Terrorism is a complex phenomenon with high uncertainty involving a myriad of dynamic known and unknown factors. It is and will remain a challenge to predict or detect terrorism outbreaks at an early stage. This research presents an alternative approach for modeling terrorism activity, one that monitors and detects space–time clusters of terrorist incidents using prospective space–time scan statistics. Such clusters provide indicators of potential outbreaks of terrorist incidents. To evaluate the effectiveness of the approach, we analyze the terrorist incidents in the Consortium for the Study of Terrorism and Responses to Terrorism's (START) Global Terrorism Database (GTD) from 1998 to 2004. Clusters of terrorist events are detected at each time stamp and life trajectories of these clusters are constructed based on their space–time relationship to each other. Through the life trajectories and trends of clusters, we demonstrate how space–time scan statistics detect terrorism outbreaks at an early stage.
Gao, Peng, and Diansheng Guo, Ke Liao, Jennifer J. Webb, Susan Cutter. 2012. "Early Detection of Terrorism Outbreaks Using Prospective Space–Time Scan Statistics." The Professional Geographer (October). http://www.tandfonline.com/doi/abs/10.1080/00330124.2012.724348#.U9EpoONdUZn