Dynamic Trend Fusion Module for Traffic Flow Prediction

2025-01-18

AI Summary

To address the challenges of modeling spatiotemporal correlations in complex dynamic traffic scenarios and insufficient integration of dynamic and static information, this paper proposes the Dynamic Spatiotemporal Trend Transformer (DST²former). Methodologically, it introduces: (1) a novel Dynamic Trend Representation Transformer (DTRformer) that adaptively models and fuses spatiotemporal trends; (2) a cross-spatiotemporal attention mechanism to explicitly capture heterogeneous spatiotemporal dependencies; and (3) a predefined graph compression scheme that distills static topological features into a compact representation while suppressing redundancy. DST²former unifies dynamic embeddings, compressed graph representations, and multi-view dynamic feature learning. Evaluated on four real-world traffic datasets, it consistently outperforms state-of-the-art methods, achieving significant improvements in both short-term and long-term forecasting accuracy—setting new SOTA performance.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Accurate traffic flow prediction is essential for applications like transport logistics but remains challenging due to complex spatio-temporal correlations and non-linear traffic patterns. Existing methods often model spatial and temporal dependencies separately, failing to effectively fuse them. To overcome this limitation, the Dynamic Spatial-Temporal Trend Transformer DST2former is proposed to capture spatio-temporal correlations through adaptive embedding and to fuse dynamic and static information for learning multi-view dynamic features of traffic networks. The approach employs the Dynamic Trend Representation Transformer (DTRformer) to generate dynamic trends using encoders for both temporal and spatial dimensions, fused via Cross Spatial-Temporal Attention. Predefined graphs are compressed into a representation graph to extract static attributes and reduce redundancy. Experiments on four real-world traffic datasets demonstrate that our framework achieves state-of-the-art performance.

Problem

• Traffic Flow Prediction
• Logistics Transportation
• Spatial-Temporal Analysis

Innovation

• DST2former
• Dynamic-Static Integration
• Spatial-Temporal Correlation