctoral thesis at the Faculty of Science, Forestry and Technology on the Kuopio campus, presenting a novel approach to monitor air quality through artificial intelligence and satellite observations.

The research combines satellite‑derived atmospheric particle readings with information from ground‑based stations, using deep‑learning algorithms to forecast pollutant levels at a spatial resolution finer than that achievable with conventional remote‑sensing methods. By training the model to detect patterns in the satellite pictures, it can produce near‑real‑time air‑quality maps even where monitoring stations are scarce.

Enhanced coverage is crucial since existing air‑quality networks depend largely on stationary monitors that are unevenly spaced, resulting in many rural and remote zones being poorly represented. Precise, high‑resolution data are vital for public‑health warnings, city planning and meeting European Union air‑quality regulations, which seek to lower exposure to pollutants associated with cardiovascular and respiratory illnesses.

The thesis taps into a wider transition in environmental monitoring, where drawbacks of satellite data—like coarse resolution and cloud interference—are being mitigated by machine‑learning methods. Scientists across the globe have shown that neural networks can bridge data gaps, adjust biases and extrapolate observations, and Porcheddu’s study contributes a Finnish viewpoint to this expanding domain.

The Faculty of Science, Forestry and Technology in Kuopio offers a multidisciplinary setting that unites physics, remote sensing and data science, furnishing the academic backbone for initiatives that link theory with practice. The results are anticipated to foster partnerships with national bodies and may guide the incorporation of the technique into the European Copernicus programme, which delivers continuous satellite data for environmental monitoring.

Future directions of the work suggest expanding the model to additional pollutants like nitrogen oxides and ozone, and scaling the system to span broader European territories. Widespread adoption could improve the speed and accuracy of air‑quality forecasts, aiding policymakers and communities in addressing pollution issues more efficiently.