Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
April 10, 2026Transportation Research Part C Emerging TechnologiesOpen Access

Origin-destination flow generation for metro network expansion using spatiotemporal gated graph neural networks

View Full Paper
Ask AI
Bookmark
Share

Authors

FDFangyi DingZZZhan ZhaoYWYamin Wang

Discussion

Loading...

Member takes

Overview

Demonstrates effective origin-destination flow generation in metro networks, suggesting a new approach for urban transit planning.

Key Points

  • The aim is to accurately generate origin-destination (OD) flow data for expanding metro networks, especially for new pairs without historical data.
  • Developed a Spatiotemporal Gated Graph Neural Network (STG-GNN) to model OD flow generation.
  • Utilized graph attention networks to capture spatial dependencies based on travel time and geographic distance.
  • Incorporated Gated Recurrent Units (GRUs) to model temporal patterns in ridership data.
  • Implemented an adaptive gated fusion module for spatial and temporal feature integration.
  • Used an age-aware weighted loss function to account for the maturity of new OD pairs.
  • STG-GNN improved the Common Part of Commute (CPC) by 13.6%.
  • Reduced Root Mean Square Error (RMSE) by 11.3% for new OD pairs.
  • Reduced Mean Absolute Error (MAE) by 4.7% for new OD pairs.
  • Consistently outperformed existing models, demonstrating strong generalization capabilities.

Cite This Study

Ding et al. (2026) studied this question.

synapsesocial.com/papers/69d892d16c1944d70ce0411ahttps://doi.org/10.1016/j.trc.2026.105677
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Multi-Step Passenger Flow Prediction for Urban Metro System Based on Spatial-Temporal Graph Neural Network2024 · 7 citations
  2. 2Dynamic Multi-Scale Spatio-Temporal Graph ODE for Metro Ridership Prediction2024
  3. 3A dynamic multigraph and multidimensional attention neural network model for metro passenger flow prediction2024 · 2 citations
  4. 4Regularized Spatial–Temporal Graph Convolutional Networks for Metro Passenger Flow Prediction2024 · 37 citations
  5. 5Disentanglement-Guided Spatial-Temporal Graph Neural Network for Metro Flow Forecasting (Student Abstract)2024