Modeling Interdependencies in Intelligent Traffic Systems and Sustainable Urban Development Using Graph Neural Networks

Urbanization and the proliferation of vehicles have intensified traffic congestion, leading to environmental degradation and impeding sustainable urban development. Intelligent Traffic Systems (ITS) have emerged as pivotal solutions to manage traffic efficiently. Recent advancements in Graph Neural Networks offer unprecedented capabilities in modeling complex spatial-temporal relationships inherent in traffic networks. This paper presents a comprehensive approach, Sustainable Urban Traffic Graph Neural Network (SUT-GNN), which integrates GNN into ITS to enhance traffic prediction accuracy, optimize traffic flow, and support sustainable city development. By incorporating environmental impact assessments and urban planning considerations, our model not only predicts traffic patterns but also aligns with sustainability objectives. Experimental results on real-world traffic datasets demonstrate the superiority of our approach over traditional methods, marking a significant step towards smarter and greener cities.