Urban Air Pollution Pattern Mining Using an Extended Spatial Co-location Data Mining Method

Air pollution in cities is one of the most problems that effects on human health, environment, economy, urban management and etc. urban managers to overcome to this problem, should determine affecting parameters and also the way that they impact on air pollution to arrange necessary plans for it. Different researches have been assessed parameters such as meteorology, traffic and topography impacts on the air pollution. Identification of affecting parameters on air pollution in urban regions using co-location pattern mining can help to solve this problem. Co-location pattern represents a subset of spatial objects that their instances usually are in close proximity. Existing methods with shorthcomings such as applying only one feature-type, considering spatial relationships explicitly as input data and extracting patterns without any emphasis on a specific object aren’t appropriate to applications such as air pollution. Then, in the present research developed a new co-location pattern mining model so that it can handel mentioned shortcomings. In this research tried to consider affects of all three before mentioned parameters simultaneously on air pollution by extracting prevalent patterns. In this literature to develop the mentioned model, we defined a framework for a data mining problem. As there was a gap in existing literature for considering different feature types, new metrics have been defined to compute the participation ratio for all point, line and polygon data. Actually, the applied metric for point data is the available one but the other ones for line and polygon data have some extensions based on neighborhood to compute these metrics. As the air pollution is a serious problem for Tehran, the developed model implemented and tested on part of Tehran’s data. To apply the proposed method, we classified each of the studied parameters to three different classes (low, normal, high) based on their physical characteristics. The data of 4 days in Farvardin, Tir, Mehr and Dey months selected and used to first, check repeatability of results and second, based on changes in seasons, control the validity of the proposed model. The input value for neighborhood radius is 1500 meter and for prevalence threshold is 0.5. The neighborhood radius is selected based on the average distances between air pollution stations and meaningfully of parameters changes. Also, the prevalence threshold was selected to find patterns which at least half of its instances participate in the pattern. The assessed results of extracted patterns first show the ability and correctness of our proposed model and second represent that medium and high air pollutions produce meaningful patterns with low traffic volume, low wind speed and also low topography. Also, their attitude is towards central regions of our case, region 6 of Tehran. Finally, it is necessary to mention that the air pollution is a spatio-temporal problem and in addition to spatial dimension, we should have an attention to temporal aspect. But in this research, the emphasis is based on spatial extension of model to apply for all feature types. Extending the proposed model to mine spatial and temporal patterns simultaneously is the goal of researchers.