AI Summary & Key Takeaways
AI InsightUnder these conditions, PM 10 accumulation is driven bylocal anthropogenic emissions ascribing to two main sources: heating plants, responsible of emissions of primaryPM 10 (mostly PM 2.5 , likely resulting from wood and biomass burning); and road traffic (basically diesel ve-hicles), mainly responsible of emissions of secondary PM 10 precursors (mostly NO x ), and secondly of primaryPM 10 emissions.The SOM analysis clearly indicated that PM 10 most critical conditions are driven by the secondary ratherprimary PM 10 component.
📌 3 Key Takeaways
Özet
A linear and an artificial neural network (ANN) statistical model have been developed and validated for short-term forecasting of PM 10 hourly concentrations in the city of Brescia (Italy). PM 10 observed concentrations werebiased by less than 1% by each model, though the ANN outperformed the linear model, as exhibiting NRMSE of0.48 vs. 0.53, and r 2 of 0.57 vs. 0.48. The self-organizing maps (SOMs) showed that both models predictionsexhibit the same clustering as the observations, with the ANN at worst capable of under-estimating clusteredPM 10 peak concentrations by 5.8 μg/m 3 .In Brescia, PM 10 most critical conditions were detected in wintertime in the early morning or late afternoonunder unfavourable meteorological conditions, i.e. reduced advection enhancing PM 10 stagnation, and lack ofprecipitations capable of reducing PM 10 resuspension. Under these conditions, PM 10 accumulation is driven bylocal anthropogenic emissions ascribing to two main sources: heating plants, responsible of emissions of primaryPM 10 (mostly PM 2.5 , likely resulting from wood and biomass burning); and road traffic (basically diesel ve-hicles), mainly responsible of emissions of secondary PM 10 precursors (mostly NO x ), and secondly of primaryPM 10 emissions.The SOM analysis clearly indicated that PM 10 most critical conditions are driven by the secondary ratherprimary PM 10 component.