Ozone pollution in outdoor environments poses serious risks to public health and ecosystems, with adverse effects ranging from respiratory issues to crop damage. Accurate estimation of ozone concentrations is crucial for effective air quality management and regulatory compliance. Traditional monitoring methods often rely on direct measurements from physical sensors, which can be limited in availability and coverage. The aim of the work is to develop a prediction algorithm based on virtual sensor approach, capable of estimating the ozone concentration in outdoor environments, exploiting the information provided by a set of indirect measurements, using machine learning techniques and direct data-driven design methodologies. The thesis, in cooperation with ARPA Lombardia, will employ Regional Air Quality Monitoring station time series data.
The student will benefit from synergies with LEAP – Laboratorio Energia e Ambiente Piacenza, already active on several projects on the topic.
Area di competenza
Emissions and Air Quality
Responsabili
Fredy Ruiz (fredy.ruiz@polimi.it) – Politecnico di Milano (DEIB)
Senem Ozgen (senem.ozgen@polimi.it) – LEAP
Competenze richieste
- Capability to formulate and solve filtering and state estimation problems
- Capability to implement and validate numerical simulations of dynamic systems
- Understanding of signal processing and systems theory
Desiderable:
- Familiarity with Matlab-Simulink and/or Python
- Experience with virtual sensors or machine learning
- Familiarity with optimization tools (CVX, Casadi, …)
Data di inizio presunta
January / February 2025
Durata
9 months. Full thesis only.
Maggiori informazioni
Weekly meeting online or in presence.