Beyond Visualisation of Dynamic City Data: Supporting Data-driven City Planning and Decision-making Processes

Abstract

Cities are complex systems shaped by numerous simultaneous dynamic processes. With the development in new technologies, we can now gather, use and analyse the dynamic urban data alongside the conventional static or semi-static data to better understand these processes and city’s everyday functioning. Although recent studies have focused on analysing urban big data, the attempts often propose means for data visualising, but fall short in data interpretation and guidance. In response, this paper outlines part of the larger study done in Singapore to systematically approach the abundant urban big data and develop an alert system for the city officials and agencies on the underlying anomalies in the city functioning. We outline a comprehensive framework and real-time “DataCube-CityScan” platform that harnesses on dynamic economic, societal, environmental, health and attitudinal data available in Singapore, such as people movement and behaviour, use of public transport, driving behaviour, park use, shopping behaviour, healthcare centre visits, etc. The types of information gathered are of different temporal basis, thus representing the velocity of changes in the pulse of city areas of different granularities. We harness on GIS, AI and isolation forest analyses to identify specific trends and anomalies/outliers in real-time and alert city officials to respond, monitor changes, plan their actions and maximise their resources timely. While the platform depends on data accuracy and timely updating, by interlinking real-time analysis, trend visualisations and supporting spatial and non-spatial information, it shows great capacity of guiding planning authorities’ decision-making processes, strategy- and policy-making.