Abstract: Forecasting of air pollutants is an important area of research in view of the current concerns regarding environment. In particular, air quality is deteriorating due to emissions increasing, particularly in urban locations. . In view of the health hazards posed by increasing air pollution, it will be useful to have a model that can predict the level of atmospheric pollutants and a geospatial interpolation approach to forecast the air pollutants over the whole domain. This paper presents an integrated model using Artificial Neural Networks and Kriging to predict the level of air pollutants at various locations in Mumbai and Navi Mumbai using past data available from meteorological department and Pollution Control Board. The proposed model is implemented and tested using MATLAB for ANN an R for Kriging and the results are presented.

Keywords: Artificial Neural Networks, Kriging, Air Pollution, Meteorological data.