Abstract
The air quality dataset derived through air quality sensors is a major dataset used in the development of air quality prediction models, but these datasets are not available for every location of interest in the world partly due to the cost of setting up the air quality sensors. As critical as the negative effect of air pollution is, many of the air quality prediction models are limited to the location whose air quality dataset is used to develop them. Thereby leaving locations without air quality datasets to be presented with speculative air quality forecasts. This situation increases the pollution exposure risk of vulnerable groups as their decision is based on speculative and inaccurate air quality prediction. This research is to investigate alternative methodology and datasets for the prediction of air quality in locations without air quality datasets or air quality sensors installed. To achieve this, we incorporate the geospatial dataset with other datasets such as traffic dataset, weather dataset and air quality dataset of other locations in the development of an air quality prediction model capable of predicting the air quality for locations without recorded air quality datasets or air quality sensor installed. This study presents a novel approach to using geospatial datasets in the development of an air quality prediction system.

This publication has 27 references indexed in Scilit: