Plenary: Tamer

As the world confronts increasingly severe disasters—including floods, earthquakes, and conflicts—the need for rapid, accurate, and comprehensive damage assessment has become critical. Remote sensing, with its capability to provide timely, multi-scale, and multi-source data, has emerged as an indispensable tool in disaster management. This session presents an integrated framework for assessing the impacts of global disasters using advanced remote sensing techniques, with a particular focus on satellite imagery, including both optical and radar data. The integration of artificial intelligence (AI) and machine learning (ML) models with satellite data enables precise mapping and monitoring of affected areas, facilitating timely responses, sustainable strategies, and effective risk mitigation. The proposed framework incorporates data fusion and change detection algorithms to evaluate disaster impacts across local, regional, and global scales. Through case studies of recent global disasters—spanning both natural and human-induced events—the framework's effectiveness in assessing damage severity and supporting rapid response efforts is demonstrated. Each case study highlights the value of integrating diverse datasets to address limitations associated with individual data sources, such as cloud cover in optical imagery or signal noise in radar data. The findings underscore the transformative potential of intelligent remote sensing technologies in building resilient societies and fostering sustainability through informed decision-making. This research advances global efforts in disaster resilience and resource sustainability, addressing the pressing challenges of the contemporary era.