Towards Resilient Transportation: A Conditional Transformer for Accident-Informed Traffic Forecasting
This work addresses the problem of improving traffic prediction accuracy for urban planning and management by integrating accident and regulation data, representing an incremental advancement through a novel method for a known bottleneck in spatio-temporal modeling.
The paper tackles the challenge of accurate traffic forecasting by addressing the complex influence of external factors like accidents and regulations, proposing ConFormer, a conditional transformer framework that integrates graph propagation with guided normalization to dynamically adjust spatial and temporal relationships, achieving state-of-the-art performance with lower computational costs and reduced parameters compared to STAEFormer.
Traffic prediction remains a key challenge in spatio-temporal data mining, despite progress in deep learning. Accurate forecasting is hindered by the complex influence of external factors such as traffic accidents and regulations, often overlooked by existing models due to limited data integration. To address these limitations, we present two enriched traffic datasets from Tokyo and California, incorporating traffic accident and regulation data. Leveraging these datasets, we propose ConFormer (Conditional Transformer), a novel framework that integrates graph propagation with guided normalization layer. This design dynamically adjusts spatial and temporal node relationships based on historical patterns, enhancing predictive accuracy. Our model surpasses the state-of-the-art STAEFormer in both predictive performance and efficiency, achieving lower computational costs and reduced parameter demands. Extensive evaluations demonstrate that ConFormer consistently outperforms mainstream spatio-temporal baselines across multiple metrics, underscoring its potential to advance traffic prediction research.