Bridge collapse prediction by small displacement data from satellite images under long-term monitoring

Thanks to developments of satellite sensors and synthetic aperture radar (SAR), it has been possible to exploit their benefits for long-term structural health monitoring (SHM) via satellite images. However, the major challenge in most of the long-term SHM projects is related to variations caused by environmental and/or operational variability (EOV). Therefore, the main objective of this study is to propose effective and efficient multi-stage unsupervised learning methods for addressing this limitation. Displacement samples extracted from a few satellite images of TerraSar-X regarding a long-term monitoring scheme of the Tadcaster Bridge is applied to validate the proposed method. Results show that the proposed methods effectively deal with the major challenges in the SAR-based SHM and provide practical tools for real applications.