Spatiotemporal multi-graph convolutional network-based provincial-day-level terrorism risk prediction.

Abstract

Predicting terrorism risk is crucial for formulating detailed counter-strategies. However, this task is challenging mainly because the risk of the concerned potential victim is not isolated. Terrorism risk has a spatiotemporal interprovincial contagious characteristic. The risk diffusion mechanism comes from three possibilities: cross-provincial terrorist attacks, internal and external echoes, and internal self-excitation. This study proposed a novel spatiotemporal graph convolutional network (STGCN)-based extension method to capture the complex and multidimensional non-Euclidean relationships between different provinces and forecast the daily risks. Specifically, three graph structures were constructed to represent the contagious process between provinces: the distance graph, the province-level root cause similarity graph, and the self-excited graph. The long short-term memory and self-attention layers were extended to STGCN for capturing context-dependent temporal characters. At the same time, the one-dimensional convolutional neural network kernel with the gated linear unit inside the classical STGCN can model single-node-dependent temporal features, and the spectral graph convolution modules can capture spatial features. The experimental results on Afghanistan terrorist attack data from 2005 to 2020 demonstrate the effectiveness of the proposed extended STGCN method compared to other machine learning prediction models. Furthermore, the results illustrate the crucial of capturing comprehensive spatiotemporal correlation characters among provinces. Based on this, this article provides counter-terrorism management insights on addressing the long-term root causes of terrorism risk and performing short-term situational prevention.