Accurate prediction of ground-level ozone concentrations is crucial for public health and environmental protection. Air quality monitoring processes require very high spatial resolution information for several hazardous air pollutants, as well as for those meteorological conditions that most influence air quality. The available datasets usually refer to long time series recorded irregularly over the area of interest or at a coarse spatial resolution. In this context, effective modeling and prediction methods are needed to forecast ozone levels in a high spatial resolution. In the chapter, the blind source separation-based approach is carried out to model and predict ground-level ozone concentrations in a multivariate framework.