Spatiotemporal Prediction of Secondary Crashes by Rebalancing Dynamic and Static Data with Generative Adversarial Networks

TL;DR

This paper introduces VarFusiGAN-Transformer, a novel hybrid model that addresses data imbalance in secondary crash prediction by generating high-fidelity data and jointly predicting crash occurrence and distribution using LSTM and GAN techniques.

Contribution

The study presents a new integrated model combining GANs and LSTM to improve secondary crash data generation and joint prediction of crash occurrence and spatiotemporal distribution.

Findings

Superior data generation fidelity compared to existing methods.

Enhanced prediction accuracy for secondary crashes.

Effective handling of dynamic and static feature coexistence.

Abstract

Data imbalance is a common issue in analyzing and predicting sudden traffic events. Secondary crashes constitute only a small proportion of all crashes. These secondary crashes, triggered by primary crashes, significantly exacerbate traffic congestion and increase the severity of incidents. However, the severe imbalance of secondary crash data poses significant challenges for prediction models, affecting their generalization ability and prediction accuracy. Existing methods fail to fully address the complexity of traffic crash data, particularly the coexistence of dynamic and static features, and often struggle to effectively handle data samples of varying lengths. Furthermore, most current studies predict the occurrence probability and spatiotemporal distribution of secondary crashes separately, lacking an integrated solution. To address these challenges, this study proposes a hybrid model named VarFusiGAN-Transformer, aimed at improving the fidelity of secondary crash data generation and jointly predicting the occurrence and spatiotemporal distribution of secondary crashes. The VarFusiGAN-Transformer model employs Long Short-Term Memory (LSTM) networks to enhance the generation of multivariate long-time series data, incorporating a static data generator and an auxiliary discriminator to model the joint distribution of dynamic and static features. In addition, the model's prediction module achieves simultaneous prediction of both the occurrence and spatiotemporal distribution of secondary crashes. Compared to existing methods, the proposed model demonstrates superior performance in generating high-fidelity data and improving prediction accuracy.