Researchers at The University of Osaka developed a deep learning model for rapid building damage assessment after floods using satellite imagery. This research establishes the first systematic benchmark for this task and introduces a novel semi-supervised learning method achieving 74% of fully supervised performance with just 10% of the labeled data. A new, lightweight deep learning model named Simple Prior Attention Disaster Assessment Net or SPADANet significantly reduces missed damaged buildings, improving recall by over 9% compared to existing models. This work provides crucial design principles for future AI disaster response, enabling faster and more efficient life-saving operations.

A new testing method could improve safety standards through better assessment of an overlooked hazard.

PFAS, a group of widely used industrial compounds known as ‘forever chemicals,’ is notoriously resistant to degradation and persists in the environment. A new dual-functional metal-organic framework, or MOF, created by University of Utah engineering researchers offers a scalable and field-deployable platform for effective remediation and monitoring of a major PFAS chemical known as perfluorooctanoic acid.