Prediction of Particulate Matter Concentrations Using Artificial Neural Network

Mill tailings at Kolar Gold Fields are creating particulate pollution on air environment. In the previous study, multiple regression models were developed for the prediction of particulate matter concentrations using data of meteorological parameters (wind speed, wind direction, temperature, humidity and solar radiation) and particulate matter (PM10 and TSP) monitored in different seasons[1]. Artificial neural network is an excellent predictive and data analysis tool for the evaluation of air pollutants. Therefore, the data were used for the development of neural network models. During development of models, the values 0.02, 0.5 and 0.7 were used as target error, learning rate and momentum respectively. Three hidden layers were used to obtain acceptable values. Performance of the models was evaluated using those sets of data which were not used during learning of neural network. Architecture of developed networks, number of hidden neurons and weights, normalised and relative error, importance and sensitivity, etc have been discussed in this paper.