Foundations, Surveys & Key Papers
8 entriesCore surveys and models behind urban computing.
Research Groups, Conferences & Training
6 entriesWhere research and learning happen.
Open Data & Datasets
15 entriesPublic data on mobility, population, environment and cities.
Tools, Libraries & Simulators
12 entriesSoftware for spatial analysis, visualisation and traffic simulation.
Related Technologies on This Site
17 entriesSmart cities, sensors, graph models and edge pages on this site.
Frequently Asked Questions
What is urban computing?
Urban computing is the process of acquiring, integrating and analysing data from sensors, vehicles, mobile devices and other sources in cities to understand and improve urban life. The 2014 survey by Yu Zheng and colleagues defines it as an interdisciplinary field combining computer science with transport, environment, energy and urban planning.
What data does urban computing use?
Typical sources are taxi and bike-share trips, public transit feeds, road networks from OpenStreetMap, air quality monitors, satellite imagery, mobile phone signals and open government portals such as NYC Open Data.
How is it different from a smart city?
A smart city is the broader programme of connected services and governance. Urban computing is the data science and computing layer inside it: sensing, data management, analysis and visualisation of urban data.
Which methods are common?
Spatio-temporal forecasting with graph neural networks such as STGCN and DCRNN, data fusion across sources, trajectory and mobility analysis, geospatial statistics and traffic simulation.
What tools should I start with?
Python with GeoPandas, OSMnx and PySAL covers most spatial analysis, kepler.gl and deck.gl handle visualisation, and SUMO or MATSim simulate traffic. The Geographic Data Science with Python book is a good start.