Interactive visual cluster detection in large geospatial datasets based on dynamic density volume visualization

Abstract

The emerging spatial big data (e.g. detailed spatial trajectories, geo-referenced social media data) provide tremendous opportunities for GIScientists and geographers. However, their large volume also poses challenges to existing spatial data analytical techniques (including visual analytical techniques). This article presents an interactive visual approach to detect clusters from those emerging data sets based on dynamic density volume visualization in a three-dimensional space (two spatial dimensions plus a third temporal or thematic dimension of interest). Cluster can be visually discovered through dynamic adjustment of density to colour/opacity mapping and extracted through flexible selection tools. The approach was tested on a large simulated data-set and a spatial trajectory data-set. The results show that the approach can overcome the visual clotting problem in traditional visualization tools caused by large data volume and facilitate the involvement of domain knowledge in analysis. It can effectively support visual cluster detection in the emerging large geospatial data sets.

Keywords:

• big data
• geovisual analytics
• social media
• trajectory
• spatial cluster

Acknowledgements

This work was supported by the National Natural Science Foundation of China [grant number 41431177], US National Institute of Health [grant number 1R03AI090465], Natural Science Research Program of Jiangsu [grant number 14KJA170001], National Basic Research Program of China [grant number 2015CB954102] and PAPD and supports to A-Xing Zhu through the Vilas Associate Award, the Hammel Faculty Fellow Award, the Manasse Chair Professorship from the University of Wisconsin-Madison, and the “One-Thousand Talents” Program of China are greatly appreciated.

Disclosure statement

No potential conflict of interest was reported by the authors.