Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

ST-GNNFormer: coupling dynamic graph learning and multi-scale temporal attention for traffic flow forecasting.

Zhengjia Chen^1,2, Junhao Chen³

¹School of Economics and Management, Chongqing Jiaotong University, Chongqing, China. lillianchen0805@163.com.

Scientific Reports

|July 1, 2026

Summary

This summary is machine-generated.

Related Concept Videos

Multi-input and Multi-variable systems

Multi-input and Multi-variable systems

Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Comparative population genomics reveals adaptive convergence in two Drosophila species across global environments.

Cell reports·2026

Same author

Laser ultrasonic detection for strut defects in additively manufactured lattice structure using zero-group-velocity Lamb waves.

Ultrasonics·2026

Same author

The Application of Nanomaterials in Kidney Stone Disease: Emerging Strategies for Early Diagnosis, Targeted Therapy, and Prevention.

International journal of nanomedicine·2026

Same author

A study on the mixed dielectric model of red clay.

Scientific reports·2026

Same author

Energy metabolism dysregulation in schizophrenia with non-thyroidal illness syndrome: Roles of citric acid and Tyrosol-4-sulfate.

Schizophrenia research·2026

Same author

Causal association analysis between 731 immune cells and cystitis: A 2-sample, bidirectional Mendelian randomization study.

Medicine·2026

Same journal

Therapeutic potential of crude protein extracts from two Egyptian freshwater snails Lanistes carinatus and Bellamya unicolor.

Scientific reports·2026

Same journal

Microbial contamination of donor corneas and post-keratoplasty endophthalmitis: a comparison between Japanese and U.S. eye banks using cold storage.

Scientific reports·2026

Same journal

Prevalence and contributing factors of virological non-suppression among adult patients on first-line antiretroviral therapy in tertiary hospitals in Ethiopia.

Scientific reports·2026

Same journal

An in vitro comparison of color stability between alkasite and different restorative materials in various staining solutions.

Scientific reports·2026

Same journal

Toward accessible mRNA LNP formulation: systematic evaluation of mixing strategies and key parameters.

Scientific reports·2026

Same journal

A network analysis of personality traits, mentalizing, and psychological health in Chinese college students.

Scientific reports·2026

See all related articles

ST-GNNFormer enhances urban traffic flow prediction by integrating adaptive graph learning and multi-scale temporal attention. This novel hybrid approach improves accuracy by capturing complex spatial and temporal traffic dynamics.

Area of Science:

Intelligent Transportation Systems
Graph Neural Networks
Deep Learning for Traffic Prediction

Background:

Urban traffic flow prediction is crucial for intelligent transportation systems but faces challenges from spatial heterogeneity and temporal dynamics.
Existing methods often model spatial and temporal aspects independently, missing synergistic interactions.
There is a need for advanced models that can capture complex spatio-temporal traffic patterns.

Purpose of the Study:

To propose ST-GNNFormer, a novel Hybrid Spatio-Temporal Graph Transformer for fine-grained traffic prediction.
To address limitations of existing methods by tightly coupling adaptive graph learning with multi-scale temporal attention.
To improve the accuracy and efficiency of urban traffic flow forecasting.

Main Methods:

Related Experiment Videos

Developed ST-GNNFormer, a hybrid model comprising Adaptive Dynamic Graph Learning (ADGL), Spatial Graph Transformer (SGT), Temporal Multi-Scale Transformer (TMST), and Cross-Scale Fusion (CSF) gate.
ADGL infers time-varying graph adjacency from node embeddings conditioned on temporal context.
SGT integrates graph biases into self-attention for spatial feature propagation, while TMST models multi-scale temporal patterns.

Main Results:

ST-GNNFormer consistently outperformed 8 competitive baselines on four public benchmarks (METR-LA, PEMS-BAY, PEMS04, PEMS08).
Achieved up to 7.5% improvement in Mean Absolute Error (MAE) at a 60-minute prediction horizon.
Demonstrated competitive computational efficiency alongside superior prediction accuracy.

Conclusions:

The proposed ST-GNNFormer effectively captures complex spatio-temporal dependencies in urban traffic flow.
The hybrid approach, combining adaptive graph learning and multi-scale temporal attention, offers significant improvements in traffic prediction accuracy.
Ablation studies and visualizations confirm the effectiveness of individual modules and the model's ability to learn physically meaningful traffic dynamics.