Analysis, Integration and Visualization of Urban Data From Multiple Heterogeneous Sources

Abstract

The rapid progress of urbanization creates great challenges for urban planners. These challenges include the environment, energy consumption, transport, and other areas. The massive amount of information generated everyday in urban environments allows more precise diagnostics of the problems and helps in the design of solutions. Since such sources of information are heterogeneous and involve a large amount of data, major computational challenges arise. The objective of this work is to propose techniques and methods that allow the integration and visualization of urban data from multiple heterogeneous sources, aiming to create tools for urban data analysis, focusing mainly on transportation and transit. We propose the Urban Transit Fingerprint visualization, in which the geometry, length and duration of travels within a city can be compared, and indicators of the relative efficiency between private (individual) and public (mass) transport can be assessed. Data from Belo Horizonte and Sao Paulo, Brazil, are analyzed using the proposed technique as case studies. Results show wide discrepancies in the effort a public transit user has to make for her mobility in various regions of each city, as compared with individual travel. These results help explaining the sharp drop in the number of transit users over the last years, thus calling on urban planners to devise public policies in the search for better solutions.