GSMT: Graph Fusion and Spatiotemporal TaskCorrection for Multi-Bus Trajectory Prediction

TL;DR

GSMT is a hybrid model combining graph attention, sequence modeling, and task correction to improve bus trajectory prediction in urban environments with limited data, outperforming existing methods.

Contribution

The paper introduces GSMT, a novel two-stage model integrating graph attention, RNN, and a task corrector for enhanced multi-bus trajectory prediction.

Findings

GSMT significantly outperforms existing approaches in real-world datasets.

The model effectively captures complex behavioral patterns from large-scale trajectory data.

Two-stage fusion and correction improve short-term and long-term prediction accuracy.

Abstract

Accurate trajectory prediction for buses is crucial in intelligent transportation systems, particularly within urban environments. In developing regions where access to multimodal data is limited, relying solely on onboard GPS data remains indispensable despite inherent challenges. To address this problem, we propose GSMT, a hybrid model that integrates a Graph Attention Network (GAT) with a sequence-to-sequence Recurrent Neural Network (RNN), and incorporates a task corrector capable of extracting complex behavioral patterns from large-scale trajectory data. The task corrector clusters historical trajectories to identify distinct motion patterns and fine-tunes the predictions generated by the GAT and RNN. Specifically, GSMT fuses dynamic bus information and static station information through embedded hybrid networks to perform trajectory prediction, and applies the task corrector for secondary refinement after the initial predictions are generated. This two-stage approach enables multi-node trajectory prediction among buses operating in dense urban traffic environments under complex conditions. Experiments conducted on a real-world dataset from Kuala Lumpur, Malaysia, demonstrate that our method significantly outperforms existing approaches, achieving superior performance in both short-term and long-term trajectory prediction tasks.