Interferometric Synthetic Aperture Radar (InSAR) processing is widely implemented to remotely inspect linear infrastructure, such as railway tracks, enabling a wide range of spatiotemporal coverage. Despite InSAR is nowadays integrated with other remote sensing data and in-situ measurements to establish structural health monitoring systems of railway infrastructure, the integration of this technology with other cutting-edge technologies can more effectively elevate automation in the rail sector through automated alerts and adaptive maintenance scheduling. This review paper provides details with respect to the integration of InSAR with other technologies, including cloud computing, Internet of Things (IoT), big data analytics, and artificial intelligence (AI), while also leveraging this space-borne information in geographic information system (GIS), building information modelling (BIM), and digital twin platforms within the lifecycle of both ballasted and ballastless railway tracks to promote railway infrastructure health monitoring. Generally, AI-driven analytics deployed on multi-source multi-scale data (with inclusion of InSAR) are characterized as key enablers to develop predictive maintenance based on InSAR processing data. Additionally, InSAR-integrated robust digital platforms ensure continuous access to high-fidelity geoinformation, thereby facilitating informed decision-making. Overall, from coarse to fine semantic integration of InSAR data for structural control, GIS facilitates multi-layer fusion of multi-modal RS data for health monitoring railway corridors at the network-level, while the digital twin exploits IoT-enabled multi-modal data and AI-driven models to detect surface and subsurface structural anomalies at the project level, thereby supporting inspection and maintenance planning of railway tracks in a formalised, knowledge-based environment.
Koohmishi et al. (Tue,) studied this question.