Skip to content
Log in
Open access

Enhanced Traffic Prediction Using Spatial–Temporal Graph Neural Networks

Akarsh Kumar Aishwarya Sinha Yadvendra Pratap Singh
2026 · IEEE Access · Vol 14, pp. 107120-107129 · 0 citations · 36 references
Computer Science

TL;DR

A Spatial-Temporal Graph Neural Network framework that can learn a combination of spatial and temporal relationships in road networks and changing time-varying patterns in traffic flow is used, which implies that adaptive spatial learning, together with the temporal sequence modeling, can produce much better forecasting stability.

Abstract

The ability to forecast traffic conditions in urban environments is essential for intelligent transport systems because it provides proactive congestion management, traffic control and informed urban mobility planning. However, due to the extreme spatial and temporal volatility of traffic flow patterns, conventional statistical, machine learning, and sequence-based deep learning approaches either fail to account for the spatial relationships between highway segments or fail to sufficiently model long-range temporal dynamics. To address these gaps, the present study uses a Spatial-Temporal Graph Neural Network (STGNN) framework that can learn a combination of spatial and temporal relationships in road networks and changing time-varying patterns in traffic flow. The model has a graph-based architecture where graph-convolutional layers are combined with gated recurrent units and transformer-based attention units, thus creating a hybrid architecture that is capable of multi-scale spatio-temporal dependencies. The METR-LA dataset was used in experiments, and it was observed that STGNN had smaller Mean Absolute Percentage Error(MAPE), Mean Absolute Error(MAE), and Root Mean Squared Error(RMSE) at 15, 30, and 60 minute horizons of prediction than the baseline and the implemented models: Sequence to Sequence (Seq2Seq) and Temporal Graph Convolutional Network (T-GCN). The model achieved the best results for the 15-minute interval with an MAE of 2.71, an RMSE of 5.17, and a MAPE of 7.08. The results imply that adaptive spatial learning, together with the temporal sequence modeling, can produce much better forecasting stability, which underlines the potential STGNN-based traffic prediction systems have to contribute to real-time traffic control.

DOI Semantic Scholar
Read PDF

Similar papers

Open access Jul 2026

Recurrent Graph Neural Network Hybrid Model for Spatio-Temporal Traffic Flow Prediction in Intelligent Transportation Systems

TETRA is proposed, a hybrid spatio-temporal traffic forecasting model that integrates Graph Convolutional Networks (GCNs) with Extended Long Short-Term Memory (xLSTM) to capture complex multi-timescale temporal patterns, including congestion propagation and delayed recovery dynamics, which are not well represented by conventional recurrent models.

Norman Bereczki, Vilmos Simon · 0 citations
Open access Jul 2026

Traffic Flow Prediction System Based on Spatiotemporal Graph Neural Network

This framework introduces an adaptive graph learning module that dynamically infers meaningful connectivity relationships among traffic sensors—not relying on fixed geographic or distance-based assumptions—but instead leveraging real-time traffic correlations and node-level embeddings, enabling effective modeling of both localized spatial interactions and multi-scale temporal dependencies across varying prediction horizons.

Zhengxu Luan, Huan Wang, Miaobowen Wang et al. · 0 citations
Conference Open access 2025

Predicting Traffic Flow Using Attention and Spatiotemporal Graph Convolutional Networks

A prediction model that incorporates multiple attention mechanisms with spatiotemporal graph convolutional networks (HASTGCN) and designs a spatiotemporal map convolution module to collaboratively model the dynamic spatiotemporal connection of traffic flow collaboratively model is used.

Chu-xia Chen · 0 citations
Open access 2026

Robustness of Spatio-Temporal Graph Neural Networks for Traffic Forecasting Under Realistic Sensor Degradation

A robust focused comparative evaluation of seven traffic forecasting approaches suggests that traffic forecasting models should be assessed not only by clean-data accuracy but also by their robustness under degraded sensing conditions before deployment in real intelligent transportation systems.

Shreya N. Desai, Kasim Ishaque Ghanchi, Ali Mehdi Mirza et al. · 0 citations
Open access Aug 2026

Adaptive Attention-Based Spatio-Temporal Forecasting Framework for Urban Traffic Speed Prediction

Spatio-temporal traffic forecasting, with reliable temporal and spatial information, is a crucial component of any urban transportation network for intelligent transportation systems and the management of mobility. This study proposes an Adaptive Spatio-Temporal Forecasting (ASTF) framework based on Graph Neural Networks (GNNs), Temporal Convolutional Networks (TCNs) and an adaptive attention mechanism. The GNN models spatial relationships between interconnected traffic sensors and TCN models temporal patterns and changing traffic conditions. Adaptive attention additionally enhances prediction by putting more weight on important sensor positions. The framework is tested on the well-known METR-LA and PEMS-BAY benchmark datasets that includes measurements of traffic speed from urban road networks. The results show the effectiveness of spatial graph learning, temporal convolution and adaptive attention in forecasting traffic speeds across the benchmark urban transportation datasets and provide a promising way to apply the proposed method in real scenarios.

Unknown authors · 0 citations
Open access Aug 2026

Building Urban Traffic Flow Prediction Model Using Spatio-Temporal Graph Convolutional Networks

The proposed position-aware spatio-temporal modeling strategy provides a practical reference for information fusion and dynamic state estimation in large-scale wireless sensing networks and electromagnetic signal-driven monitoring systems, supporting future intelligent perception and communication infrastructures.

J. Sun, Y. Liu, Y. Dou et al. · 0 citations