Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

UMOD: A Novel and Effective Urban Metro Origin-Destination Flow Prediction Method

Peng Xie, Minbo Ma, Bin Wang, Junbo Zhang, Tianrui Li

TL;DR

This work proposes a novel and effective urban metro OD flow prediction method (UMOD), comprising three core modules: a data embedding module, a temporal relation module, and a spatial relation module, which outperforms existing approaches, delivering superior predictive performance.

Abstract

Accurate prediction of metro Origin-Destination (OD) flow is essential for the development of intelligent transportation systems and effective urban traffic management. Existing approaches typically either predict passenger outflow of departure stations or inflow of destination stations. However, we argue that travelers generally have clearly defined departure and arrival stations, making these OD pairs inherently interconnected. Consequently, considering OD pairs as a unified entity more accurately reflects actual metro travel patterns and allows for analyzing potential spatio-temporal correlations between different OD pairs. To address these challenges, we propose a novel and effective urban metro OD flow prediction method (UMOD), comprising three core modules: a data embedding module, a temporal relation module, and a spatial relation module. The data embedding module projects raw OD pair inputs into hidden space representations, which are subsequently processed by the temporal and spatial relation modules to capture both inter-pair and intra-pair spatio-temporal dependencies. Experimental results on two real-world urban metro OD flow datasets demonstrate that adopting the OD pairs perspective is critical for accurate metro OD flow prediction. Our method outperforms existing approaches, delivering superior predictive performance.

UMOD: A Novel and Effective Urban Metro Origin-Destination Flow Prediction Method

TL;DR

This work proposes a novel and effective urban metro OD flow prediction method (UMOD), comprising three core modules: a data embedding module, a temporal relation module, and a spatial relation module, which outperforms existing approaches, delivering superior predictive performance.

Abstract

Accurate prediction of metro Origin-Destination (OD) flow is essential for the development of intelligent transportation systems and effective urban traffic management. Existing approaches typically either predict passenger outflow of departure stations or inflow of destination stations. However, we argue that travelers generally have clearly defined departure and arrival stations, making these OD pairs inherently interconnected. Consequently, considering OD pairs as a unified entity more accurately reflects actual metro travel patterns and allows for analyzing potential spatio-temporal correlations between different OD pairs. To address these challenges, we propose a novel and effective urban metro OD flow prediction method (UMOD), comprising three core modules: a data embedding module, a temporal relation module, and a spatial relation module. The data embedding module projects raw OD pair inputs into hidden space representations, which are subsequently processed by the temporal and spatial relation modules to capture both inter-pair and intra-pair spatio-temporal dependencies. Experimental results on two real-world urban metro OD flow datasets demonstrate that adopting the OD pairs perspective is critical for accurate metro OD flow prediction. Our method outperforms existing approaches, delivering superior predictive performance.
Paper Structure (16 sections, 5 equations, 5 figures, 6 tables)

This paper contains 16 sections, 5 equations, 5 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Related work
  3. Traffic Flow Prediction
  4. Origin-Destination Prediction
  5. Problem Formulation
  6. Methodology
  7. Data Embedding Module
  8. Temporal Relation Module
  9. Spatial Relation Module
  10. Experiments
  11. Experiment Settings
  12. Experimental Results
  13. Ablation Study
  14. Hyper-parameters Analysis
  15. Discussion
  16. ...and 1 more sections

Figures (5)

  • Figure 1: The figure illustrates metro stations as interconnected nodes with two types of flows: Outflow and Inflow. By shifting to an origin-destination (OD) perspective, the OD flow graph in the upper right provides a comprehensive view of passenger movements, overcoming the limitations of traditional metro maps.
  • Figure 2: The UMOD method consists of three core modules: a Data Embedding module, a Temporal Transformer module, and a Spatial MLP module.
  • Figure 3: Spatial embedding (OD pairs embedding) of OD flow.
  • Figure 4: Impact of Number of Input Embedding Dimensions.
  • Figure 5: Impact of Number of Adaptive Embedding Dimensions.