The ability to forecast the concentration of air pollutants in an urban region is crucial for decision-makers wishing to reduce the impact of pollution on public health through active measures (e.g. temporary traffic closures). In this study, we present a machine learning approach applied to the forecast of the day-ahead maximum value of the ozone concentration for several geographical locations in southern Switzerland. Due to the low density of measurement stations and to the complex orography of the use case terrain, we adopted feature selection methods instead of explicitly restricting relevant features to a neighbourhood of the prediction sites, as common in spatio-temporal forecasting methods. We then used Shapley values to assess the explainability of the learned models in terms of feature importance and feature interactions in relation to ozone predictions; our analysis suggests that the trained models effectively learned explanatory cross-dependencies among atmospheric variables. Finally, we show how weighting observations helps in increasing the accuracy of the forecasts for specific ranges of ozone's daily peak values.