Urban Traffic Accident Risk Prediction Revisited: Regionality, Proximity, Similarity and Sparsity

TL;DR

This paper introduces a novel hierarchical spatio-temporal network for urban traffic accident risk prediction that effectively considers regional background, spatial proximity, semantic similarity, and sparsity, demonstrating superior performance on real datasets.

Contribution

The paper proposes a multi-granularity hierarchical model incorporating remote sensing data and novel encoding and attention mechanisms for improved accident risk prediction.

Findings

Outperforms state-of-the-art methods on real datasets.

Effectively captures regional background and spatial-temporal correlations.

Addresses data sparsity with hierarchical risk prediction tasks.

Abstract

Traffic accidents pose a significant risk to human health and property safety. Therefore, to prevent traffic accidents, predicting their risks has garnered growing interest. We argue that a desired prediction solution should demonstrate resilience to the complexity of traffic accidents. In particular, it should adequately consider the regional background, accurately capture both spatial proximity and semantic similarity, and effectively address the sparsity of traffic accidents. However, these factors are often overlooked or difficult to incorporate. In this paper, we propose a novel multi-granularity hierarchical spatio-temporal network. Initially, we innovate by incorporating remote sensing data, facilitating the creation of hierarchical multi-granularity structure and the comprehension of regional background. We construct multiple high-level risk prediction tasks to enhance model's ability to cope with sparsity. Subsequently, to capture both spatial proximity and semantic similarity, region feature and multi-view graph undergo encoding processes to distill effective representations. Additionally, we propose message passing and adaptive temporal attention module that bridges different granularities and dynamically captures time correlations inherent in traffic accident patterns. At last, a multivariate hierarchical loss function is devised considering the complexity of the prediction purpose. Extensive experiments on two real datasets verify the superiority of our model against the state-of-the-art methods.