Small drones and ai evaluate disaster damage quickly in two states
Key Findings for Small UAS for Post-Disaster Damage Assessment from the CURSE'26 Exercise
Computer Vision and Pattern Recognition
Summary
After disasters like hurricanes, it's important to know which buildings and roads are damaged to help recovery efforts. The authors tested a small drone system with AI to quickly look at images and decide where damage happened. Their AI worked well for buildings in different places without extra changes, but had trouble with roads because of lighting and map mismatches. They also found using drones for this kind of work is now common, but there are challenges like needing faster data transfer and ethical concerns.
What this means in practice
- •For emergency management teams: Use drone-collected images with AI to quickly identify building damage across different states without needing manual corrections.
- •For drone operations teams: Time drone flights optimally to improve AI accuracy for assessing disaster damage in the field.
Authors
Thomas Manzini, Stephen Johnson, Priyankari Perali, David Merrick, Robin Murphy
Abstract
The CLARKE building and road damage assessment AI classifier was incorporated into the Catastrophic Unmanned Remote Sensing Exercise (CURSE) 2026, which trained 23 small uncrewed aerial systems (sUAS) teams from state and local agencies and non-governmental organizations in Florida and Missouri on how to collect imagery for an incident command Remote Sensing Cell. Although CLARKE has been operationally deployed to two hurricanes (Debby and Helene), CURSE'26 presented an opportunity to evaluate the machine learning model with a larger set of never-before-seen orthomosaics. The results show that building and road damage assessment together ran in 3.5 minutes on average, and that building damage assessment achieved a Micro F1 of 0.834 with no manual adjustments to correct spatial misalignment and delivered that performance in both Florida and Missouri, demonstrating good geographic transfer. It also showed that road damage assessment performed poorly due to sensitivity to misalignment between road maps and the images, and to lighting and environmental conditions in an urban setting. The analysis of CURSE'26 presents five other findings of value to the sUAS community: that the use of sUAS and machine learning is now operationally normalized and accepted, sUAS teams in the field can improve classification accuracy by timing their flights, exercises are good operational tests but their value for evaluating learning models is less clear, edge computing is needed to overcome the wireless upload barrier, and the application of sUAS and AI to disaster response has ethical and legal ramifications for pilots and data managers.