AI-Powered Urban Mobility Analysis for Advanced Traffic Flow Forecasting

Rapid global urbanization has resulted in burgeoning metropolitan populations, posing significant challenges for managing transportation infrastructure. Despite various attempts to address these issues, persistent challenges hinder urban growth. This study emphasizes the crucial need for effective traffic flow forecasting in city traffic management systems, with Catania serving as a case study due to its notable traffic congestion. Predicting traffic flow encounters obstacles, such as the cost and feasibility of deploying sensors across all roads. To overcome this, the authors suggest an innovative two-level machine learning approach, involving an unsupervised clustering model to extract patterns from extensive sensor-generated big data, followed by supervised machine learning models forecasting traffic within individual clusters. Notably, this method allows predictions for roads without sensor data by leveraging a small subset of alternative data sources