AN INTEGRATED ML AND GEOSPATIAL FRAMEWORK FOR CONTEXT-AWARE SHORTTERM CONGESTION FORECASTING IN TOURISM-HEAVY URBAN MOBILITY NODE
Tourism-heavy urban mobility nodes often experience short, intense congestion spikes where visitor surges interact with commuter-related traffic. Despite growing interest in smart mobility management, few studies integrate real-time computer vision sensing with uncertainty-aware machine learning to support operational decision-making at tourism-intensive urban nodes. This study aims to develop and validate a real-time, uncertainty-aware traffic prediction framework that provides actionable, short-horizon (15-minute) congestion intelligence in such areas. Town Quay (Southampton, UK) is used as a case study. Three months of continuous webcam footage (July–September 2025) were processed with a YOLO + SORT pipeline to generate 15-minute vehicle counts. Counts were enriched with contextual features capturing weather (clear/foggy/rainy), day–night cycle, and day type (business vs. leisure). CatBoost and LightGBM were trained using a chronological split (first two months for training, third month for testing). Uncertainty quantification combined conformal prediction intervals with Gaussian Mixture Model (GMM). Traffic volumes varied systematically with context, with the highest average loads occurring during clear-weather daytime business periods. The framework achieved MAE = 43.62, R² = 0.902, and CCC = 0.94. These findings demonstrate that integrating computer-vision traffic sensing with contextual feature engineering and uncertainty-aware learning yields reliable, interpretable 15-minute congestion forecasts. This enables proactive, risk-informed interventions (e.g., port-arrival coordination, adaptive traffic control) that help protect the physical carrying capacity and heritage-setting quality of tourism-intensive areas while maintaining everyday urban mobility.