Data-Driven Assessment of Urban Transportation Infrastructure: AI, Remote Sensing, and IoT Approaches for Sustainable Management of Pavements, Bridges, and Tunnels

Urban transportation systems, including roads, sidewalks, bridges, and tunnels, form the backbone of modern cities. Their sustained functionality is critical not only for mobility and trade but also for public safety, social equity, and long-term urban sustainability. Yet, transportation networks worldwide are aging faster than maintenance capacities can respond, with deferred repairs accumulating into billions of dollars annually across both developed and developing economies.Conventional condition assessment remains largely periodic, manual, and subjective, limiting the scale and urgency required for effective infrastructure stewardship. Emerging data-driven technologies such as artificial intelligence (AI), remote sensing, and Internet of Things (IoT) sensor networks are driving a transformative shift. Together, these technologies enable continuous, objective, and scalable monitoring of transportation assets, opening new possibilities for proactive assessment and predictive maintenance.Despite these technological opportunities, the assessment and management of urban transportation systems remain challenging. Pavement distress detection, bridge health monitoring, and tunnel defect mapping remain heavily dependent on labor-intensive inspections that cannot deliver the continuous, high-resolution condition data needed for proactive, risk-informed maintenance planning.Recent advances, such as deep learning models, particularly convolutional neural networks (CNNs) and transformer-based architectures are beginning to shift this landscape by achieving strong detection performance of defects such as cracks and potholes across diverse asset types. UAV platforms equipped with optical cameras and LiDAR sensors also enable rapid, non-intrusive surveys, while IoT-embedded sensors provide real-time structural response data for critical assets. Furthermore, digital twin frameworks are emerging as integrative environments that fuse sensor data, inspection records, and predictive models to support condition-based maintenance scheduling and cost optimization.However, major gaps remain in data standardization, interoperability, scalability across varied infrastructure types, and the incorporation of environmental and climate stressors. Additionally, the growing connectivity of monitoring systems introduces cybersecurity vulnerabilities that threaten data integrity and operational safety. This research topic seeks contributions that advance these technical, analytical, and security frontiers in data-driven infrastructure assessment.This research topic aims to consolidate and advance knowledge on the application of data-driven technologies for the sustainable assessment and management of urban transportation systems, including roads, sidewalks, bridges, highways, and tunnels. We welcome original research articles, systematic reviews, and perspective papers that explore methodological innovations, practical applications, and interdisciplinary perspectives. Contributions are invited on themes including, but not limited to:- AI and deep learning for pavement distress detection, classification, and severity mapping- UAV, satellite, and ground-based remote sensing for infrastructure inspection- IoT-enabled real-time monitoring and digital twin integration for transportation infrastructure- Cybersecurity frameworks for data-driven infrastructure monitoring systems- Climate-responsive and sustainability-driven infrastructure management- Standards, interoperability, and scalable deployment of condition assessment technologies Topic editors: Annabel Dompey, Hwa Kian Chai, ZhiQiang Chen Source: https://www.frontiersin.org/research-topics/84384/data-driven-assessment-of-urban-transportation-infrastructure-ai-remote-sensing-and-iot-approaches-for-sustainable-management-of-pavements-bridges-and-tunnels