Spatial temporal incidence dynamic graph neural networks for traffic flow forecasting

Abstract Accurate and real-time traffic passenger flows forecasting at transportation hubs, such as subway/bus stations, is a practical application and of great significance for urban traffic planning, control, guidance, etc. Recently deep learning based methods are promised to learn the spatial-temporal features from high non-linearity and complexity of traffic flows. However, it is still very challenging to handle so much complex factors including the urban transportation network topological structures and the laws of traffic flows with spatial and temporal dependencies. Considering both the static hybrid urban transportation network structures and dynamic spatial-temporal relationships among stations from historical traffic passenger flows, a more effective and fine-grained spatial-temporal features learning framework is necessary. In this paper, we propose a novel spatial-temporal incidence dynamic graph neural networks framework for urban traffic passenger flows prediction. We first model dynamic traffic station relationships over time as spatial-temporal incidence dynamic graph structures based on historically traffic passenger flows. Then we design a novel dynamic graph recurrent convolutional neural network, namely Dynamic-GRCNN, to learn the spatial-temporal features representation for urban transportation network topological structures and transportation hubs. To fully utilize the historical passenger flows, we sample the short-term, medium-term and long-term historical traffic data in training, which can capture the periodicity and trend of the traffic passenger flows at different stations. We conduct extensive experiments on different types of traffic passenger flows datasets including subway, taxi and bus flows in Beijing. The results show that the proposed Dynamic-GRCNN effectively captures comprehensive spatial-temporal correlations significantly and outperforms both traditional and deep learning based urban traffic passenger flows prediction methods.

• Publication year

  2020

• Venue

  Information Sciences

• Publication date

  2020-01-20

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.1016/j.ins.2020.01.043
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Deep Irregular Convolutional Residual LSTM for Urban Traffic Passenger Flows Prediction

  2020cited by this paper
• Hierarchical Taxonomy-Aware and Attentional Graph Capsule RCNNs for Large-Scale Multi-Label Text Classification

  2019cited by this paper
• Predicting Multi-step Citywide Passenger Demands Using Attention-based Neural Networks

  2018cited by this paper
• Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction

  2018cited by this paper
• Dynamic Spatio-temporal Graph-based CNNs for Traffic Prediction

  2018cited by this paper
• Kernel-Weighted Graph Convolutional Network: A Deep Learning Approach for Traffic Forecasting

  2018cited by this paper
• Large-Scale Hierarchical Text Classification with Recursively Regularized Deep Graph-CNN

  2018cited by this paper
• Author contribution statement

  2018cited by this paper
• Deep Convolutional Mesh RNN for Urban Traffic Passenger Flows Prediction

  2018cited by this paper
• Graph CNNs for Urban Traffic Passenger Flows Prediction

  2018influential reference
• Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting

  2017influential reference
• LSTM network: a deep learning approach for short-term traffic forecast

  2017cited by this paper
• Predicting Citywide Crowd Flows Using Deep Spatio-Temporal Residual Networks

  2017influential reference
• Scalable deep traffic flow neural networks for urban traffic congestion prediction

  2017cited by this paper
• Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction

  2017influential reference
• Computing Urban Traffic Congestions by Incorporating Sparse GPS Probe Data and Social Media Data

  2017cited by this paper
• Short-Term Forecasting of Passenger Demand under On-Demand Ride Services: A Spatio-Temporal Deep Learning Approach

  2017cited by this paper
• FCN-rLSTM: Deep Spatio-Temporal Neural Networks for Vehicle Counting in City Cameras

  2017cited by this paper
• Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting

  2017influential reference
• Estimating Urban Traffic Congestions with Multi-sourced Data

  2016cited by this paper
• Learning Convolutional Neural Networks for Graphs

  2016influential reference
• Catch Me If You Can: Detecting Pickpocket Suspects from Large-Scale Transit Records

  2016cited by this paper
• Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction

  2016cited by this paper
• Urban Traffic Flow Prediction Using a Spatio-Temporal Random Effects Model

  2016cited by this paper
• Short‐term traffic flow prediction with linear conditional Gaussian Bayesian network

  2016cited by this paper
• Deep learning for short-term traffic flow prediction

  2016cited by this paper
• Short Term Traffic Flow Prediction Using Deep Learning Approach

  2016cited by this paper
• DNN-based prediction model for spatio-temporal data

  2016cited by this paper
• Citywide traffic congestion estimation with social media

  2015cited by this paper
• Traffic Flow Prediction With Big Data: A Deep Learning Approach

  2015cited by this paper
• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting

  2015cited by this paper
• Predicting Short-Term Traffic Flow by Long Short-Term Memory Recurrent Neural Network

  2015cited by this paper
• Twitter Interactions as a Data Source for Transportation Incidents

  2013cited by this paper
• The Car that Hit The Burning House: Understanding Small Scale Incident Related Information in Microblogs

  2013cited by this paper
• On optimization methods for deep learning

  2011cited by this paper
• Lane-level traffic estimations using microscopic traffic variables

  2010cited by this paper
• Applied research of data sensing and service to ubiquitous intelligent transportation system

  2010cited by this paper
• Predictions of Freeway Traffic Speeds and Volumes Using Vector Autoregressive Models

  2009influential reference
• Whether Weather Matters to Traffic Demand, Traffic Safety, and Traffic Operations and Flow

  2006cited by this paper
• Modeling and Forecasting Vehicular Traffic Flow as a Seasonal ARIMA Process: Theoretical Basis and Empirical Results

  2003cited by this paper
• Comparison of parametric and nonparametric models for traffic flow forecasting

  2002cited by this paper
• Development of Artificial Neural Network Models to Predict Driver Injury Severity in Traffic Accidents at Signalized Intersections

  2001cited by this paper
• Urban Freeway Traffic Flow Prediction: Application of Seasonal Autoregressive Integrated Moving Average and Exponential Smoothing Models

  1998cited by this paper
• TRAFFIC FLOW FORECASTING: COMPARISON OF MODELING APPROACHES

  1997cited by this paper
• Short-Term Prediction of Traffic Volume in Urban Arterials

  1995influential reference
• Dynamic prediction of traffic volume through Kalman Filtering

  1984cited by this paper

• MPST-Mamba: a Mamba-based multi-period spatio-temporal model for traffic flow prediction

  2026cites this paper
• Gumbel Sparse Attention Spatio-Temporal Network: A framework for traffic risk prediction

  2026cites this paper
• HT-GNN: Hyper-Temporal Graph Neural Network for Customer Lifetime Value Prediction in Baidu Ads

  2026cites this paper
• Bi-STDGCN: A Bidirectional Spatiotemporal Diffusion Graph Convolutional Network With Multiscale Anomaly-Guided Attention for Traffic Forecasting

  2026cites this paper
• Multimodal Fault Diagnosis Method Based on Node-Level Adaptive Attention and Dynamic Graph Learning

  2026cites this paper
• Spatio-Temporal Propagation-Aware Graph Neural Network for Traffic Flow Prediction

  2026cites this paper
• A Comprehensive Analysis of Incident and Object Detection in Traffic Environments

  2026cites this paper
• PGSFormer: traffic flow prediction based on joint optimization of progressive graph convolutional networks with subseries transformer

  2026cites this paper
• Principal Component Analysis Embedded Temporal Attention Spatiotemporal Graph Convolutional Networks for Traffic Flow Prediction

  2025cites this paper
• Towards Robust and Interpretable Spatial-Temporal Graph Modeling for Traffic Prediction

  2025cites this paper
• Uncertainty-Aware Disentangled Dynamic Graph Attention Network for Out-of-Distribution Generalization

  2025cites this paper
• DMGF-STAN: Spatio-Temporal Attention Network and Dynamic Multi-Graph Fusion for Traffic Flow Prediction

  2025cites this paper
• Interpretable train-level entry flow prediction using GMM-based features and ensemble learning

  2025cites this paper
• A hybrid graph memory network approach with multi-level feature representation for traffic flow forecast

  2025cites this paper
• Sample and Aggregate Voronoi Neighborhood Weighted Graph Neural Network (SAGE-Voronoi) and Its Capability for City-Sized Vehicle Traffic Time Series Prediction

  2025cites this paper
• Spatio-temporal Graph Convolutional Neural Network for traffic signal prediction in large-scale urban networks

  2025cites this paper
• Graph neural networks: Historical backgrounds, present revolutions, and conventionalization for the future

  2025cites this paper
• Discovering the Precursors of Traffic Breakdowns Using Spatiotemporal Graph Attribution Networks

  2025cites this paper
• Iterative GNN-Based Traffic Flow Prediction and Sensor Placement Optimization

  2025cites this paper
• Evaluating the auto-regressive integrated moving average method for inventory minimization against the recurrent neural network based model materials forecasting performance

  2025cites this paper
• Inference-friendly Graph Compression for Graph Neural Networks

  2025influential citation
• Learning dynamic interaction for multimodal transportation systems: A joint passenger flow prediction approach based on spatiotemporal hypergraph convolution networks

  2025cites this paper
• ST-GAN: Spatial-Temporal Graph Attention Network for Traffic Prediction

  2025cites this paper
• MSGAT-GRU: A Multi-Scale Graph Attention and Recurrent Model for Spatiotemporal Road Accident Prediction

  2025cites this paper
• MDHGFN: Multiscale Dual Hypergraph Fusion Spatiotemporal Network for traffic flow prediction

  2025cites this paper
• How Different from the Past? Spatio-Temporal Time Series Forecasting with Self-Supervised Deviation Learning

  2025cites this paper
• Novel deep learning framework for rainfall forecasting integrating generative adversarial and spatiotemporal graph neural networks

  2025cites this paper
• Dynamic Graph Convolutional Recurrent Network With Temporal Self‐Attention for Accurate Traffic Flow Prediction

  2025cites this paper
• An attention-based dynamic graph model for on-street parking availability prediction

  2025cites this paper
• Traffic Speed Series Prediction Based on Multi-View Spatial-Temporal Graph Convolutional Networks

  2025cites this paper
• ScaDyG:A New Paradigm for Large-scale Dynamic Graph Learning

  2025cites this paper
• Spatio-temporal graph hierarchical learning framework for metro passenger flow prediction across stations and lines

  2025cites this paper
• ST2SNet: Spatial–Temporal Two-Layer Synchronous Network for Traffic Flow Prediction

  2025cites this paper
• Urban Rail Transit Passenger Flow Prediction with Gaussian Process Regression Based on CEEMDAN

  2025cites this paper
• Spatio-temporal Graph Neural Network Fused with Maritime Knowledge for Predicting Traffic Flows in Ports

  2025cites this paper
• Backdoor-Empowered Regulable Privilege Authorization for Edge-Level Graph Learning in 6G Vehicular Networks

  2025cites this paper
• Understanding metro origin-destination passenger flow dynamics: a novel entropy and machine learning perspective

  2025cites this paper
• Multi-scale time series prediction model based on deep learning and its application

  2025cites this paper
• Long-term spatio-temporal graph attention network for traffic forecasting

  2025cites this paper
• MSTT: A Multi-Spatio-Temporal Graph Attention Model for Pedestrian Trajectory Prediction

  2025cites this paper
• Securing Virtual Private Networks Against Cyber Threats Using Feedforward Neural Networks

  2025cites this paper
• Development of a Sustainable National Traffic Information Notification System: A GNSS-Based with Enhanced-LSTM for Urban Road Traffic Speed Forecasting

  2025cites this paper
• Spatiotemporal Prediction of the Impact of Dynamic Passenger Flow at Subway Stations on the Sustainable Industrial Heritage Land Use

  2025cites this paper
• A Dynamic Regional-Aggregation-Based Heterogeneous Graph Neural Network for Traffic Prediction

  2025cites this paper
• Pedestrian Volume Prediction Using a Diffusion Convolutional Gated Recurrent Unit Model with Dynamic Time Warping

  2025cites this paper
• Multi-source data-driven intelligent analysis and decision optimization for high-density pedestrian flows in urban public spaces

  2025cites this paper
• Predictive Configuration on DHCP in WLANs

  2025cites this paper
• HL-HGAT: Heterogeneous Graph Attention Network via Hodge-Laplacian Operator

  2025cites this paper
• DETNO: A Diffusion-Enhanced Transformer Neural Operator for Long-Term Traffic Forecasting

  2025cites this paper
• A Knowledge-Guided Cross-Modal Feature Fusion Model for Local Traffic Demand Prediction

  2025cites this paper
• WEST GCN-LSTM: Weighted stacked spatio-temporal graph neural networks for regional traffic forecasting

  2025cites this paper
• DyExplainer: Self-explainable Dynamic Graph Neural Network with Sparse Attentions

  2025cites this paper
• Network-level short-term traffic state prediction incorporating critical nodes: A knowledge-based deep fusion approach

  2024cites this paper
• Comparison of artificial neural networks and regression analysis for airway passenger estimation

  2024cites this paper
• Phase transition-like behaviors of propagation of passenger stranding phenomena in subway networks

  2024influential citation
• Predicting dynamic responses of continuous deformable bodies:A graph-based learning approach

  2024cites this paper
• MAST-GNN: A multimodal adaptive spatio-temporal graph neural network for airspace complexity prediction

  2024cites this paper
• Spatial–Temporal Graph Attention Gated Recurrent Transformer Network for Traffic Flow Forecasting

  2024cites this paper
• Heterogeneous graph neural networks for fraud detection and explanation in supply chain finance

  2024cites this paper
• Exploring the spatial effects on the level of congestion caused by traffic accidents in urban road networks: A case study of Beijing

  2024cites this paper
• FediTT: A Federated Learning Approach for Privacy-Preserving Traffic Flow Prediction

  2024cites this paper
• Regularized Spatial–Temporal Graph Convolutional Networks for Metro Passenger Flow Prediction

  2024cites this paper
• DERGCN: Dynamic-Evolving graph convolutional networks for human trajectory prediction

  2024cites this paper
• Embedding Public Opinion and Global Aviation Network for Dengue Fever Prediction: An LSTM-Based Approach

  2024cites this paper
• ActIPP: Active Intellectual Property Protection of Edge-Level Graph Learning for Distributed Vehicular Networks

  2024cites this paper
• Vision Technologies with Applications in Traffic Surveillance Systems: A Holistic Survey

  2024cites this paper
• Acoustic emission signals characterization and damage source localization in composite heterogeneous panels

  2024cites this paper
• Pedestrian Volume Prediction Using a Diffusion Convolutional Gated Recurrent Unit Model

  2024cites this paper
• IEDSFAN: information enhancement and dynamic-static fusion attention network for traffic flow forecasting

  2024cites this paper
• Transfer learning with a spatiotemporal graph convolution network for city flow prediction

  2024cites this paper
• Graph neural network based time estimator for SAT solver

  2024cites this paper
• A Spatiotemporal Locomotive Axle Temperature Prediction Approach Based on Ensemble Graph Convolutional Recurrent Unit Networks

  2024cites this paper
• Causality-Inspired Spatial-Temporal Explanations for Dynamic Graph Neural Networks

  2024cites this paper
• Analyzing and Comparing Global Sustainability Standards: LEED, BREEAM, and PBRS in Green Building arch article topic

  2024cites this paper
• SSGC-GAT: Synergistic Similarity Graph Construction Strategy Combined With GAT Network for Wind Turbine Anomaly Identification Using SCADA Data

  2024cites this paper
• SDDObench: A Benchmark for Streaming Data-Driven Optimization with Concept Drift

  2024cites this paper
• Predicting traffic intensity in the urban area of Madrid: Integrating route network topology into a machine-learning model

  2024cites this paper
• Dynamic traffic network representation model for improving the prediction performance of passenger flow for mass rapid transit

  2024cites this paper
• Prediction of Traffic Flow in Vehicular Ad-hoc Networks using Optimized Based-Neural Network

  2024cites this paper
• Fine‐Grained Passenger Load Prediction inside Metro Network via Smart Card Data

  2024cites this paper
• Learning dynamic and multi-scale graph structure for traffic demand prediction

  2024cites this paper
• Short-term Traffic Flow Prediction：A Method of MEA-LSTM Model Based on Chaotic Characteristics Analysis

  2024cites this paper
• A District-Centric Attention Mechanism Approach for Online Ride-Hailing Demand Forecasting

  2024cites this paper
• Modeling urban traffic volume incorporating driver stochasticity and traffic correlation with waveguide-based quantum walk

  2024cites this paper
• Channel spatio-temporal convolutional network for pedestrian trajectory prediction

  2024cites this paper
• A Fairness Group Recommendation Algorithm Based On User Activity

  2024cites this paper
• Research on Optimization of Traffic Management in Smart Tourism Cities for Sustainable Development

  2024cites this paper
• WEST GCN-LSTM: Weighted Stacked Spatio-Temporal Graph Neural Networks for Regional Traffic Forecasting

  2024cites this paper
• Learning structure perception MLPs on graphs: a layer-wise graph knowledge distillation framework

  2024cites this paper
• Neural networks for intelligent multilevel control of artificial and natural objects based on data fusion: A survey

  2024cites this paper
• A review of research methods on the coupling relationship between urban rail transit and urban space: revealing spatiotemporal relationships through big data

  2024cites this paper
• Deep-learning reconstruction of complex dynamical networks from incomplete data.

  2024cites this paper
• Uncertainty Quantification for Traffic Forecasting Using Deep-Ensemble-Based Spatiotemporal Graph Neural Networks

  2024cites this paper
• λGrapher: A Resource-Efficient Serverless System for GNN Serving through Graph Sharing

  2024cites this paper
• MTLMetro: A Deep Multi-Task Learning Model for Metro Passenger Demands Prediction

  2024cites this paper
• FedAGAT: Real-time traffic flow prediction based on federated community and adaptive graph attention network

  2024cites this paper
• A Novel Money Laundering Prediction Model Based on a Dynamic Graph Convolutional Neural Network and Long Short-Term Memory

  2024cites this paper
• Advancing Graph Neural Networks with HL-HGAT: A Hodge-Laplacian and Attention Mechanism Approach for Heterogeneous Graph-Structured Data

  2024cites this paper
• An Enhanced Ensemble-Based Long Short-Term Memory Approach for Traffic Volume Prediction

  2024cites this paper
• Neural embeddings of urban big data reveal spatial structures in cities

  2024cites this paper