Multi-Temporal SAR Interferometry for Structural Assessment of Bridges: flood event of PO river 2019

This thesis aims to demonstrate the potential of satellite-based remote sensing techniques in developing an innovative health-monitoring method for detecting anomalies across multiple bridges within a geographical region, by analyzing their response to common environmental factors such as air temperature and time-varying water level. An “anomaly index” is evaluated for seven bridges on the Po River (Italy) in two scenarios: first by analyzing each bridge individually and comparing its behavior during documented flood and erosion events to its normal behavior prior to the flood; and second, by using a transfer learning approach that allows for the detection of anomalies based on deviations in the behavior of one bridge relative to the others, thus not relying on past data. Simulated and real case studies involving steel railway bridges spanning the Po River demonstrate the effectiveness of the proposed approach, highlighting its potential for large-scale applications.