A Long‐Term Traffic Flow Prediction Method Based on Weather‐Grouped Temporal Feature Reconstruction
Open Access
- 1 January 2026
- journal article
- Published by Institution of Engineering and Technology (IET) in IET Intelligent Transport Systems
- Vol. 20 (1)
Abstract
Long‐term traffic flow prediction remains challenging due to the time‐varying and non‐linear influence of meteorological conditions on traffic dynamics. This study proposes weather‐grouped temporal feature reconstruction (WGTFR), a forecast‐conditioned latent fusion framework that systematically incorporates weather forecast information into sequential and graph‐based prediction architectures. WGTFR comprises three coordinated modules: Dynamic feature weighting (DFW), which calibrates forecast‐aware weather relevance within latent representations; feature separation and directional fusion (FSDF), which disentangles strong and weak weather–traffic interactions and propagates them independently and hierarchical reconstruction fusion (HRF), which consolidates these interactions into prediction‐oriented latent states. Experiments on real‐world traffic and weather data from California evaluate WGTFR across four backbone architectures—Seq2Seq, Transformer, Autoformer and GCN‐Seq2Seq—under multiple long‐horizon prediction settings. WGTFR achieves the lowest RMSE across nearly all evaluated architectures and prediction horizons. Relative to weather‐free baselines, it reduces mean RMSE by 1.5% to 9.1% averaged across prediction lengths; relative to direct weather concatenation, a further 1.1% to 14% reduction is achieved. These results establish that forecast‐conditioned grouped reconstruction provides a reliable and architecture‐agnostic strategy for incorporating meteorological information into long‐horizon traffic forecasting, with performance gains increasing progressively with prediction horizon length.Keywords
This publication has 42 references indexed in Scilit:
- Adaptive spatial–temporal graph attention network for real-time traffic forecastingEngineering Applications of Artificial Intelligence, 2025
- Dynamic multi-graph spatio-temporal learning for citywide traffic flow prediction in transportation systemsChaos, Solitons & Fractals, 2025
- Long-term spatio-temporal graph attention network for traffic forecastingExpert Systems with Applications, 2025
- A data-fusion spatiotemporal matrix factorization approach for citywide traffic flow estimation and prediction under insufficient detectionInformation Fusion, 2025
- A traffic-weather generative adversarial network for traffic flow prediction for road networks under bad weatherEngineering Applications of Artificial Intelligence, 2024
- Traffic flow prediction under multiple adverse weather based on self-attention mechanism and deep learning modelsPhysica A: Statistical Mechanics and its Applications, 2023
- Hybrid deep learning models for traffic stream variables prediction during rainfallMultimodal Transportation, 2022
- Sensor location model for O/D estimation: Multi-criteria meta-heuristics approachOperations Research Perspectives, 2019
- Deep learning for short-term traffic flow predictionTransportation Research Part C: Emerging Technologies, 2017
- Long short-term memory neural network for traffic speed prediction using remote microwave sensor dataTransportation Research Part C: Emerging Technologies, 2015