Airborne AI technology achieves precise detection of underwater munitions in shallow waters

On July 2, 2026, researchers at the University of Miami announced a breakthrough in detecting underwater munitions using airborne AI. This innovative method combines advanced multispectral sensing with artificial intelligence to identify unexploded ordnance (UXO) in shallow coastal waters, addressing a significant global safety concern.

Advanced Detection Technology for Coastal Safety

The study, published in the April issue of Frontiers in Marine Science, reveals that this new airborne imaging approach can reliably detect UXO, which poses ongoing hazards to public safety, marine ecosystems, and infrastructure. The research team, led by Ved Chirayath, utilized NASA technologies to enhance detection accuracy while minimizing false positives.

Chirayath emphasized the importance of this technology, stating, "Unexploded ordnance in shallow waters remains a serious global challenge. Our results demonstrate a scalable, airborne solution that can help improve detection accuracy and support safer coastal environments." The detection of UXO in waters less than 10 meters deep has traditionally been challenging due to limitations in conventional acoustic search methods.

Methodology and Results from Airborne Imaging Missions

The research team conducted airborne imaging missions over a test site at Broad Key in the northern Florida Keys. They deployed inert munitions and decoy objects across two locations, capturing images with drones equipped with NASA Fluid Lensing and MiDAR technologies. Fluid Lensing corrects distortions from ocean surface waves, while MiDAR provides active multispectral illumination.

The resulting imagery was instrumental in training a machine-learning model that successfully identified all deployed targets. The system maintained high precision even after weeks of biofouling and sediment accumulation, demonstrating its effectiveness in complex marine environments.

• All UXO targets detected in Fluid Lensing RGB images
• Active MiDAR sensing produced the highest precision
• Minimal false positives achieved across detection methods

Future Directions and Implications for Environmental Safety

While the study's results are promising, researchers acknowledge the need for further testing to expand the system's capabilities across various environments and types of munitions. Improved detection methods are crucial for reducing risks to coastal communities and preventing environmental contamination.

The integration of AI and advanced imaging technologies represents a significant advancement in marine safety, with potential applications beyond UXO detection. As the technology evolves, it may offer new solutions for monitoring and protecting marine ecosystems.