Spatio-temporal estimation of air quality parameters using linear genetic programming

Air quality planning and management requires accurate and consistent records of the air quality parameters. Limited number of monitoring stations and inconsistent measurements of the air quality parameters is a very serious problem in many parts of India. It becomes difficult for the authorities to plan proactive measures with such a limited data. Estimation models can be developed using soft computing techniques considering the physics behind pollution dispersion as they can work very well with limited data. They are more realistic and can present the complete picture about the air quality. In the present case study spatio-temporal models using Linear Genetic Programming (LGP) have been developed for estimation of air quality parameters. The air quality data from four monitoring stations of an Indian city has been used and LGP models have been developed to estimate pollutant concentration of the fifth station. Three types of models are developed. In the first type, models are developed considering only the pollutant concentrations at the neighboring stations without considering the effect of distance between the stations as well the significance of the prevailing wind direction. Second type of models are distance based models based on the hypothesis that there will be atmospheric interactions between the two stations under consideration and the effect increases with decrease in the distance between the two. In third type the effect of the prevailing wind direction is also considered in choosing the input stations in wind and distance based models. Models are evaluated using Band Error and it was observed that majority of the errors are in +/-1 band.