A neural net-air dispersion model validation study using the Indianapolis urban data set
It is presented an integrated model composed by a dispersion model and a Neural Net (NN). The NN uses the concentrations predicted by the an analytical dispersion model as input variables of the net. This methodology was validated using Indianapolis urban data set where releases from an elevated emission source were considered. An improvement of performances is shown when the neural network is added downstream to the dispersion model. Tests reveal the system is able to reproduce the expected behaviour of pollutant concentration, with the downwind distance and stability of the atmosphere in urban area.
Keywords: air pollution, dispersion modelling, mixed models, neural networks, calibration data set, air quality, pollutant dispersion