Application of machine learning-based AI in defect monitoring of earth retaining structures and tunnels of transport systems: A review

• A rare review of ML-b AI in defect monitoring of ERS and tunnels of transport systems. • Current state of AI adoption to replace human inspection in defect monitoring. • AI technologies in the market to enhance productivity in defect monitoring. • Challenges and limitations hindering the adoption of AI in defect monitoring. • Future AI research is required to address challenges and limitations. The transport system in a modern city is a complex and challenging web of roads, railways, metros, and pedestrian networks. The networks consist of various components, including transport tunnels and earth-retaining structures (ERS). Transport tunnels are passageways serving road traffic, trains, and pedestrians, while ERS are designed to support earth embankments and slopes along the road and rail networks. Inspecting these tunnels and ERS requires significant resources and planning, often using human inspectors which relies significantly on the experience and skill of trained personnel. Researchers have begun to consider employing artificial intelligence (AI) techniques to automate certain aspects of monitoring previously performed by personnel in a rapidly advancing area of interest. This article presents a rare review of machine learning-based AI (ML-b AI) techniques for defect monitoring of ERS and tunnels. It is organized based on different categories of ML-b AI defect detection techniques, including current development stages, practical impacts, and future directions, many aspects of which have not been reviewed previously. It contributes to much-needed literature on this topic and also highlights broad challenges faced by ML-b AI techniques for defect monitoring of ERS and tunnels, especially the lack of development in the detection of non-crack defects.