Data fusion and neural network combination method for air pollution level monitoring

Over the last ten years, Salamanca has been considered among the most polluted cities in Mexico, with the most important air pollutants being SO₂ and PM₁₀. Currently, in Salamanca, an environmental monitoring network (EMN) is installed in which time series of criteria pollutants and meteorological variables are obtained. Unfortunately air pollution level is computed in each monitoring station without taking into account those meteorological variables. In this paper, we propose a novel methodology to compute air pollution levels taking the meteorological variables as a decision factor by means of data fusion and neural networks. First, in preprocessing stage two feature vectors (FV_{SO 2} and FV_{PM 10}) are built for each monitoring station. Next, in data fusion stage, a representative feature vector by pollutant (RFV_{SO 2} and RFV_{PM 10}) is built with the maximum value of the three FVs. Finally, an artificial neural network (ANN) is trained with the RFV in order to classify future environmental situations. Self-organizing map (SOM) is the ANN applied. In this paper, time series of pollutant concentrations and meteorological variables are obtained from the EMN. EMN is composed for the three monitoring stations in Salamanca. Data used in this study have approved according to Proaire environmental authority standards.