A Bayesian weather–driven spatio–temporal model for PM10 in Lombardy

Po Valley is well known to be one of the most polluted areas in Italy, because of its large population density, its shape and climate. Thus, there is an obvious interest in monitoring the air quality in several stations scattered across the whole territory. In this work, we develop a Bayesian spatio–temporal model describing the PM10 pollution in Lombardy to assess how station features and weather factors affect the PM10 concentration. We will rely on Stan for posterior inference