ST-MambaSync: The Complement of Mamba and Transformers for Spatial-Temporal in Traffic Flow Prediction

TL;DR

ST-MambaSync is a novel traffic flow prediction model that combines transformer technology with the ST-Mamba block, improving accuracy, efficiency, and explainability for urban traffic management.

Contribution

It introduces the Mamba mechanism within a transformer framework for the first time, enhancing model performance and interpretability in traffic flow prediction.

Findings

Sets new benchmarks for accuracy and speed

Addresses long sequence data challenges effectively

Improves model explainability

Abstract

Accurate traffic flow prediction is crucial for optimizing traffic management, enhancing road safety, and reducing environmental impacts. Existing models face challenges with long sequence data, requiring substantial memory and computational resources, and often suffer from slow inference times due to the lack of a unified summary state. This paper introduces ST-MambaSync, an innovative traffic flow prediction model that combines transformer technology with the ST-Mamba block, representing a significant advancement in the field. We are the pioneers in employing the Mamba mechanism which is an attention mechanism integrated with ResNet within a transformer framework, which significantly enhances the model's explainability and performance. ST-MambaSync effectively addresses key challenges such as data length and computational efficiency, setting new benchmarks for accuracy and processing speed through comprehensive comparative analysis. This development has significant implications for urban planning and real-time traffic management, establishing a new standard in traffic flow prediction technology.