MM-STFlowNet: A Transportation Hub-Oriented Multi-Mode Passenger Flow Prediction Method via Spatial-Temporal Dynamic Graph Modeling

2025-04-08

AI Summary

Addressing the challenges of modeling dynamically coupled multimodal passenger flows and achieving accurate short-term prediction in large-scale integrated transportation hubs, this paper proposes a hub-oriented dynamic spatiotemporal graph modeling framework. We innovatively design the Spatiotemporal Dynamic Graph Convolutional Recurrent Network (STDGCRN), which jointly integrates dynamic graph convolution, temporal convolution, and gated recurrent units, augmented by an adaptive channel-wise attention mechanism and an external-factor-driven self-attention enhancement module. Experiments on a real-world dataset from Guangzhou South Railway Station demonstrate state-of-the-art performance: the proposed method reduces average prediction error by 18.7% during peak hours compared to existing approaches, significantly enhancing decision-support capabilities for multimodal coordinated scheduling.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for 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 learning to rank, online learning, and counterfactual learning for ranking

Abstract

Accurate and refined passenger flow prediction is essential for optimizing the collaborative management of multiple collection and distribution modes in large-scale transportation hubs. Traditional methods often focus only on the overall passenger volume, neglecting the interdependence between different modes within the hub. To address this limitation, we propose MM-STFlowNet, a comprehensive multi-mode prediction framework grounded in dynamic spatial-temporal graph modeling. Initially, an integrated temporal feature processing strategy is implemented using signal decomposition and convolution techniques to address data spikes and high volatility. Subsequently, we introduce the Spatial-Temporal Dynamic Graph Convolutional Recurrent Network (STDGCRN) to capture detailed spatial-temporal dependencies across multiple traffic modes, enhanced by an adaptive channel attention mechanism. Finally, the self-attention mechanism is applied to incorporate various external factors, further enhancing prediction accuracy. Experiments on a real-world dataset from Guangzhounan Railway Station in China demonstrate that MM-STFlowNet achieves state-of-the-art performance, particularly during peak periods, providing valuable insight for transportation hub management.

Problem

• Predicts multi-mode passenger flow in transportation hubs
• Captures spatial-temporal dependencies between different modes
• Enhances accuracy with dynamic graph modeling and attention

Innovation

• Dynamic spatial-temporal graph modeling for multi-mode prediction
• Integrated temporal feature processing with signal decomposition
• Adaptive channel attention mechanism for spatial-temporal dependencies