Search

Artificial neural networks are functional alternative techniques in modelling the intricate vehicular exhaust emission dispersion phenomenon. Pollutant predictions are notoriously complex when using either deterministic or stochastic models, which explains why this model was developed using a neural network. Neural networks have the ability to learn about non-linear relationships between the used variables. In this paper a recurrent neural network (Elman model) based forecaster for the prediction of daily maximum concentrations of SO2, O3, PM10, NO2, CO in the city of Palermo is proposed. The effectiveness of the presented forecaster was tested using a time series recorded between 1 January 2003 to 31 December 2004 in eight monitoring stations in urban area of Palermo (Italy). Experimental trials show that the developed and tuned model is appropriate, giving small values of root mean square error (RMSE) , mean absolute error (MAE) and mean square error (MSE). In addition, the related correlation coefficient ranges from 0.72 to 0.97 for each forecasted pollutant, underlying a small difference between the forecasted and the measured values. The above results make the proposed forecaster a powerful tool for pollution management systems.

A steady-state bi-dimensional turbulent diffusion equation was studied to find the concentration distribution of a pollutant near the ground. We have considered the air pollutant emitted from an elevated point source in the lower atmosphere in adiabatic conditions. The wind velocity and diffusion coefficient are given by power laws. We have found analytical solutions using or the Lie Group Analysis or the Method of Separation of Variables. The classical diffusion equation has been modified introducing the falling term with non-zero deposition velocity. Analytical solutions are essential to test numerical models for the great difficulty in validating with experiments.

Indoor air quality near the industrial site is tightly joined to pollutant concentration level, since outdoor pollution heavily influences air quality and, consequently, inhabitants health. A pollution management system is essential for health protection. Automatic air quality management systems have became an important research issue with strong implications for inhabitants’ health. In this paper an automatic forecaster based on neural networks for SO 2 concentration prevision is proposed. The analyzed area covers different small towns near the industrial site of Priolo, in the south of the world. Among these towns, Melilli was the first town in Italy that was evacuated for high level of pollutant concentrations. In the paper, a traditional stochastic method and several neural models are also compared. Overall, the results of the simulation show that the employment of a neural network forecaster is the most efficient tool to follow the big variations of pollutants concentration when thermal inversion height is taking place. In particular, an Elman neural network shows interesting results in 1, 2, and 3 h ahead forecasting of SO 2 concentration, doing the proposed forecaster a powerful tool for both pollution management and health warning systems.

According to the protocols for the reduction of the production of the gases responsible of the greenhouse effect, it makes necessary to develop systems able to forecast and to evaluate such gases. The dump of Bellolampo, situated in proximity of the urban area in Palermo, is a source of CO2 and CH4. It was officially created in the eighties and only some years later it was decided to convert it into a controlled landfill, soon becoming a catch basin of refuse for a large hinterland constituted by approximately 50 small towns. The city of Palermo has been equipped with a network of weather and air-quality stations far monitoring the main components that are responsible for atmospherlc pollution. The network consists of 10 fixed stations located both in peripheral and centrai parts of the city. The gases produced by the landfill, under particular meteorologica! conditions, reach the nearby inhabited centre, making to record many peak events, dangerous for the population health. The purpose of this research is to develop a pure predictive model, using an Artificial Neural Network (ANN), to forecast, with a lead time of a dai, the CH4 concentration in the site of Palermo and to help the administrations to rationalize the preventive intervention to reduce the occurrence of this pollutant. The mode! uses an available time series which was recorded by the network of monitoring stations, on the urban area of Palermo, far the period 2003-2004. This study has some important implications for health warning systems environmental management in places with high pollution concentration

Many landfills for urban solid waste have been developed in sites very close to urbanised areas thus exposing the population to various dangerous pollutants. The landfill of "Bellolampo", located a few kilometres from the city ofPalermo is one of these. It was officially created in the eighties and only some years later it was decided convert it into a controlled landfill, soon becoming a catch basin of refuse for a large hinterland constituted by approximately 50 small towns. In recent years the city of Palermo has been equipped with a network of weather and air-quality stations for monitoring the main components that afe responsible for atmospheric pollution; it consists of 10 fixed stations located both in peripheral and centraI parts ofthe city. Four ofthem afe able to measure the CH4 concentration. In this work an analysis of the meteorological data and of the CH4 concentrations, acquired downwind the emission source, has been carried out. A dispersion Gaussian model of pollutants was applied in order to estimate the amount of the CH4 released by the landfill. The estimated values were validated by utilising the methane concentration values recorded by the biogas capture system installed in the landfill area.

In this paper a new method is presented for the evaluation of methane concentration near urban sites. The work is based on field measurements taken for a lon period of time on selected sites of the town of Palermo. The main finding of the work is that the landfill seriously affects the air quality of the town, at least around the selected sites

In this paper the first results produced by an Elman neural network for hourly SO2 ground concentration forecasting are presented. Time series has been recorded between 1998 and 2001 and are referred to a monitoring station of SO2 in the industrial site of Priolo, Syracuse, Italy. Data has been kindly provided by CIPA (Consorzio Industriale per la Protezione dell'Ambiente, Siracusa, Italia). Time series parameters are the horizontal and vertical wind velocity, the wind direction, the stability classes of Thomas, the base level of the layer of the atmospheric stability, the gradient of the potential temperature and the difference of the potential temperature of reference.

Nowadays, the influence of the vehicular traffic on the degradation of urban atmosphere is focused on by researchers belonging to different fields in view of its prime importance for public health. The control of exhaust gases emission is primary in order to keep air pollution below the specified limits of the laws in force. In previous works the “medium car” characterises a country in modelling a pollutant in urban areas. This is the central parameter of a forecasting model proposed by Pignato and LoMastro, of pollutant concentration near urban cross-road with traffic lights in continue queue and platoon flow. The proofs have been carried on two classes of displacement vehicles and four classes of age considering the circulating park. We have found the trend of the pollutants emission vs. rpm in the phase of “acceleration” and in the phase of “stopping and deceleration”. Applying the model proposed it is possible forecast the maximum concentration of the considered pollutant in platoon flow near urban cross road with traffic light, without the bus presence. The "medium car", is the fictitious vehicle polluting like that real one of the platoon most probable composition. In steady-state conditions, the vehicular traffic is governed by stoppages at crossroad assuming the pattern of a "platoon flow", or crossing by "platoons". Any vehicle of the platoon undergoes the following kinematics phases: entering the queue, deceleration within the queue, waiting and starting from rest. With the laboratory equipment of AMAT" Azienda Municipalizzata AutoTrasporti" of Palermo, supplied with a torque dynamometer and necessary instrumentation, we measured the emission of some pollutants, as CO, NOx, emitted from vehicles submitted to the phases and conditions above described