Hierarchical Clustering of Spatial Urban Data

The growth of data volume collected in urban contexts opens up to their exploitation for improving citizens’ quality-of-life and city management issues, like resource planning (water, electricity), traffic, air and water quality, public policy and public safety services. Moreover, due to the large-scale diffusion of GPS and scanning devices, most of the available data are geo-referenced. Considering such an abundance of data, a very desirable and common task is to identify homogeneous regions in spatial data by partitioning a city into uniform regions based on pollution density, mobility spikes, crimes, or on other characteristics. Density-based clustering algorithms have been shown to be very suitable to detect density-based regions, i.e. areas in which urban events occur with higher density than the remainder of the dataset. Nevertheless, an important issue of such algorithms is that, due to the adoption of global parameters, they fail to identify clusters with varied densities, unless the clusters are clearly separated by sparse regions. In this paper we provide a preliminary analysis about how hierarchical clustering can be used to discover spatial clusters of different densities, in spatial urban data. The algorithm can automatically estimate the area of data having different densities, it can automatically estimate parameters for each cluster so as to reduce the requirement for human intervention or domain knowledge.