The field of remote sensing and AI is moving towards more efficient and accurate methods for monitoring and assessing infrastructure damage. Researchers are exploring the use of cross-modal data, such as optical and SAR imagery, to improve detection and tracking capabilities. Additionally, there is a growing interest in using explainable AI techniques to better understand the impact of environmental factors, such as flooding, on pavement deterioration. The development of low-power and resource-efficient algorithms is also a key area of focus, particularly for onboard methane detection and other applications where computational resources are limited. Notable papers include:

• A novel dataset and method for cross-modal ship re-identification using optical and SAR imagery, which enables all-weather tracking and shorter re-imaging cycles.
• A deep learning framework for building damage assessment using VHR SAR and geospatial data, which demonstrates improved detection accuracy and generalizability to previously unseen areas.