4D GIS and Prediction

Mark Altaweel


For the last two decades, GIS technologies have increasingly been used to incorporate not only spatial relationships but also analyzing and visualizing space across time. Spatial-temporal GIS, or 4D GIS, has, in particular, become essential in areas where GIS is needed for predicting dimensions across time. For example, infrastructure monitoring needs to analyze where and when vulnerabilities may arise in infrastructure due to depletion or events.[1]

Examples of 4D GIS

These aspects have made 4D GIS increasingly needed as a real-time platform that also offers not just current monitoring of events but can take input or data gathered and predict what could happen as a type of forecasting tool. As an example, GPS data may indicate a current path for a vehicle, but knowing where that vehicle is likely to go would require knowledge perhaps about past behavior or other attributes that enable prediction to be possible. For many current applications, current methods include fuzzy logic or using statistical probability (e.g., Bayesian modeling) where events can be predicted and displayed across time of when a given event is predicted.[2] Key to prediction is having access to large sets of data, where history of given locations or objects within given settings can be provided to enable predictive techniques. Efficiency data techniques, such as change of difference method, allow GIS to only update spatial data where changes are detected rather than the entire map or spatial display. Additionally technology incorporate generative spatial-temporal data allow real time integration of time and spatial data that can be data mined through built in or machine learning techniques such as using neural networks.[3] What these technologies are enabling is a future where GIS will increasingly be used as a means to provide forecasts for a range of events, from weather modeling to infrastructure development and management.


[1] For information on how 4D GIS is used with infrastructure monitoring, see:  Iwamura, Kazuaki, Keiro Muro, Nobuhiro Ishimaru, and Manabu Fukushima. 2011. “4D-GIS (4 Dimensional GIS) as Spatial-Temporal Data Mining Platform and Its Application to Managementand Monitoring of Large-Scale Infrastructures.” In , 38–43. IEEE. doi:10.1109/ICSDM.2011.5969001.

Free weekly newsletter

Fill out your e-mail address to receive our newsletter!

[2] For more information on predictive capacities of 4D GIS, see: Jjumba, Anthony, and Suzana Dragićević. 2016. “Towards a Voxel-Based Geographic Automata for the Simulation of Geospatial Processes.” ISPRS Journal of Photogrammetry and Remote Sensing, February. doi:10.1016/j.isprsjprs.2016.01.017.

[3] For an example of generative methods for GIS,  see:  Jjumba, Anthony, and Suzana Dragicevic. 2015. “Integrating GIS-Based Geo-Atom Theory and Voxel Automata to Simulate the Dispersal of Airborne Pollutants: Geo -Atom Theory and Voxel Automata to Simulate Dispersal of Airborne Pollutants.” Transactions in GIS 19 (4): 582–603. doi:10.1111/tgis.12113.

Related 4D GIS Articles


Photo of author
About the author
Mark Altaweel
Mark Altaweel is a Reader in Near Eastern Archaeology at the Institute of Archaeology, University College London, having held previous appointments and joint appointments at the University of Chicago, University of Alaska, and Argonne National Laboratory. Mark has an undergraduate degree in Anthropology and Masters and PhD degrees from the University of Chicago’s Department of Near Eastern Languages and Civilizations.