This special session invites contributions on the latest advances in indirect or “drive-by” methods for bridge modal identification and structural health monitoring (SHM). Using instrumented vehicles as mobile sensors has emerged as a scalable and cost-effective alternative to traditional bridge SHM, enabling more continuous and network-level condition assessment. In recent years, advances in machine learning and digital-twin technologies, among others, have further broadened the capabilities of drive-by approaches and improved their robustness under operational and environmental variability.

The session aims to bring together theoretical developments, algorithmic innovations, and practical case studies demonstrating the potential of drive-by SHM. Topics of interest include, but are not limited to:

• Bridge damage detection and condition monitoring using indirect methods
• Identification of modal properties from vehicle-sensing data
• Machine learning and physics-informed hybrid data models for drive-by SHM
• Building digital-twin platforms based on vehicle data
• Scalable monitoring strategies using fleets or crowdsourced vehicle measurements

Keywords: Drive-By, Bridge, Structural Health Monitoring, Machine Learning, Response Prediction

Track chairs

Abdollah Malekjafarian, University College Dublin

Yifu Lan, University of Cambridge

Ekin Ozer, University College Dublin