A linear and an artificial neural network (ANN) statistical model have been developed and validated for short-term forecasting of PM₁₀ hourly concentrations in the city of Brescia (Italy). PM₁₀ observed concentrations were biased by less than 1% by each model, though the ANN outperformed the linear model, as exhibiting NRMSE of 0.48 vs. 0.53, and r² of 0.57 vs. 0.48. The self-organizing maps (SOMs) showed that both models predictions exhibit the same clustering as the observations, with the ANN at worst capable of under-estimating clustered PM₁₀ peak concentrations by 5.8 μg/m³.

In Brescia, PM₁₀ most critical conditions were detected in wintertime in the early morning or late afternoon under unfavourable meteorological conditions, i.e. reduced advection enhancing PM₁₀ stagnation, and lack of precipitations capable of reducing PM₁₀ resuspension. Under these conditions, PM₁₀ accumulation is driven by local anthropogenic emissions ascribing to two main sources: heating plants, responsible of emissions of primary PM₁₀ (mostly PM_2.5, likely resulting from wood and biomass burning); and road traffic (basically diesel vehicles), mainly responsible of emissions of secondary PM₁₀ precursors (mostly NO_x), and secondly of primary PM₁₀ emissions.

The SOM analysis clearly indicated that PM₁₀ most critical conditions are driven by the secondary rather primary PM₁₀ component.