New Spatiotemporal Clustering Algorithms and their Applications to Ozone Pollution

Abstract

Spatiotemporal clustering is a process of grouping a set of objects based on their spatial and temporal similarities. In this paper we propose two new spatiotemporal clustering algorithms, called Spatiotemporal Shared Nearest Neighbor clustering algorithm (ST-SNN), and Spatiotemporal Separated Shared Nearest Neighbor clustering algorithm (ST-SEP-SNN), to cluster overlapping polygons that can change their locations, sizes and shapes over time. Both ST-SNN and ST-SEP-SNN are based on well established generic density-based clustering algorithm Shared Nearest Neighbor (SNN), which can find clusters of different sizes, shapes, and densities in high dimensional data. New similarity functions are proposed for computing spatiotemporal similarities between spatiotemporal polygons as well. We evaluate and demonstrate the effectiveness of our approaches in a case study involving ozone pollution events in the Houston-Galveston-Brazoria (HGB) area. The experimental results show that both ST-SNN and ST-SEP-SNN algorithms can find interesting spatiotemporal patterns from ozone pollution data.