Extracting long-term spatiotemporal characteristics of traffic flow using attention-based convolutional transformer

Abstract

Predicting traffic flow is vital for optimizing transportation efficiency, reducing fuel consumption, and minimizing commute times. While artificial intelligence tools have been effective in addressing this, there have been some difficulties in processing spatial and temporal data. Current transformer-based methods, although cutting-edge for traffic prediction, encounter challenges with handling long sequences and capturing temporal relations effectively. Addressing these, the research introduces a model combining multi-scale attention modules within transformer layers. This model employs spatio-temporal transformer blocks, enriched with multi-scale convolutional attention mechanisms, allowing for a deeper understanding of temporal and spatial traffic patterns. This unique attention mechanism enhances data feature interpretation, leading to heightened prediction precision. The tests on extensive traffic datasets showcase the model's prowess in capturing both local and global traffic features, resulting in superior traffic status predictions. In summary, the innovative model offers an efficacious approach to long-sequence traffic data learning and temporal relationship extraction, setting a new benchmark in traffic flow prediction accuracy.