F-GGRU: A Sensor-Driven Deep Learning Framework for Smart City Weather-Aware Traffic Congestion Prediction

Akbar Ali¹Adnan Nadeem^2*Noureen Zafar³Muhammad Shiraz¹

• ¹Federal Urdu University of Arts Science and Technology - Islamabad Campus, Islamabad, Pakistan
• ²Islamic University of Madinah, Medina, Saudi Arabia
• ³PMAS-Arid Agriculture University Rawalpindi, Rawalpindi, Pakistan

The deployment of various sensors including inductive loops, radars, GPS devices, cameras and floating car data (FCD) in intelligent transportation systems generates a stream of heterogeneous data, further complicated by exogenous factors like weather conditions and temporal patterns (e.g., peak hours, weekends). For urban traffic development planning, the accurate prediction of congestion under the influence of these exogenous factors remains a major challenge. The proliferation of these diverse data sources creates a complex prediction environment, demanding advanced analytical frameworks. To address this issue, we propose a novel Fusion-based Generative Adversarial Network with Gated Recurrent Unit (F-GGRU) framework. The F-GGRU develops a generic data pipeline for integrating and preprocessing multi-source data, featuring advanced techniques for outlier removal, fuzzy logic-based automatic labeling, and Generative Adversarial Networks (GANs) for class balancing. Extensive experimentation was conducted on a novel real-time dataset from the Safe City Islamabad Pakistan (SCIP) project, integrating heterogeneous and exogenous features. The results demonstrate that our proposed F-GGRU framework consistently achieves superior performance, with 98.48% accuracy, 0.97 precision, 1.00 recall, 0.985 F1-score, and a 0.9914 ROC-AUC score. This significantly outperforms a suite of benchmark models—including Logistic Regression, Random Forest, XGBoost, and deep learning baselines like GRU and ANN, which achieved accuracies between 77–83% with notably lower precision and recall for the congested class. Crucially, hyperparameter tuning and rigorous validation on a second independent dataset (CityPulse, Aarhus) confirmed the model's robustness and generalizability, achieving even higher performance (99.42% accuracy, 0.9976 AUC) while maintaining perfect recall. These findings affirm that the F-GGRU framework is not only highly accurate but also a robust and generalizable solution for real-world traffic congestion prediction in smart cities