In crisis situations, decision-makers rely on timely, accurate, and trustworthy information about hazard extent, exposed assets, and potential impacts to guide response actions and reduce risk. Recent advances in satellite, airborne, and UAV remote sensing—combined with ground-based sensors and IoT—now make near-real-time monitoring possible at regional to global scales, even in highly vulnerable areas. At the same time, AI and machine learning are accelerating the conversion of these data streams into actionable insights. However, key challenges remain, including scalability, robustness across diverse conditions, uncertainty quantification, and transparency in model behavior.
This session invites contributions that integrate multi-sensor observations with AI—particularly explainable and interpretable methods—to support hazard detection, damage and impact assessment, forecasting, and susceptibility/hazard/risk mapping. Relevant topics include rapid mapping and alert systems, multi-platform data fusion, UAV-enabled monitoring, benchmark datasets and standards, and best practices for training, evaluation, and trustworthy deployment in operational and crisis settings.