Forecasting PM10 in metropolitan areas: Efficacy of neural networks.

Deterministic photochemical air quality models are commonly used for regulatory management and planning of urban airsheds. These models are complex, computer intensive, and hence are prohibitively expensive for routine air quality predictions. Stochastic methods are becoming increasingly popular as an alternative, which relegate decision making to artificial intelligence based on Neural Networks that are made of artificial neurons or 'nodes' capable of 'learning through training' via historic data. A Neural Network was used to predict particulate matter concentration at a regulatory monitoring site in Phoenix, Arizona; its development, efficacy as a predictive tool and performance vis-à-vis a commonly used regulatory photochemical model are described in this paper. It is concluded that Neural Networks are much easier, quicker and economical to implement without compromising the accuracy of predictions. Neural Networks can be used to develop rapid air quality warning systems based on a network of automated monitoring stations.

Air pollution impact assessment on agroecosystem and human health characterisation in the area surrounding the industrial settlement of Milazzo (Italy): a multidisciplinary approach.

In order to evaluate the impact of atmospheric pollutants emitted by the industrial settlement of Milazzo (Italy) on agriculture, sulphur dioxide and ozone levels in air were monitored and the data were used to estimate yield losses of the most widespread cultures. Trace element concentrations in crops and soils were also detected and metabolic profiles of soil microbial communities were considered. Vibrio fischeri test was used to appraise airborne pollutant ecotoxicity and epidemiological studies on causes of death distribution were carried out to characterize health state of people living in the area. All the sampling points were selected in farms on the basis of a theoretical meteo-diffusive model of industrial air pollutants. Experimental SO2 and O3 values mainly exceeded the threshold established by Italian and EU regulations to protect vegetation and they correspond to estimated significant crop losses. Conversely toxic element residues in soils and in agroalimentary products were generally lower than the fixed values. SO2 and O3 concentrations, toxic element contents and ecotoxicity levels of airborne pollutants were not related only to industrial site emissions, while the fluctuations on metabolic profiles of soil microbial communities seem to agree with the predicted deposition of xenobiotic compounds from the industrial plants. The epidemiological study evidenced a better health state of populations living in the investigated area than in the Messina province and the Sicily region but, inside the area, males living in the municipalities closest to the industrial settlement exhibited a worst health state than those in the very far ones.